system

Abstract

The system according to this embodiment aims to understand the level of comprehension of new employees and provide appropriate guidance. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a consultation promotion unit, and an assist unit. The collection unit collects what the new employee understands. The analysis unit analyzes the information collected by the collection unit. The consultation promotion unit prompts the new employee to consult with a supervisor for urgent matters based on the information analyzed by the analysis unit. The assist unit assists the supervisor with questions while conveying the prerequisites to them based on the consultations prompted by the consultation promotion unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, it is difficult to grasp the understanding level of new employees and provide appropriate guidance, and there is room for improvement in efficient new employee training.

[0005] The system according to the embodiment aims to grasp the understanding level of new employees and provide appropriate guidance.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a consultation promotion unit, and an assistance unit. The collection unit collects what the new employee understands. The analysis unit analyzes the information collected by the collection unit. The consultation promotion unit prompts the new employee to consult with a supervisor for urgent matters based on the information analyzed by the analysis unit. The assistance unit assists the supervisor with questions while conveying prerequisites based on the consultations prompted by the consultation promotion unit. [Effects of the Invention]

[0007] The system according to this embodiment can grasp the level of understanding of new employees and provide appropriate guidance. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The mentoring system according to an embodiment of the present invention is an innovative system that provides 24-hour support for the growth of new employees. This mentoring system utilizes individualized learning plans, real-time work support, and a rich knowledge database, and works in conjunction with human supervisors and senior colleagues to achieve efficient and consistent new employee training. It contributes to improving the productivity of the entire organization through the transfer of experience and the maximization of individual potential. For example, the mentoring system collects what the new employee understands. What the new employee has learned is recorded in notes and shared with agents. For example, information such as "This specification document is scheduled to be provided tomorrow, and I don't understand the content on page 17" is shared. Next, the mentoring system analyzes the information on chats and documents and provides explanations in language that the new employee understands. For example, it provides an explanation such as "On-premise is like Apigee, which we learned about the other day, and we are talking about the normal situation where a 200 response is returned." Furthermore, the mentoring system analyzes the chat content and prompts consultation with a mentor for urgent matters. For example, it provides advice such as "This is about on-premise. Consult with your mentor immediately!" The mentoring system also assists with questions while conveying the prerequisites to the mentor. For example, information such as, "The new employee currently has an incomplete understanding of on-premises systems. They are aware that one of the on-premises systems is Apigee. Please prioritize teaching them this task, as it is due tomorrow," might be provided. This agent-assisted support reduces the workload on the department and allows for significant growth in the new employee. In this way, the training system can efficiently support the growth of new employees.

[0029] The instruction system according to this embodiment comprises a collection unit, an analysis unit, a consultation promotion unit, and an assistance unit. The collection unit collects what new employees understand. The collection unit collects information, for example, by having new employees record what they have learned in notes. The collection unit can also collect information through, for example, questionnaires or interviews. The collection unit can also grasp the level of understanding of new employees through observation. The analysis unit analyzes the information collected by the collection unit. The analysis unit analyzes the information using, for example, data analysis techniques. The analysis unit can also evaluate the level of understanding of new employees using, for example, statistical analysis. The analysis unit can also analyze the information using text mining techniques. The consultation promotion unit prompts new employees to consult with their instructors for urgent matters based on the information analyzed by the analysis unit. The consultation promotion unit prompts new employees to consult with their instructors using, for example, notifications or alerts. The consultation promotion unit can also prompt new employees to consult with their instructors using, for example, reminders. The consultation promotion unit can also prioritize notifying instructors of urgent matters. The Assist Unit assists the instructor with questions while conveying prerequisites based on consultations facilitated by the Consultation Facilitation Unit. The Assist Unit supports the instructor, for example, by providing question templates. The Assist Unit can also assist the instructor using support tools, for example. The Assist Unit can also support the instructor by providing background information and relevant data. This allows the instruction system according to the embodiment to efficiently support the growth of new employees. Some or all of the above-described processes in the Collection Unit, Analysis Unit, Consultation Facilitation Unit, and Assist Unit may be performed using AI, for example, or without AI. For example, when a new employee records what they have learned in a memo, the Collection Unit can use AI to analyze the contents of the memo and evaluate the level of understanding. The Analysis Unit can input the collected information into the AI, which can then analyze the information. The Consultation Facilitation Unit can use AI to automatically determine which consultations are urgent and notify the instructor. The Assist Unit can use AI to generate question templates and provide them to the instructor.

[0030] The data collection department collects information on what new employees understand. For example, this information is collected when new employees record what they have learned in notes. Specifically, new employees use a dedicated application to record the knowledge and skills they acquire through daily work and training. This application automatically saves the contents of the notes to the cloud, making them accessible to the data collection department. The data collection department can also collect information through surveys and interviews. Surveys are sent to new employees regularly, and the responses are stored in a database. Interviews are conducted via video calls or in person, and the content is recorded and videotaped for later analysis. Furthermore, the data collection department can assess new employees' understanding through observation. For example, supervisors and mentors observe new employees' work performance and record it on evaluation sheets. These evaluation sheets are sent to the data collection department and integrated with other data. This allows the data collection department to understand new employees' understanding from multiple perspectives and collect detailed data. Additionally, the data collection department can centrally manage this data and collaborate with other departments as needed. For example, collected data is stored on a cloud server and made accessible to the analysis and consultation departments. Furthermore, by adjusting the frequency and accuracy of data collection, flexible responses can be made to specific situations and conditions. This allows the data collection department to collect data efficiently and effectively, improving the overall system performance.

[0031] The Analysis Department analyzes the information collected by the Collection Department. For example, the Analysis Department uses data analysis techniques to analyze the information. Specifically, it analyzes collected notes, questionnaires, and interview content using text mining techniques to extract frequently occurring keywords and phrases. This allows for an understanding of the knowledge and skills acquired by new employees. Furthermore, statistical analysis can be used to evaluate the understanding of new employees. For example, questionnaire responses are compiled and the distribution and trends of understanding are analyzed. In addition, AI can be used to analyze the collected information. AI uses natural language processing techniques to analyze text data, evaluate understanding, and identify problems. For example, AI can analyze the content of new employees' notes and identify areas of high and low understanding. This allows the Analysis Department to quickly and accurately analyze collected data and grasp the understanding of new employees. Furthermore, the Analysis Department can utilize historical data and statistical information to analyze long-term trends and patterns. For example, based on past data of new employees, it can predict fluctuations in understanding at specific times and under specific conditions and formulate future countermeasures. Furthermore, by using anomaly detection algorithms, it is possible to detect unusual patterns and abnormal data and issue warnings early. This allows the analysis unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the entire system.

[0032] The Consultation Promotion Department prompts new employees to consult with their mentors for urgent matters based on information analyzed by the Analysis Department. Specifically, it uses AI to automatically determine the urgency of matters and notify mentors. For example, the AI ​​identifies areas where new employees have difficulty understanding or problems based on the analyzed data and assesses their urgency. If it is determined to be urgent, it sends a notification or alert to the mentor. Notifications are sent via email or messaging apps to enable mentors to respond quickly. It can also use reminders to prompt mentors to consult. Reminders are sent to mentors regularly to ensure they do not forget matters that require attention. Furthermore, the Consultation Promotion Department can prioritize notifying mentors of urgent matters. For example, the AI ​​identifies the most urgent issue from among multiple issues and notifies mentors of it as a priority. This allows mentors to respond quickly to important issues. In addition, the Consultation Promotion Department also supports mentors in taking appropriate action. For example, it provides mentors with detailed information and background information on the problem and suggests appropriate response methods. This allows the consultation promotion department to support mentors in responding quickly and appropriately, thereby efficiently promoting the growth of new employees.

[0033] The Assistance Department assists instructors with questions while communicating prerequisites based on consultations facilitated by the Consultation Facilitation Department. Specifically, it generates question templates using AI and provides them to instructors. For example, the AI ​​generates question templates that instructors should ask new employees based on collected data and analysis results. These templates include specific question content, question order, and intent, enabling instructors to ask questions efficiently. The Assistance Department can also assist instructors using support tools. For example, it installs a dedicated assistance tool on the tablet or PC used by instructors, providing real-time support when instructors ask questions. This tool has the function of suggesting appropriate answer examples and additional questions as instructors input questions. Furthermore, the Assistance Department can support instructors by providing background information and relevant data. For example, it provides instructors with the new employee's past learning history and evaluation results of their comprehension level, enabling instructors to understand the new employee's situation and provide appropriate guidance. In this way, the Assistance Department can support instructors in efficiently and effectively guiding new employees and promote their growth. Furthermore, the support unit can collect feedback from instructors and continuously improve the accuracy of question templates and support tools. This allows the support unit to provide optimal support for both instructors and new employees, thereby improving the overall performance of the system.

[0034] The memo section allows new employees to record what they have learned in notes. The memo section allows new employees to record notes by hand, for example. The memo section also allows new employees to record notes in digital format, for example. The memo section allows new employees to set the frequency of note recording, for example. This makes it easier for new employees to organize what they have learned by recording it in notes. Some or all of the above processes in the memo section may be performed using AI, for example, or not using AI. For example, the memo section can input the notes recorded by new employees into an AI, which can then analyze the contents of the notes.

[0035] The analysis unit includes an explanation unit that analyzes chat and document screen information and provides explanations in language that new employees understand. For example, the explanation unit can analyze chat text data and provide explanations in language that new employees can easily understand. The explanation unit can also analyze document screen information and provide explanations in language that new employees can easily understand. The explanation unit can also replace technical terms with everyday terms when providing explanations. This improves the level of understanding by providing explanations in language that new employees understand. Some or all of the above processing in the explanation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the explanation unit can input chat text data into a generative AI, and the generative AI can generate explanations in language that new employees can easily understand.

[0036] The Consultation Facilitation Department encourages consultation with supervisors for urgent matters. The Consultation Facilitation Department can assess urgency based on, for example, the importance of the task. The Consultation Facilitation Department can also assess urgency based on, for example, the approaching deadline. The Consultation Facilitation Department can also encourage consultation with supervisors using, for example, notifications or alerts. This enables a swift response by prompting consultation with supervisors for urgent matters. Some or all of the above processes in the Consultation Facilitation Department may be performed using, for example, AI, or not using AI. For example, the Consultation Facilitation Department can input the importance of the task and the approaching deadline into the AI, which can then assess the urgency and notify the supervisor.

[0037] The assistance unit assists the instructor with questions while communicating prerequisites. The assistance unit supports the instructor by, for example, providing background information. The assistance unit can also support the instructor by, for example, providing relevant data. The assistance unit can also support the instructor by, for example, providing question templates. This improves the efficiency of instruction by assisting the instructor with questions while communicating prerequisites. Some or all of the above processing in the assistance unit may be performed using, for example, AI, or not using AI. For example, the assistance unit can input background information and relevant data into the AI, and the AI ​​can generate question templates and provide them to the instructor.

[0038] The workload reduction unit reduces the workload of departments with the support of agents. The workload reduction unit can, for example, distribute tasks. The workload reduction unit can also, for example, use efficiency tools to streamline operations. The workload reduction unit can also reduce the workload by, for example, setting task priorities. This enables efficient business operations by reducing the workload of departments with the support of agents. Some or all of the above processes in the workload reduction unit may be performed using AI, for example, or not using AI. For example, the workload reduction unit can input task distribution into AI, and the AI ​​can propose the optimal task distribution.

[0039] The data collection unit analyzes the new employee's past learning history and selects the optimal information collection method. For example, the data collection unit focuses on collecting information in areas where the new employee has a low level of understanding, based on what they have learned in the past. The data collection unit can also analyze the learning methods (videos, texts, etc.) used by the new employee in the past and select the optimal information collection method. For example, the data collection unit can select learning methods that are effective at specific times of day based on the new employee's past learning history and collect information. In this way, the optimal information collection method can be selected by analyzing the new employee's past learning history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input the new employee's past learning history into AI, and the AI ​​can select the optimal information collection method.

[0040] The data collection unit dynamically changes the priority of the information to be collected based on the new employee's work progress. For example, if a new employee completes a specific task, the data collection unit prioritizes collecting information related to that task. The data collection unit can also prioritize collecting information related to tasks that a new employee is behind on. For example, if a new employee starts a new task, the data collection unit can also prioritize collecting information related to that task. This enables efficient information collection by dynamically changing the priority of information based on the new employee's work progress. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input the new employee's work progress into the AI, which can then dynamically change the priority of information.

[0041] The data collection unit prioritizes collecting highly relevant information, taking into account the geographical location of new employees. For example, if a new employee is in a specific office, the data collection unit prioritizes collecting information related to that office. If a new employee is on a business trip, the data collection unit may also prioritize collecting information related to their business trip destination. If a new employee is working remotely, the data collection unit may also prioritize collecting information related to resources accessible from their home. This allows for the priority collection of highly relevant information by considering the geographical location of new employees. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input the geographical location of new employees into an AI, which can then prioritize collecting highly relevant information.

[0042] The data collection unit analyzes the social media activities of new employees and collects relevant information. For example, the data collection unit collects relevant information based on the interests and passions that new employees share on social media. The data collection unit can also collect relevant information by analyzing posts from experts and industry leaders that new employees follow on social media. The data collection unit can also collect relevant information by analyzing the activities of groups and communities that new employees participate in on social media. In this way, relevant information can be collected by analyzing the social media activities of new employees. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input new employees' social media activity data into AI, and the AI ​​can collect relevant information.

[0043] The analysis unit adjusts the level of detail of the analysis based on the importance of the collected information. For example, the analysis unit performs a detailed analysis on information of high importance. The analysis unit can also perform a concise analysis on information of low importance. The analysis unit can also perform an analysis of moderate level of detail on information of moderate importance. By adjusting the level of detail of the analysis based on the importance of the collected information, efficient information analysis becomes possible. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the collected information into the AI, and the AI ​​can adjust the level of detail of the analysis.

[0044] The analysis unit applies different analysis algorithms depending on the category of information. For example, the analysis unit applies a technical analysis algorithm to technical information. The analysis unit can also apply a market analysis algorithm to market information. The analysis unit can also apply a human resources analysis algorithm to human resources information. By applying different analysis algorithms depending on the category of information, appropriate information analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of information into the AI, and the AI ​​can apply an appropriate analysis algorithm.

[0045] The analysis department determines the priority of analysis based on when the information was submitted. For example, the analysis department prioritizes the analysis of recently submitted information. The analysis department may also postpone the analysis of older information. The analysis department may also moderately analyze information with a moderate submission date. This allows for efficient information analysis by determining the priority of analysis based on when the information was submitted. Some or all of the above processes in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department can input the submission dates of the information into the AI, and the AI ​​can determine the priority of analysis.

[0046] The analysis unit adjusts the order of analysis based on the relevance of the information. For example, the analysis unit prioritizes the analysis of highly relevant information. The analysis unit may also postpone the analysis of less relevant information. The analysis unit may also moderately analyze information of moderate relevance. By adjusting the order of analysis based on the relevance of the information, efficient information analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the information into the AI, and the AI ​​can adjust the order of analysis.

[0047] The Consultation Promotion Department selects the most suitable consultation method by referring to past consultation history. For example, the Consultation Promotion Department prioritizes suggesting consultation methods previously used by new employees (chat, telephone, etc.). The Consultation Promotion Department can also select the most effective consultation method from a new employee's past consultation history. For example, the Consultation Promotion Department can suggest the most suitable consultation method based on the content of past consultations by new employees. In this way, the most suitable consultation method can be selected by referring to past consultation history. Some or all of the above processes in the Consultation Promotion Department may be performed using AI, for example, or not. For example, the Consultation Promotion Department can input past consultation history into AI, and the AI ​​can select the most suitable consultation method.

[0048] The consultation promotion department applies different promotion methods depending on the category of the consultation. For example, the consultation promotion department applies technical promotion methods to technical consultations. For example, the consultation promotion department may also apply human resources promotion methods to human resources consultations. For example, the consultation promotion department may also apply market promotion methods to market-related consultations. By applying different promotion methods depending on the category of the consultation, appropriate consultation promotion becomes possible. Some or all of the above processing in the consultation promotion department may be performed using AI, for example, or not using AI. For example, the consultation promotion department can input the category of the consultation into the AI, and the AI ​​can apply an appropriate promotion method.

[0049] The consultation promotion department determines priorities based on when the consultation content is submitted. For example, the consultation promotion department will prioritize recently submitted consultations. For example, the consultation promotion department may postpone older consultations. For example, the consultation promotion department may process consultations of moderate age appropriately. This allows for efficient consultation promotion by determining priorities based on when the consultation content is submitted. Some or all of the above processing in the consultation promotion department may be performed using AI, for example, or not using AI. For example, the consultation promotion department can input the submission dates of consultation content into AI, and the AI ​​can determine the priorities.

[0050] The consultation facilitation department adjusts the order of consultations based on their relevance. For example, the consultation facilitation department prioritizes processing consultations with high relevance. For example, the consultation facilitation department may postpone consultations with low relevance. For example, the consultation facilitation department may process consultations with moderate relevance appropriately. This allows for efficient consultation facilitation by adjusting the order based on the relevance of the consultations. Some or all of the above processing in the consultation facilitation department may be performed using AI, for example, or not using AI. For example, the consultation facilitation department can input the relevance of the consultations into the AI, and the AI ​​can adjust the order.

[0051] The assistance unit adjusts the level of detail of the assistance based on the importance of the question. For example, the assistance unit provides detailed assistance for high-importance questions. For example, the assistance unit can provide concise assistance for low-importance questions. For example, the assistance unit can provide assistance with an appropriate level of detail for questions of moderate importance. This allows for efficient support by adjusting the level of detail of the assistance based on the importance of the question. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the importance of the question into the AI, and the AI ​​can adjust the level of detail of the assistance.

[0052] The assistance unit applies different assistance algorithms depending on the category of the question. For example, the assistance unit applies a technical assistance algorithm to a technical question. For example, the assistance unit can also apply a human resources assistance algorithm to a human resources question. For example, the assistance unit can also apply a market-related assistance algorithm to a market-related question. By applying different assistance algorithms depending on the category of the question, appropriate support can be provided. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the category of the question into the AI, and the AI ​​can apply an appropriate assistance algorithm.

[0053] The assistance unit determines the priority of assistance based on when the questions were submitted. For example, the assistance unit will prioritize assistance for recently submitted questions. The assistance unit may also postpone assistance for older questions. For example, the assistance unit may provide appropriate assistance for questions submitted at a moderate time. This allows for efficient support by determining the priority of assistance based on when the questions were submitted. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the submission dates of the questions into the AI, which can then determine the priority of assistance.

[0054] The assistance unit adjusts the order of assistance based on the relevance of the questions. For example, the assistance unit prioritizes assisting with questions that are highly relevant. The assistance unit may also postpone assisting with questions that are less relevant. The assistance unit may also provide appropriate assistance to questions that are moderately relevant. This allows for efficient support by adjusting the order of assistance based on the relevance of the questions. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the relevance of the questions into the AI, which can then adjust the order of assistance.

[0055] The note-taking section adjusts the level of detail in the notes based on the importance of the learning content. For example, the note-taking section records detailed notes for highly important learning content. For example, the note-taking section can also record concise notes for less important learning content. For example, the note-taking section can record notes with a moderate level of detail for moderately important learning content. This allows for efficient note-taking by adjusting the level of detail in the notes based on the importance of the learning content. Some or all of the above processing in the note-taking section may be performed using AI, for example, or without AI. For example, the note-taking section can input the importance of the learning content into the AI, and the AI ​​can adjust the level of detail in the notes.

[0056] The note-taking section applies different recording methods depending on the category of the learning content. For example, the note-taking section applies a technical note-taking method to technical learning content. The note-taking section can also apply a human resources note-taking method to human resources learning content. The note-taking section can also apply a market-related note-taking method to market-related learning content. By applying different recording methods depending on the category of the learning content, appropriate note-taking becomes possible. Some or all of the above processing in the note-taking section may be performed using AI, for example, or without AI. For example, the note-taking section can input the category of the learning content into the AI, and the AI ​​can apply an appropriate recording method.

[0057] The explanation section adjusts the level of detail in the explanation based on the importance of the learning content. For example, the explanation section provides detailed explanations for highly important learning content. For example, the explanation section can provide concise explanations for less important learning content. For example, the explanation section can provide explanations of moderate importance. By adjusting the level of detail in the explanation based on the importance of the learning content, efficient explanations become possible. Some or all of the above processing in the explanation section may be performed using AI, for example, or without AI. For example, the explanation section can input the importance of the learning content into the AI, and the AI ​​can adjust the level of detail in the explanation.

[0058] The explanation unit applies different explanation methods depending on the category of the learning content. For example, the explanation unit applies a technical explanation method to technical learning content. For example, the explanation unit can also apply a human resources explanation method to human resources learning content. For example, the explanation unit can also apply a market-related explanation method to market-related learning content. By applying different explanation methods depending on the category of the learning content, appropriate explanations become possible. Some or all of the above processing in the explanation unit may be performed using AI, for example, or without AI. For example, the explanation unit can input the category of the learning content into the AI, and the AI ​​can apply an appropriate explanation method.

[0059] The workload reduction unit adjusts the level of detail in workload reduction based on the importance of the tasks. For example, the workload reduction unit performs detailed workload reduction for tasks of high importance. The workload reduction unit can also perform simple workload reduction for tasks of low importance. The workload reduction unit can also perform workload reduction with an appropriate level of detail for tasks of medium importance. By adjusting the level of detail in workload reduction based on the importance of the tasks, efficient workload reduction becomes possible. Some or all of the above processing in the workload reduction unit may be performed using AI, for example, or without AI. For example, the workload reduction unit can input the importance of the tasks into the AI, and the AI ​​can adjust the level of detail in workload reduction.

[0060] The load reduction unit applies different load reduction methods depending on the category of work content. For example, the load reduction unit applies a technical load reduction method to technical tasks. The load reduction unit can also apply a human resources load reduction method to human resources tasks. The load reduction unit can also apply a market-related load reduction method to market-related tasks. By applying different load reduction methods depending on the category of work content, appropriate load reduction becomes possible. Some or all of the above processing in the load reduction unit may be performed using AI, for example, or without AI. For example, the load reduction unit can input the category of work content into the AI, and the AI ​​can apply an appropriate load reduction method.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The training system further includes a feedback section. The feedback section evaluates the work performance of new employees and provides appropriate feedback. For example, the feedback section can evaluate the quality of tasks completed by new employees and point out areas for improvement. It can also monitor the progress of new employees and evaluate their achievement of goals. Furthermore, the feedback section can compare the self-assessment of new employees with the assessment of their supervisors and provide advice to bridge the gap. This allows new employees to obtain concrete guidance for self-improvement. Some or all of the above processes in the feedback section may be performed using AI, for example, or not. For example, the feedback section can input the work data of new employees into an AI, which can then generate evaluations and feedback.

[0063] The memo section can also be equipped with a voice input function. The voice input function allows new employees to record notes by voice. For example, new employees can take notes by voice during meetings. The voice input function can also convert voice to text using speech recognition technology and save it as a digital memo. Furthermore, the voice input function can also search and edit memos using voice commands. This allows new employees to efficiently record and manage notes without using their hands. Some or all of the above processing in the voice input function may be performed using AI, for example, or not using AI. For example, the voice input function can input the new employee's voice data into AI, which can then convert the voice to text.

[0064] The explanatory section can also be equipped with a visual aid function. The visual aid function uses diagrams and graphs to explain things in a way that is easy for new employees to understand. For example, the explanatory section can show complex processes using flowcharts. It can also visually show data trends using graphs. Furthermore, the explanatory section can summarize information concisely using infographics. This allows new employees to deepen their understanding through visual information. Some or all of the above processing in the visual aid function may be performed using AI, for example, or not using AI. For example, the explanatory section can input data into AI, and the AI ​​can generate appropriate visual aids.

[0065] The data collection unit can further consider the geographical location of new employees to prioritize the collection of highly relevant information. For example, if a new employee is in a specific office, it can prioritize the collection of information related to that office. Similarly, if a new employee is on a business trip, it can prioritize the collection of information related to their destination. Furthermore, if a new employee is working remotely, it can prioritize the collection of information related to resources accessible from their home. This allows for the prioritization of highly relevant information by considering the geographical location of new employees. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For instance, the data collection unit could input the geographical location of new employees into an AI, which could then prioritize the collection of highly relevant information.

[0066] The analysis unit can apply different analysis algorithms depending on the category of information. For example, a technical analysis algorithm can be applied to technical information. A market analysis algorithm can also be applied to market information. Furthermore, a human resources analysis algorithm can be applied to human resources information. By applying different analysis algorithms depending on the category of information, appropriate information analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of information into the AI, and the AI ​​can apply an appropriate analysis algorithm.

[0067] The Consultation Promotion Department can further select the most suitable consultation method by referring to past consultation history. For example, it can prioritize suggesting consultation methods previously used by new employees (chat, telephone, etc.). It can also select the most effective consultation method from the new employee's past consultation history. Furthermore, it can suggest the most suitable consultation method based on the content of past consultations by new employees. In this way, the most suitable consultation method can be selected by referring to past consultation history. Some or all of the above processes in the Consultation Promotion Department may be performed using AI, for example, or not. For example, the Consultation Promotion Department can input past consultation history into AI, and the AI ​​can select the most suitable consultation method.

[0068] The assistance unit can apply different assistance algorithms depending on the category of the question. For example, a technical assistance algorithm can be applied to a technical question. Similarly, a human resources assistance algorithm can be applied to a human resources question. Furthermore, a market-related assistance algorithm can be applied to a market-related question. This allows for appropriate support by applying different assistance algorithms depending on the category of the question. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the category of the question into the AI, which can then apply an appropriate assistance algorithm.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The information gathering department collects what new employees understand. For example, information is collected by having new employees take notes on what they have learned. Information can also be collected through questionnaires and interviews. Furthermore, the level of understanding of new employees can be grasped through observation. Step 2: The analysis department analyzes the information collected by the collection department. For example, they analyze the information using data analysis techniques and statistical analysis to evaluate the level of understanding of new employees. They can also analyze the information using text mining techniques. Step 3: The Consultation Facilitation Department, based on the information analyzed by the Analysis Department, encourages consultations with supervisors for urgent cases. For example, they can use notifications, alerts, and reminders to prompt consultations with supervisors. They can also prioritize notifying supervisors of urgent cases. Step 4: The Assistance Department assists the instructor with questions, communicating prerequisites based on the consultation facilitated by the Consultation Facilitation Department. For example, they support the instructor by providing question templates. They can also assist the instructor by providing support tools, background information, and relevant data.

[0071] (Example of form 2) The mentoring system according to an embodiment of the present invention is an innovative system that provides 24-hour support for the growth of new employees. This mentoring system utilizes individualized learning plans, real-time work support, and a rich knowledge database, and works in conjunction with human supervisors and senior colleagues to achieve efficient and consistent new employee training. It contributes to improving the productivity of the entire organization through the transfer of experience and the maximization of individual potential. For example, the mentoring system collects what the new employee understands. What the new employee has learned is recorded in notes and shared with agents. For example, information such as "This specification document is scheduled to be provided tomorrow, and I don't understand the content on page 17" is shared. Next, the mentoring system analyzes the information on chats and documents and provides explanations in language that the new employee understands. For example, it provides an explanation such as "On-premise is like Apigee, which we learned about the other day, and we are talking about the normal situation where a 200 response is returned." Furthermore, the mentoring system analyzes the chat content and prompts consultation with a mentor for urgent matters. For example, it provides advice such as "This is about on-premise. Consult with your mentor immediately!" The mentoring system also assists with questions while conveying the prerequisites to the mentor. For example, information such as, "The new employee currently has an incomplete understanding of on-premises systems. They are aware that one of the on-premises systems is Apigee. Please prioritize teaching them this task, as it is due tomorrow," might be provided. This agent-assisted support reduces the workload on the department and allows for significant growth in the new employee. In this way, the training system can efficiently support the growth of new employees.

[0072] The instruction system according to this embodiment comprises a collection unit, an analysis unit, a consultation promotion unit, and an assistance unit. The collection unit collects what new employees understand. The collection unit collects information, for example, by having new employees record what they have learned in notes. The collection unit can also collect information through, for example, questionnaires or interviews. The collection unit can also grasp the level of understanding of new employees through observation. The analysis unit analyzes the information collected by the collection unit. The analysis unit analyzes the information using, for example, data analysis techniques. The analysis unit can also evaluate the level of understanding of new employees using, for example, statistical analysis. The analysis unit can also analyze the information using text mining techniques. The consultation promotion unit prompts new employees to consult with their instructors for urgent matters based on the information analyzed by the analysis unit. The consultation promotion unit prompts new employees to consult with their instructors using, for example, notifications or alerts. The consultation promotion unit can also prompt new employees to consult with their instructors using, for example, reminders. The consultation promotion unit can also prioritize notifying instructors of urgent matters. The Assist Unit assists the instructor with questions while conveying prerequisites based on consultations facilitated by the Consultation Facilitation Unit. The Assist Unit supports the instructor, for example, by providing question templates. The Assist Unit can also assist the instructor using support tools, for example. The Assist Unit can also support the instructor by providing background information and relevant data. This allows the instruction system according to the embodiment to efficiently support the growth of new employees. Some or all of the above-described processes in the Collection Unit, Analysis Unit, Consultation Facilitation Unit, and Assist Unit may be performed using AI, for example, or without AI. For example, when a new employee records what they have learned in a memo, the Collection Unit can use AI to analyze the contents of the memo and evaluate the level of understanding. The Analysis Unit can input the collected information into the AI, which can then analyze the information. The Consultation Facilitation Unit can use AI to automatically determine which consultations are urgent and notify the instructor. The Assist Unit can use AI to generate question templates and provide them to the instructor.

[0073] The data collection department collects information on what new employees understand. For example, this information is collected when new employees record what they have learned in notes. Specifically, new employees use a dedicated application to record the knowledge and skills they acquire through daily work and training. This application automatically saves the contents of the notes to the cloud, making them accessible to the data collection department. The data collection department can also collect information through surveys and interviews. Surveys are sent to new employees regularly, and the responses are stored in a database. Interviews are conducted via video calls or in person, and the content is recorded and videotaped for later analysis. Furthermore, the data collection department can assess new employees' understanding through observation. For example, supervisors and mentors observe new employees' work performance and record it on evaluation sheets. These evaluation sheets are sent to the data collection department and integrated with other data. This allows the data collection department to understand new employees' understanding from multiple perspectives and collect detailed data. Additionally, the data collection department can centrally manage this data and collaborate with other departments as needed. For example, collected data is stored on a cloud server and made accessible to the analysis and consultation departments. Furthermore, by adjusting the frequency and accuracy of data collection, flexible responses can be made to specific situations and conditions. This allows the data collection department to collect data efficiently and effectively, improving the overall system performance.

[0074] The Analysis Department analyzes the information collected by the Collection Department. For example, the Analysis Department uses data analysis techniques to analyze the information. Specifically, it analyzes collected notes, questionnaires, and interview content using text mining techniques to extract frequently occurring keywords and phrases. This allows for an understanding of the knowledge and skills acquired by new employees. Furthermore, statistical analysis can be used to evaluate the understanding of new employees. For example, questionnaire responses are compiled and the distribution and trends of understanding are analyzed. In addition, AI can be used to analyze the collected information. AI uses natural language processing techniques to analyze text data, evaluate understanding, and identify problems. For example, AI can analyze the content of new employees' notes and identify areas of high and low understanding. This allows the Analysis Department to quickly and accurately analyze collected data and grasp the understanding of new employees. Furthermore, the Analysis Department can utilize historical data and statistical information to analyze long-term trends and patterns. For example, based on past data of new employees, it can predict fluctuations in understanding at specific times and under specific conditions and formulate future countermeasures. Furthermore, by using anomaly detection algorithms, it is possible to detect unusual patterns and abnormal data and issue warnings early. This allows the analysis unit to not only grasp the situation in real time but also to handle long-term risk management and anomaly detection, thereby improving the reliability and safety of the entire system.

[0075] The Consultation Promotion Department prompts new employees to consult with their mentors for urgent matters based on information analyzed by the Analysis Department. Specifically, it uses AI to automatically determine the urgency of matters and notify mentors. For example, the AI ​​identifies areas where new employees have difficulty understanding or problems based on the analyzed data and assesses their urgency. If it is determined to be urgent, it sends a notification or alert to the mentor. Notifications are sent via email or messaging apps to enable mentors to respond quickly. It can also use reminders to prompt mentors to consult. Reminders are sent to mentors regularly to ensure they do not forget matters that require attention. Furthermore, the Consultation Promotion Department can prioritize notifying mentors of urgent matters. For example, the AI ​​identifies the most urgent issue from among multiple issues and notifies mentors of it as a priority. This allows mentors to respond quickly to important issues. In addition, the Consultation Promotion Department also supports mentors in taking appropriate action. For example, it provides mentors with detailed information and background information on the problem and suggests appropriate response methods. This allows the consultation promotion department to support mentors in responding quickly and appropriately, thereby efficiently promoting the growth of new employees.

[0076] The Assistance Department assists instructors with questions while communicating prerequisites based on consultations facilitated by the Consultation Facilitation Department. Specifically, it generates question templates using AI and provides them to instructors. For example, the AI ​​generates question templates that instructors should ask new employees based on collected data and analysis results. These templates include specific question content, question order, and intent, enabling instructors to ask questions efficiently. The Assistance Department can also assist instructors using support tools. For example, it installs a dedicated assistance tool on the tablet or PC used by instructors, providing real-time support when instructors ask questions. This tool has the function of suggesting appropriate answer examples and additional questions as instructors input questions. Furthermore, the Assistance Department can support instructors by providing background information and relevant data. For example, it provides instructors with the new employee's past learning history and evaluation results of their comprehension level, enabling instructors to understand the new employee's situation and provide appropriate guidance. In this way, the Assistance Department can support instructors in efficiently and effectively guiding new employees and promote their growth. Furthermore, the support unit can collect feedback from instructors and continuously improve the accuracy of question templates and support tools. This allows the support unit to provide optimal support for both instructors and new employees, thereby improving the overall performance of the system.

[0077] The memo section allows new employees to record what they have learned in notes. The memo section allows new employees to record notes by hand, for example. The memo section also allows new employees to record notes in digital format, for example. The memo section allows new employees to set the frequency of note recording, for example. This makes it easier for new employees to organize what they have learned by recording it in notes. Some or all of the above processes in the memo section may be performed using AI, for example, or not using AI. For example, the memo section can input the notes recorded by new employees into an AI, which can then analyze the contents of the notes.

[0078] The analysis unit includes an explanation unit that analyzes chat and document screen information and provides explanations in language that new employees understand. For example, the explanation unit can analyze chat text data and provide explanations in language that new employees can easily understand. The explanation unit can also analyze document screen information and provide explanations in language that new employees can easily understand. The explanation unit can also replace technical terms with everyday terms when providing explanations. This improves the level of understanding by providing explanations in language that new employees understand. Some or all of the above processing in the explanation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the explanation unit can input chat text data into a generative AI, and the generative AI can generate explanations in language that new employees can easily understand.

[0079] The Consultation Facilitation Department encourages consultation with supervisors for urgent matters. The Consultation Facilitation Department can assess urgency based on, for example, the importance of the task. The Consultation Facilitation Department can also assess urgency based on, for example, the approaching deadline. The Consultation Facilitation Department can also encourage consultation with supervisors using, for example, notifications or alerts. This enables a swift response by prompting consultation with supervisors for urgent matters. Some or all of the above processes in the Consultation Facilitation Department may be performed using, for example, AI, or not using AI. For example, the Consultation Facilitation Department can input the importance of the task and the approaching deadline into the AI, which can then assess the urgency and notify the supervisor.

[0080] The assistance unit assists the instructor with questions while communicating prerequisites. The assistance unit supports the instructor by, for example, providing background information. The assistance unit can also support the instructor by, for example, providing relevant data. The assistance unit can also support the instructor by, for example, providing question templates. This improves the efficiency of instruction by assisting the instructor with questions while communicating prerequisites. Some or all of the above processing in the assistance unit may be performed using, for example, AI, or not using AI. For example, the assistance unit can input background information and relevant data into the AI, and the AI ​​can generate question templates and provide them to the instructor.

[0081] The workload reduction unit reduces the workload of departments with the support of agents. The workload reduction unit can, for example, distribute tasks. The workload reduction unit can also, for example, use efficiency tools to streamline operations. The workload reduction unit can also reduce the workload by, for example, setting task priorities. This enables efficient business operations by reducing the workload of departments with the support of agents. Some or all of the above processes in the workload reduction unit may be performed using AI, for example, or not using AI. For example, the workload reduction unit can input task distribution into AI, and the AI ​​can propose the optimal task distribution.

[0082] The data collection unit estimates the emotions of new employees and collects changes in their comprehension level in real time based on the estimated emotions. For example, if a new employee is stressed, the data collection unit may monitor the changes in their comprehension level in real time, as this may decrease. The data collection unit may also monitor the changes in their comprehension level in real time, as this may improve if a new employee is relaxed. For example, if a new employee is excited, their comprehension level on a particular topic may fluctuate rapidly, so the data collection unit may also monitor the changes in real time. This allows for appropriate support by collecting changes in comprehension level in real time based on the emotions of new employees. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input the new employee's emotion data into an AI, which can then collect changes in comprehension level in real time.

[0083] The data collection unit analyzes the new employee's past learning history and selects the optimal information collection method. For example, the data collection unit focuses on collecting information in areas where the new employee has a low level of understanding, based on what they have learned in the past. The data collection unit can also analyze the learning methods (videos, texts, etc.) used by the new employee in the past and select the optimal information collection method. For example, the data collection unit can select learning methods that are effective at specific times of day based on the new employee's past learning history and collect information. In this way, the optimal information collection method can be selected by analyzing the new employee's past learning history. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input the new employee's past learning history into AI, and the AI ​​can select the optimal information collection method.

[0084] The data collection unit dynamically changes the priority of the information to be collected based on the new employee's work progress. For example, if a new employee completes a specific task, the data collection unit prioritizes collecting information related to that task. The data collection unit can also prioritize collecting information related to tasks that a new employee is behind on. For example, if a new employee starts a new task, the data collection unit can also prioritize collecting information related to that task. This enables efficient information collection by dynamically changing the priority of information based on the new employee's work progress. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input the new employee's work progress into the AI, which can then dynamically change the priority of information.

[0085] The data collection unit estimates the emotions of new employees and adjusts the level of detail of the information collected based on the estimated emotions. For example, if a new employee is stressed, the data collection unit can provide detailed information to deepen understanding. For example, if a new employee is relaxed, the data collection unit can provide concise information to facilitate efficient learning. For example, if a new employee is excited, the data collection unit can provide interesting and detailed information to increase motivation to learn. This allows for the provision of appropriate information by adjusting the level of detail of the information based on the emotions of the new employees. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not using AI. For example, the data collection unit can input the new employee's emotion data into an AI, which can then adjust the level of detail of the information.

[0086] The data collection unit prioritizes collecting highly relevant information, taking into account the geographical location of new employees. For example, if a new employee is in a specific office, the data collection unit prioritizes collecting information related to that office. If a new employee is on a business trip, the data collection unit may also prioritize collecting information related to their business trip destination. If a new employee is working remotely, the data collection unit may also prioritize collecting information related to resources accessible from their home. This allows for the priority collection of highly relevant information by considering the geographical location of new employees. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input the geographical location of new employees into an AI, which can then prioritize collecting highly relevant information.

[0087] The data collection unit analyzes the social media activities of new employees and collects relevant information. For example, the data collection unit collects relevant information based on the interests and passions that new employees share on social media. The data collection unit can also collect relevant information by analyzing posts from experts and industry leaders that new employees follow on social media. The data collection unit can also collect relevant information by analyzing the activities of groups and communities that new employees participate in on social media. In this way, relevant information can be collected by analyzing the social media activities of new employees. Some or all of the above processing in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input new employees' social media activity data into AI, and the AI ​​can collect relevant information.

[0088] The analysis department estimates the emotions of new employees and adjusts the presentation of the analysis results based on the estimated emotions. For example, if a new employee is nervous, the analysis department provides a simple and easily understandable presentation. If a new employee is relaxed, the analysis department may also provide a presentation that includes detailed information. If a new employee is in a hurry, the analysis department may also provide a presentation that gets straight to the point. This allows for the provision of appropriate information by adjusting the presentation of the analysis results based on the emotions of the new employees. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis department may be performed using AI or not. For example, the analysis department can input new employee emotion data into an AI, which can then adjust the presentation of the analysis results.

[0089] The analysis unit adjusts the level of detail of the analysis based on the importance of the collected information. For example, the analysis unit performs a detailed analysis on information of high importance. The analysis unit can also perform a concise analysis on information of low importance. The analysis unit can also perform an analysis of moderate level of detail on information of moderate importance. By adjusting the level of detail of the analysis based on the importance of the collected information, efficient information analysis becomes possible. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the importance of the collected information into the AI, and the AI ​​can adjust the level of detail of the analysis.

[0090] The analysis unit applies different analysis algorithms depending on the category of information. For example, the analysis unit applies a technical analysis algorithm to technical information. The analysis unit can also apply a market analysis algorithm to market information. The analysis unit can also apply a human resources analysis algorithm to human resources information. By applying different analysis algorithms depending on the category of information, appropriate information analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of information into the AI, and the AI ​​can apply an appropriate analysis algorithm.

[0091] The analysis department estimates the emotions of new employees and prioritizes the analysis results based on the estimated emotions. For example, if a new employee is stressed, the analysis department prioritizes analyzing information to reduce stress. For example, if a new employee is relaxed, the analysis department may prioritize analyzing information to increase their motivation to learn. For example, if a new employee is excited, the analysis department may prioritize analyzing information that will pique their interest. This allows for the provision of appropriate information by prioritizing the analysis results based on the emotions of new employees. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis department may be performed using AI or not. For example, the analysis department can input new employee emotion data into an AI, which can then determine the priority of the analysis results.

[0092] The analysis department determines the priority of analysis based on when the information was submitted. For example, the analysis department prioritizes the analysis of recently submitted information. The analysis department may also postpone the analysis of older information. The analysis department may also moderately analyze information with a moderate submission date. This allows for efficient information analysis by determining the priority of analysis based on when the information was submitted. Some or all of the above processes in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department can input the submission dates of the information into the AI, and the AI ​​can determine the priority of analysis.

[0093] The analysis unit adjusts the order of analysis based on the relevance of the information. For example, the analysis unit prioritizes the analysis of highly relevant information. The analysis unit may also postpone the analysis of less relevant information. The analysis unit may also moderately analyze information of moderate relevance. By adjusting the order of analysis based on the relevance of the information, efficient information analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the relevance of the information into the AI, and the AI ​​can adjust the order of analysis.

[0094] The consultation promotion department estimates the emotions of new employees and adjusts the urgency of consultations based on the estimated emotions. For example, if a new employee is feeling stressed, the consultation promotion department may increase the urgency to encourage consultation. For example, if a new employee is relaxed, the consultation promotion department may also decrease the urgency to encourage consultation. For example, if a new employee is excited, the consultation promotion department may also adjust the urgency appropriately to encourage consultation. This allows for appropriate consultation promotion by adjusting the urgency of consultations based on the emotions of new employees. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the consultation promotion department may be performed using AI or not using AI. For example, the consultation promotion department can input new employee emotion data into an AI, which can then adjust the urgency of consultations.

[0095] The Consultation Promotion Department selects the most suitable consultation method by referring to past consultation history. For example, the Consultation Promotion Department prioritizes suggesting consultation methods previously used by new employees (chat, telephone, etc.). The Consultation Promotion Department can also select the most effective consultation method from a new employee's past consultation history. For example, the Consultation Promotion Department can suggest the most suitable consultation method based on the content of past consultations by new employees. In this way, the most suitable consultation method can be selected by referring to past consultation history. Some or all of the above processes in the Consultation Promotion Department may be performed using AI, for example, or not. For example, the Consultation Promotion Department can input past consultation history into AI, and the AI ​​can select the most suitable consultation method.

[0096] The consultation promotion department applies different promotion methods depending on the category of the consultation. For example, the consultation promotion department applies technical promotion methods to technical consultations. For example, the consultation promotion department may also apply human resources promotion methods to human resources consultations. For example, the consultation promotion department may also apply market promotion methods to market-related consultations. By applying different promotion methods depending on the category of the consultation, appropriate consultation promotion becomes possible. Some or all of the above processing in the consultation promotion department may be performed using AI, for example, or not using AI. For example, the consultation promotion department can input the category of the consultation into the AI, and the AI ​​can apply an appropriate promotion method.

[0097] The Consultation Facilitation Department estimates the emotions of new employees and determines the priority of consultations based on the estimated emotions. For example, if a new employee is feeling stressed, the Consultation Facilitation Department will increase the priority and encourage consultation. For example, if a new employee is relaxed, the Consultation Facilitation Department may also lower the priority and encourage consultation. For example, if a new employee is excited, the Consultation Facilitation Department may adjust the priority appropriately and encourage consultation. This allows for appropriate consultation facilitation by determining the priority of consultations based on the emotions of new employees. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the Consultation Facilitation Department may be performed using AI or not using AI. For example, the Consultation Facilitation Department can input new employee emotion data into an AI, which can then determine the priority of consultations.

[0098] The consultation promotion department determines priorities based on when the consultation content is submitted. For example, the consultation promotion department will prioritize recently submitted consultations. For example, the consultation promotion department may postpone older consultations. For example, the consultation promotion department may process consultations of moderate age appropriately. This allows for efficient consultation promotion by determining priorities based on when the consultation content is submitted. Some or all of the above processing in the consultation promotion department may be performed using AI, for example, or not using AI. For example, the consultation promotion department can input the submission dates of consultation content into AI, and the AI ​​can determine the priorities.

[0099] The consultation facilitation department adjusts the order of consultations based on their relevance. For example, the consultation facilitation department prioritizes processing consultations with high relevance. For example, the consultation facilitation department may postpone consultations with low relevance. For example, the consultation facilitation department may process consultations with moderate relevance appropriately. This allows for efficient consultation facilitation by adjusting the order based on the relevance of the consultations. Some or all of the above processing in the consultation facilitation department may be performed using AI, for example, or not using AI. For example, the consultation facilitation department can input the relevance of the consultations into the AI, and the AI ​​can adjust the order.

[0100] The assistance unit estimates the emotions of new employees and adjusts the way it communicates based on the estimated emotions. For example, if a new employee is nervous, the assistance unit provides a simple and easily understandable communication style. If a new employee is relaxed, the assistance unit may also provide a more detailed communication style. If a new employee is in a hurry, the assistance unit may also provide a more concise communication style. By adjusting the way the assistance is communicated based on the new employee's emotions, appropriate support can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the assistance unit may be performed using AI or not using AI. For example, the assistance unit can input the new employee's emotion data into an AI, which can then adjust the way the assistance is communicated.

[0101] The assistance unit adjusts the level of detail of the assistance based on the importance of the question. For example, the assistance unit provides detailed assistance for high-importance questions. For example, the assistance unit can provide concise assistance for low-importance questions. For example, the assistance unit can provide assistance with an appropriate level of detail for questions of moderate importance. This allows for efficient support by adjusting the level of detail of the assistance based on the importance of the question. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the importance of the question into the AI, and the AI ​​can adjust the level of detail of the assistance.

[0102] The assistance unit applies different assistance algorithms depending on the category of the question. For example, the assistance unit applies a technical assistance algorithm to a technical question. For example, the assistance unit can also apply a human resources assistance algorithm to a human resources question. For example, the assistance unit can also apply a market-related assistance algorithm to a market-related question. By applying different assistance algorithms depending on the category of the question, appropriate support can be provided. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the category of the question into the AI, and the AI ​​can apply an appropriate assistance algorithm.

[0103] The assistance unit estimates the emotions of new employees and determines the priority of assistance based on the estimated emotions. For example, if a new employee is feeling stressed, the assistance unit will prioritize providing assistance. For example, if a new employee is relaxed, the assistance unit may also lower the priority of providing assistance. For example, if a new employee is excited, the assistance unit may adjust the priority appropriately. This allows for appropriate support by determining the priority of assistance based on the emotions of the new employee. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the assistance unit may be performed using AI, or not using AI. For example, the assistance unit can input the new employee's emotion data into an AI, which can then determine the priority of assistance.

[0104] The assistance unit determines the priority of assistance based on when the questions were submitted. For example, the assistance unit will prioritize assistance for recently submitted questions. The assistance unit may also postpone assistance for older questions. For example, the assistance unit may provide appropriate assistance for questions submitted at a moderate time. This allows for efficient support by determining the priority of assistance based on when the questions were submitted. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the submission dates of the questions into the AI, which can then determine the priority of assistance.

[0105] The assistance unit adjusts the order of assistance based on the relevance of the questions. For example, the assistance unit prioritizes assisting with questions that are highly relevant. The assistance unit may also postpone assisting with questions that are less relevant. The assistance unit may also provide appropriate assistance to questions that are moderately relevant. This allows for efficient support by adjusting the order of assistance based on the relevance of the questions. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the relevance of the questions into the AI, which can then adjust the order of assistance.

[0106] The memo section estimates the emotions of new employees and adjusts the memo recording method based on the estimated emotions. For example, if a new employee is nervous, the memo section provides a simple and highly visible memo recording method. For example, if a new employee is relaxed, the memo section can also provide a memo recording method that includes detailed information. For example, if a new employee is in a hurry, the memo section can also provide a memo recording method that gets straight to the point. This allows for appropriate memo recording by adjusting the memo recording method based on the new employee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the memo section may be performed using AI, for example, or not using AI. For example, the memo section can input the new employee's emotion data into the AI, and the AI ​​can adjust the memo recording method.

[0107] The note-taking section adjusts the level of detail in the notes based on the importance of the learning content. For example, the note-taking section records detailed notes for highly important learning content. For example, the note-taking section can also record concise notes for less important learning content. For example, the note-taking section can record notes with a moderate level of detail for moderately important learning content. This allows for efficient note-taking by adjusting the level of detail in the notes based on the importance of the learning content. Some or all of the above processing in the note-taking section may be performed using AI, for example, or without AI. For example, the note-taking section can input the importance of the learning content into the AI, and the AI ​​can adjust the level of detail in the notes.

[0108] The memo unit estimates the emotions of new employees and determines the priority of memos based on the estimated emotions. For example, if a new employee is feeling stressed, the memo unit will prioritize recording memos. If a new employee is relaxed, the memo unit may also prioritize recording memos less. If a new employee is excited, the memo unit may adjust the priority appropriately before recording memos. This allows for appropriate memo recording by determining the priority of memos based on the new employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the memo unit may be performed using AI or not. For example, the memo unit can input new employee emotion data into an AI, which can then determine the priority of memos.

[0109] The note-taking section applies different recording methods depending on the category of the learning content. For example, the note-taking section applies a technical note-taking method to technical learning content. The note-taking section can also apply a human resources note-taking method to human resources learning content. The note-taking section can also apply a market-related note-taking method to market-related learning content. By applying different recording methods depending on the category of the learning content, appropriate note-taking becomes possible. Some or all of the above processing in the note-taking section may be performed using AI, for example, or without AI. For example, the note-taking section can input the category of the learning content into the AI, and the AI ​​can apply an appropriate recording method.

[0110] The explanation unit estimates the emotions of new employees and adjusts the way the explanation is presented based on the estimated emotions. For example, if a new employee is nervous, the explanation unit provides a simple and easy-to-understand explanation. For example, if a new employee is relaxed, the explanation unit may provide an explanation that includes detailed information. For example, if a new employee is in a hurry, the explanation unit may provide an explanation that gets straight to the point. This allows for appropriate explanations by adjusting the way the explanation is presented based on the emotions of the new employees. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the explanation unit may be performed using AI or not using AI. For example, the explanation unit can input the new employee's emotion data into an AI, which can then adjust the way the explanation is presented.

[0111] The explanation section adjusts the level of detail in the explanation based on the importance of the learning content. For example, the explanation section provides detailed explanations for highly important learning content. For example, the explanation section can provide concise explanations for less important learning content. For example, the explanation section can provide explanations of moderate importance. By adjusting the level of detail in the explanation based on the importance of the learning content, efficient explanations become possible. Some or all of the above processing in the explanation section may be performed using AI, for example, or without AI. For example, the explanation section can input the importance of the learning content into the AI, and the AI ​​can adjust the level of detail in the explanation.

[0112] The explanation unit estimates the emotions of new employees and determines the priority of explanations based on the estimated emotions. For example, if a new employee is feeling stressed, the explanation unit will prioritize that explanation. For example, if a new employee is relaxed, the explanation unit may also prioritize that explanation lower. For example, if a new employee is excited, the explanation unit may adjust the priority appropriately. This allows for appropriate explanations by determining the priority of explanations based on the emotions of the new employees. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the explanation unit may be performed using AI, or not using AI. For example, the explanation unit can input new employee emotion data into an AI, which can then determine the priority of explanations.

[0113] The explanation unit applies different explanation methods depending on the category of the learning content. For example, the explanation unit applies a technical explanation method to technical learning content. For example, the explanation unit can also apply a human resources explanation method to human resources learning content. For example, the explanation unit can also apply a market-related explanation method to market-related learning content. By applying different explanation methods depending on the category of the learning content, appropriate explanations become possible. Some or all of the above processing in the explanation unit may be performed using AI, for example, or without AI. For example, the explanation unit can input the category of the learning content into the AI, and the AI ​​can apply an appropriate explanation method.

[0114] The workload reduction unit estimates the emotions of new employees and adjusts the workload reduction method based on the estimated emotions. For example, if a new employee is feeling stressed, the workload reduction unit strengthens the workload reduction method. For example, if a new employee is relaxed, the workload reduction unit may also ease the workload reduction method. For example, if a new employee is excited, the workload reduction unit may also moderately adjust the workload reduction method. This allows for appropriate workload reduction by adjusting the workload reduction method based on the emotions of the new employees. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the workload reduction unit may be performed using AI, for example, or without AI. For example, the workload reduction unit can input the new employee's emotion data into an AI, which can then adjust the workload reduction method.

[0115] The workload reduction unit adjusts the level of detail in workload reduction based on the importance of the tasks. For example, the workload reduction unit performs detailed workload reduction for tasks of high importance. The workload reduction unit can also perform simple workload reduction for tasks of low importance. The workload reduction unit can also perform workload reduction with an appropriate level of detail for tasks of medium importance. By adjusting the level of detail in workload reduction based on the importance of the tasks, efficient workload reduction becomes possible. Some or all of the above processing in the workload reduction unit may be performed using AI, for example, or without AI. For example, the workload reduction unit can input the importance of the tasks into the AI, and the AI ​​can adjust the level of detail in workload reduction.

[0116] The workload reduction unit estimates the emotions of new employees and determines the priority of workload reduction based on the estimated emotions. For example, if a new employee is feeling stressed, the workload reduction unit will increase the priority of workload reduction. For example, if a new employee is relaxed, the workload reduction unit may also decrease the priority of workload reduction. For example, if a new employee is excited, the workload reduction unit may also adjust the priority appropriately to reduce workload. This allows for appropriate workload reduction by determining the priority of workload reduction based on the emotions of new employees. Emotion estimation is achieved using an emotion estimation function, for example, using 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 such examples. Some or all of the above processing in the workload reduction unit may be performed using AI, for example, or without AI. For example, the workload reduction unit can input the new employee's emotion data into an AI, which can then determine the priority of workload reduction.

[0117] The load reduction unit applies different load reduction methods depending on the category of work content. For example, the load reduction unit applies a technical load reduction method to technical tasks. The load reduction unit can also apply a human resources load reduction method to human resources tasks. The load reduction unit can also apply a market-related load reduction method to market-related tasks. By applying different load reduction methods depending on the category of work content, appropriate load reduction becomes possible. Some or all of the above processing in the load reduction unit may be performed using AI, for example, or without AI. For example, the load reduction unit can input the category of work content into the AI, and the AI ​​can apply an appropriate load reduction method.

[0118] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0119] The training system further includes a feedback section. The feedback section evaluates the work performance of new employees and provides appropriate feedback. For example, the feedback section can evaluate the quality of tasks completed by new employees and point out areas for improvement. It can also monitor the progress of new employees and evaluate their achievement of goals. Furthermore, the feedback section can compare the self-assessment of new employees with the assessment of their supervisors and provide advice to bridge the gap. This allows new employees to obtain concrete guidance for self-improvement. Some or all of the above processes in the feedback section may be performed using AI, for example, or not. For example, the feedback section can input the work data of new employees into an AI, which can then generate evaluations and feedback.

[0120] The memo section can also be equipped with a voice input function. The voice input function allows new employees to record notes by voice. For example, new employees can take notes by voice during meetings. The voice input function can also convert voice to text using speech recognition technology and save it as a digital memo. Furthermore, the voice input function can also search and edit memos using voice commands. This allows new employees to efficiently record and manage notes without using their hands. Some or all of the above processing in the voice input function may be performed using AI, for example, or not using AI. For example, the voice input function can input the new employee's voice data into AI, which can then convert the voice to text.

[0121] The explanatory section can also be equipped with a visual aid function. The visual aid function uses diagrams and graphs to explain things in a way that is easy for new employees to understand. For example, the explanatory section can show complex processes using flowcharts. It can also visually show data trends using graphs. Furthermore, the explanatory section can summarize information concisely using infographics. This allows new employees to deepen their understanding through visual information. Some or all of the above processing in the visual aid function may be performed using AI, for example, or not using AI. For example, the explanatory section can input data into AI, and the AI ​​can generate appropriate visual aids.

[0122] The consultation promotion department can further estimate the emotions of new employees using an emotion estimation function and adjust the urgency of the consultation based on the estimated emotions. For example, if a new employee is feeling stressed, the urgency can be increased to encourage consultation. Conversely, if a new employee is relaxed, the urgency can be decreased to encourage consultation. Furthermore, if a new employee is excited, the urgency can be appropriately adjusted to encourage consultation. In this way, appropriate consultation promotion becomes possible by adjusting the urgency of the consultation based on the emotions of the new employee. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the consultation promotion department may be performed using AI, for example, or without AI. For example, the consultation promotion department can input new employee emotion data into AI, and the AI ​​can adjust the urgency of the consultation.

[0123] The assistance unit can further estimate the emotions of new employees using an emotion estimation function and adjust the way it expresses itself based on the estimated emotions. For example, if a new employee is nervous, it can provide a simple and highly visible expression. If a new employee is relaxed, it can provide an expression that includes detailed information. Furthermore, if a new employee is in a hurry, it can provide an expression that gets straight to the point. This allows for appropriate support by adjusting the way the assistance is expressed based on the emotions of the new employee. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the assistance unit may be performed using AI, or not using AI. For example, the assistance unit can input the new employee's emotion data into the AI, and the AI ​​can adjust the way the assistance is expressed.

[0124] The load reduction unit can further estimate the emotions of new employees using an emotion estimation function and adjust the load reduction method based on the estimated emotions. For example, if a new employee is feeling stressed, the load reduction method can be strengthened. Conversely, if a new employee is relaxed, the load reduction method can be mitigated. Furthermore, if a new employee is excited, the load reduction method can be appropriately adjusted. This allows for appropriate load reduction by adjusting the load reduction method based on the emotions of the new employees. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the load reduction unit may be performed using AI, for example, or without AI. For example, the load reduction unit can input the new employee's emotion data into an AI, which can then adjust the load reduction method.

[0125] The data collection unit can further consider the geographical location of new employees to prioritize the collection of highly relevant information. For example, if a new employee is in a specific office, it can prioritize the collection of information related to that office. Similarly, if a new employee is on a business trip, it can prioritize the collection of information related to their destination. Furthermore, if a new employee is working remotely, it can prioritize the collection of information related to resources accessible from their home. This allows for the prioritization of highly relevant information by considering the geographical location of new employees. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For instance, the data collection unit could input the geographical location of new employees into an AI, which could then prioritize the collection of highly relevant information.

[0126] The analysis unit can apply different analysis algorithms depending on the category of information. For example, a technical analysis algorithm can be applied to technical information. A market analysis algorithm can also be applied to market information. Furthermore, a human resources analysis algorithm can be applied to human resources information. By applying different analysis algorithms depending on the category of information, appropriate information analysis becomes possible. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of information into the AI, and the AI ​​can apply an appropriate analysis algorithm.

[0127] The Consultation Promotion Department can further select the most suitable consultation method by referring to past consultation history. For example, it can prioritize suggesting consultation methods previously used by new employees (chat, telephone, etc.). It can also select the most effective consultation method from the new employee's past consultation history. Furthermore, it can suggest the most suitable consultation method based on the content of past consultations by new employees. In this way, the most suitable consultation method can be selected by referring to past consultation history. Some or all of the above processes in the Consultation Promotion Department may be performed using AI, for example, or not. For example, the Consultation Promotion Department can input past consultation history into AI, and the AI ​​can select the most suitable consultation method.

[0128] The assistance unit can apply different assistance algorithms depending on the category of the question. For example, a technical assistance algorithm can be applied to a technical question. Similarly, a human resources assistance algorithm can be applied to a human resources question. Furthermore, a market-related assistance algorithm can be applied to a market-related question. This allows for appropriate support by applying different assistance algorithms depending on the category of the question. Some or all of the above processing in the assistance unit may be performed using AI, for example, or without AI. For example, the assistance unit can input the category of the question into the AI, which can then apply an appropriate assistance algorithm.

[0129] The following briefly describes the processing flow for example form 2.

[0130] Step 1: The information gathering department collects what new employees understand. For example, information is collected by having new employees take notes on what they have learned. Information can also be collected through questionnaires and interviews. Furthermore, the level of understanding of new employees can be grasped through observation. Step 2: The analysis department analyzes the information collected by the collection department. For example, they analyze the information using data analysis techniques and statistical analysis to evaluate the level of understanding of new employees. They can also analyze the information using text mining techniques. Step 3: The Consultation Facilitation Department, based on the information analyzed by the Analysis Department, encourages consultations with supervisors for urgent cases. For example, they can use notifications, alerts, and reminders to prompt consultations with supervisors. They can also prioritize notifying supervisors of urgent cases. Step 4: The Assistance Department assists the instructor with questions, communicating prerequisites based on the consultation facilitated by the Consultation Facilitation Department. For example, they support the instructor by providing question templates. They can also assist the instructor by providing support tools, background information, and relevant data.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] Each of the multiple elements described above, including the collection unit, analysis unit, consultation promotion unit, assistance unit, memo unit, and load reduction unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart device 14 and collects information by having new employees record what they have learned in a memo. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected information. The consultation promotion unit is implemented, for example, by the control unit 46A of the smart device 14 and prompts new employees to consult with their mentors for urgent matters. The assistance unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and assists with questions while conveying prerequisites to the mentor. The memo unit is implemented, for example, by the control unit 46A of the smart device 14 and records what new employees have learned in a memo. The load reduction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and reduces the workload on the department with agent support. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0135] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] Each of the multiple elements described above, including the collection unit, analysis unit, consultation promotion unit, assistance unit, memo unit, and load reduction unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the smart glasses 214 and collects information by having new employees record what they have learned in a memo. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected information. The consultation promotion unit is implemented, for example, by the control unit 46A of the smart glasses 214 and prompts new employees to consult with their supervisors for urgent matters. The assistance unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and assists with questions while communicating prerequisites to the supervisor. The memo unit is implemented, for example, by the control unit 46A of the smart glasses 214 and records what new employees have learned in a memo. The load reduction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and reduces the workload on the department with agent support. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0151] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] Each of the multiple elements described above, including the collection unit, analysis unit, consultation promotion unit, assistance unit, memo unit, and load reduction unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the headset terminal 314 and collects information by having new employees record what they have learned in a memo. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the collected information. The consultation promotion unit is implemented by, for example, the control unit 46A of the headset terminal 314 and prompts new employees to consult with their supervisors for urgent matters. The assistance unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and assists with questions while conveying prerequisites to the supervisor. The memo unit is implemented by, for example, the control unit 46A of the headset terminal 314 and records what new employees have learned in a memo. The load reduction unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and reduces the workload on the department with agent support. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0167] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.).

[0180] 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.

[0181] 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.

[0182] 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.

[0183] Each of the multiple elements described above, including the collection unit, analysis unit, consultation promotion unit, assistance unit, memo unit, and load reduction unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the control unit 46A of the robot 414 and collects information by recording what new employees have learned in memos. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected information. The consultation promotion unit is implemented, for example, by the control unit 46A of the robot 414 and prompts new employees to consult with their supervisors for urgent matters. The assistance unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and assists with questions while conveying prerequisites to the supervisor. The memo unit is implemented, for example, by the control unit 46A of the robot 414 and records what new employees have learned in memos. The load reduction unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and reduces the workload on the department with agent support. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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."

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] (Note 1) The collection department is responsible for gathering information on what new employees understand, An analysis unit analyzes the information collected by the aforementioned collection unit, Based on the information analyzed by the aforementioned analysis department, the consultation promotion department will encourage those with high urgency to consult with their supervisors, The Assistance Department assists the instructors with questions while conveying the preconditions to them based on the consultations facilitated by the aforementioned Consultation Facilitation Department, Equipped with A system characterized by the following features. (Note 2) It includes a note-taking section where new employees can record what they have learned. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit is The company has a commentary department that analyzes chat and document screen information and provides explanations in language that new employees can understand. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned consultation promotion department, For urgent matters, encourage consultation with your supervisor. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned assist unit is Assist the instructor with questions while explaining the prerequisites. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes a load reduction unit that reduces the workload on departments through agent-based support. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is The system estimates the emotions of new employees and collects real-time data on changes in their understanding based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Analyze the past learning history of new employees to select the most suitable information gathering method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is The system dynamically changes the priority of information collected based on the work progress of new employees. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is The system estimates the emotions of new employees and adjusts the level of detail of the information collected based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is Considering the geographical location of new employees, we prioritize collecting highly relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is Analyze the social media activities of new employees and collect relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit is We estimate the emotions of new employees and adjust the way the analysis results are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit is Adjust the level of detail in the analysis based on the importance of the collected information. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit is Apply different analysis algorithms depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit is The system estimates the emotions of new employees and prioritizes the analysis results based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit is Prioritize analysis based on when the information was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit is Adjust the order of analysis based on the relevance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned consultation promotion department, The system estimates the emotions of new employees and adjusts the urgency of consultations based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned consultation promotion department, We will select the most suitable consultation method by referring to past consultation history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned consultation promotion department, Different facilitation methods are applied depending on the category of the consultation. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned consultation promotion department, The system estimates the emotions of new employees and determines the priority of consultations based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned consultation promotion department, Prioritization will be determined based on when the consultation request was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned consultation promotion department, The order will be adjusted based on the relevance of the consultation topics. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned assist unit is The system estimates the emotions of new employees and adjusts the way assistance is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned assist unit is The level of detail in the assistance is adjusted based on the importance of the question. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned assist unit is Apply different assistance algorithms depending on the category of the question. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned assist unit is The system estimates the emotions of new employees and determines the priority of assistance based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned assist unit is We will prioritize assistance based on when the questions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned assist unit is The order of assistance is adjusted based on the relevance of the questions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned memo section is, Estimate the emotions of new employees and adjust the note-taking method based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned memo section is, Adjust the level of detail in your notes based on the importance of the learning material. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned memo section is, Estimate the emotions of new employees and prioritize notes based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned memo section is, Apply different recording methods depending on the category of learning content. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned explanatory section is, We estimate the emotions of new employees and adjust the way explanations are presented based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned explanatory section is, The level of detail in the explanations is adjusted based on the importance of the learning material. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned explanatory section is, The system estimates the emotions of new employees and determines the priority of explanations based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned explanatory section is, Apply different explanation methods depending on the category of learning content. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned load reduction unit is The system estimates the emotions of new employees and adjusts methods for reducing their workload based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 40) The aforementioned load reduction unit is Adjust the level of detail in workload reduction based on the importance of the task. The system described in Appendix 6, characterized by the features described herein. (Note 41) The aforementioned load reduction unit is The system estimates the emotions of new employees and determines the priority for workload reduction based on those estimated emotions. The system described in Appendix 6, characterized by the features described herein. (Note 42) The aforementioned load reduction unit is Apply different workload reduction methods depending on the category of work. The system described in Appendix 6, characterized by the features described herein. [Explanation of Symbols]

[0203] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection department is responsible for gathering information on what new employees understand, An analysis unit analyzes the information collected by the aforementioned collection unit, Based on the information analyzed by the aforementioned analysis department, the consultation promotion department will encourage those with high urgency to consult with their supervisors, Based on the consultations facilitated by the aforementioned consultation promotion department, the assistance department assists the instructors by conveying the preconditions and asking questions. Equipped with A system characterized by the following features.

2. It includes a note-taking section where new employees can record what they have learned. The system according to feature 1.

3. The aforementioned analysis unit is The company has a commentary department that analyzes chat and document screen information and provides explanations in language that new employees can understand. The system according to feature 1.

4. The aforementioned consultation promotion department, For urgent matters, encourage consultation with your supervisor. The system according to feature 1.

5. The aforementioned assist unit is Assist the instructor with questions while explaining the prerequisites. The system according to feature 1.

6. It includes a load reduction unit that reduces the workload on departments through agent-based support. The system according to feature 1.

7. The aforementioned collection unit is The system estimates the emotions of new employees and collects real-time data on changes in their understanding based on those estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is Analyze the past learning history of new employees to select the most suitable information gathering method. The system according to feature 1.

9. The aforementioned collection unit is The system dynamically changes the priority of information collected based on the work progress of new employees. The system according to feature 1.

Images