system

Abstract

The system according to the embodiment aims to effectively utilize manuals in training new employees and to realize efficient training. [Solution] A system according to an embodiment includes a receiving unit, a generating unit, a providing unit, a progress tracking unit, and an evaluating unit. The receiving unit receives questions. The generating unit analyzes the questions received by the receiving unit and searches for relevant portions of the manual. The providing unit provides answers generated by the generating unit. The progress tracking unit tracks the learning progress of the new employee based on the answers provided by the providing unit. The evaluating unit evaluates the new employee's level of understanding based on the progress tracked by the progress tracking unit.

Description

[Technical Field]

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

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

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

[0004] In conventional technology, manuals are not fully utilized in training new employees, making it difficult to provide efficient training.

[0005] The system according to the embodiment aims to effectively utilize manuals in training new employees and to realize efficient training. [Means for solving the problem]

[0006] The system according to the embodiment includes a receiving unit, a generating unit, a providing unit, a progress tracking unit, and an evaluating unit. The receiving unit receives a question. The generating unit analyzes the question received by the receiving unit and searches for the relevant part of the manual. The providing unit provides the answer generated by the generating unit. The progress tracking unit tracks the learning progress of the new employee based on the answer provided by the providing unit. The evaluating unit evaluates the new employee's level of understanding based on the progress tracked by the progress tracking unit. [Effects of the Invention]

[0007] The system according to the embodiment can effectively utilize manuals in training new employees, thereby realizing efficient training. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A new employee training assistance system according to an embodiment of the present invention uses a generation AI to assist new employee training in conjunction with a manual. In this new employee training assistance system, a new employee inputs questions or concerns about their work into the generation AI, which then searches for the relevant section of the appropriate manual and generates an answer. The generation AI then provides additional information and concrete examples related to the question, providing supplementary explanations to help the new employee understand. This mechanism allows new employees to quickly resolve their work-related concerns and progress efficiently. For example, a new employee inputs a question or concern about their work into the generation AI. For example, the new employee may input a specific question such as, "What are the procedures for this work?" or "Please tell me how to use this tool." This information is then input into the generation AI. The generation AI then analyzes the input question and searches for the relevant section of the appropriate manual. The generation AI then understands the content of the question and identifies the relevant section of the manual. For example, in response to the question, "What are the procedures for this work?", the generation AI searches for the relevant section of the manual regarding work procedures and generates the answer. The generation AI then provides additional information and concrete examples related to the question. For example, in response to a question such as "Please tell me how to use this tool," the generative AI provides supplementary explanations, including specific steps and important points on how to use the tool. This allows new employees to obtain not only the answer to their question but also related information, leading to a deeper understanding. This system allows new employees to quickly resolve questions about their work and progress efficiently in their learning. For example, if a new employee has a question while working, they can immediately enter the question into the generative AI and receive an appropriate answer. This allows new employees to progress in their learning at their own pace, improving work efficiency. This allows the new employee training assistance system to search for the relevant part of the manual in response to the new employee's question, provide an answer, track learning progress, and evaluate comprehension.

[0029] A new employee training assistance system according to an embodiment includes a reception unit, a generation unit, a provision unit, a progress tracking unit, and an evaluation unit. The reception unit receives questions from new employees regarding their work. Questions from new employees regarding their work include, but are not limited to, questions in text format, voice format, and questions about specific topics. The reception unit receives questions entered in text format, for example. The reception unit can also receive questions entered in voice format. The reception unit can also receive questions about specific topics. For example, the reception unit analyzes questions entered in text format using natural language processing technology to understand the content of the question. Questions entered in voice format are converted into text using speech recognition technology and then analyzed using natural language processing technology. The generation unit analyzes the questions received by the reception unit and searches for a relevant section of an appropriate manual. For example, the generation unit analyzes the content of the question using natural language processing technology and identifies a relevant section of the manual. For example, the generation unit extracts keywords from the question and searches for a relevant section of the manual based on the keywords. The generation unit can also use context analysis to understand the content of the question and identify the relevant section of the manual. The provision unit provides the answer generated by the generation unit. The provision unit can provide the answer, for example, in text format. The provision unit can also provide the answer in audio format. The provision unit can also provide the answer using diagrams. For example, the provision unit provides the text format answer generated by the generation unit as is. When providing the answer in audio format, the text format answer is converted into audio using speech synthesis technology and provided. The progress tracking unit tracks the new employee's learning progress based on the answers provided by the provision unit. The progress tracking unit tracks the learning progress based on evaluation criteria such as test results, study time, and achievement level. For example, the progress tracking unit records the results of a test conducted by the new employee based on the answers provided and evaluates the learning progress based on the results. It can also record study time and evaluate the learning progress based on the time. It can also record achievement level and evaluate the learning progress based on the achievement level. The evaluation unit evaluates the new employee's understanding based on the progress tracked by the progress tracking unit.The evaluation unit evaluates the level of understanding based on evaluation criteria such as the percentage of correct answers on a test and the content of feedback. For example, the evaluation unit evaluates the level of understanding of a new employee based on the percentage of correct answers on a test. The evaluation unit can also evaluate the level of understanding based on the content of feedback. As a result, the new employee training assistance system according to the embodiment can search for relevant parts of an appropriate manual in response to a question from a new employee, provide an answer, track learning progress, and evaluate the level of understanding.

[0030] The new employee training assistance system includes a history storage unit that stores a question history. The history storage unit stores the question history. The question history may be in a text format, a database structure, a storage period, or the like, but is not limited to these examples. The history storage unit stores, for example, a question history input in text format. The history storage unit can also store the question history based on the database structure. The history storage unit can also store the question history based on the storage period. For example, the history storage unit stores the question history input in text format in a database. The question history can also be classified and stored based on the database structure. The question history can also be periodically updated based on the storage period, and old question history can also be deleted. In this way, by storing the question history, past question content can be referenced.

[0031] The new employee training assistance system includes an update unit that updates the contents of the manual. The update unit updates the contents of the manual. The contents of the manual include, for example, update frequency, update criteria, update procedures, etc., but are not limited to these examples. The update unit, for example, periodically checks the contents of the manual and updates them as necessary. The update unit can also update the contents of the manual based on the update criteria. Furthermore, the update unit can also update the contents of the manual based on the update procedures. For example, the update unit periodically checks the contents of the manual and updates them based on the latest information. Important information can also be updated preferentially based on the update criteria. The contents of the manual can also be updated efficiently based on the update procedures. This allows the contents of the manual to be updated to the latest information.

[0032] The new employee training assistance system includes a supplementary explanation unit that provides additional information or specific examples related to the question. The supplementary explanation unit provides additional information or specific examples related to the question. Examples of additional information include, but are not limited to, related materials, links, and references. Examples of specific examples include, but are not limited to, actual case studies and simulation results. For example, the supplementary explanation unit provides materials related to the question. The supplementary explanation unit can also provide links related to the question. Furthermore, the supplementary explanation unit can provide references related to the question. For example, the supplementary explanation unit provides materials related to the question in digital form. When providing links, links to related web pages are provided. When providing references, information on related books and papers is provided. This makes it possible to provide related additional information and specific examples in addition to answers to questions.

[0033] The new employee training assistance system includes a feedback unit that provides regular feedback to new employees. The feedback unit provides regular feedback to new employees. Examples of feedback include, but are not limited to, regular reports, oral feedback, and feedback through an online platform. For example, the feedback unit provides regular reports. The feedback unit can also provide oral feedback. Furthermore, the feedback unit can provide feedback through an online platform. For example, the feedback unit sends regular reports by email. When providing oral feedback, the feedback is provided through regular meetings. When providing feedback through an online platform, a dedicated feedback system is used. By providing regular feedback to new employees, it is possible to check their learning progress and point out areas for improvement.

[0034] The reception unit can analyze the new employee's past question history and select a question reception method. For example, the reception unit uses a generation AI to automatically predict and receive related questions based on the content of questions frequently asked by the new employee in the past. The reception unit can also prioritize receiving question formats (text, voice, etc.) that the new employee has used in the past. Furthermore, the reception unit can analyze the new employee's past question history to determine whether they tend to ask more questions during certain time periods and increase the number of questions received during those time periods. For example, the reception unit stores the new employee's past question history in a database and analyzes that data to understand question trends. Based on the question trends, the reception unit selects the optimal question reception method. In this way, the optimal question reception method can be selected by analyzing the new employee's past question history.

[0035] When receiving a question, the reception unit can filter the questions based on the new employee's current work situation and areas of interest. For example, the reception unit prioritizes receiving questions related to the work the new employee is currently working on. The reception unit can also filter and receive related questions based on the new employee's areas of interest. Furthermore, the reception unit can grasp the new employee's work situation in real time and receive appropriate questions. For example, the reception unit stores the new employee's work situation in a database and analyzes the data to grasp question trends. Based on the question trends, the reception unit selects the optimal question reception method. In this way, by filtering questions based on the new employee's current work situation and areas of interest, more relevant questions can be received.

[0036] When receiving questions, the reception unit can prioritize receiving highly relevant questions based on the new employee's geographical location information. For example, if the new employee is in a specific office, the reception unit can prioritize receiving questions related to that office. Also, if the new employee is on a business trip, the reception unit can prioritize receiving questions related to the business trip destination. Furthermore, if the new employee is working remotely, the reception unit can prioritize receiving questions related to work at home. For example, the reception unit obtains the new employee's geographical location information using GPS data or IP address, and determines the priority of questions based on that information. In this way, by taking the new employee's geographical location information into consideration, highly relevant questions can be prioritized.

[0037] When accepting a question, the reception unit can analyze the new employee's social media activity and accept related questions. For example, the reception unit prioritizes accepting questions related to work that the new employee has shared on social media. The reception unit can also accept questions related to topics in which the new employee has shown interest on social media. Furthermore, the reception unit can predict and accept questions related to specific work from the new employee's social media activity. For example, the reception unit stores the new employee's social media activity in a database and analyzes the data to understand question trends. Based on the question trends, the reception unit selects the optimal question acceptance method. In this way, relevant questions can be accepted by analyzing the new employee's social media activity.

[0038] When generating an answer, the generation unit can adjust the level of detail of the answer based on the importance of the question. For example, the generation unit allows the generation AI to generate a detailed answer to an important question. The generation unit can also allow the generation AI to generate a concise answer to a general question. Furthermore, the generation unit can also allow the generation AI to generate an answer that can be quickly addressed to a question with a high degree of urgency. For example, the generation unit stores the importance of the question in a database and analyzes the data to understand the trend of questions. Based on the trend of questions, the generation unit selects the optimal answer generation method. In this way, by adjusting the level of detail of the answer based on the importance of the question, it is possible to provide a more appropriate answer.

[0039] When generating an answer, the generation unit can apply different generation algorithms depending on the question category. For example, in the generation unit, the generation AI applies a specialized algorithm to generate an answer to a technical question. In addition, in the generation unit, the generation AI can apply an algorithm specialized for procedures to generate an answer to a question about business procedures. Furthermore, in the generation unit, the generation AI can apply an algorithm specialized for the tool to generate an answer to a question about how to use a tool. For example, the generation unit stores the question categories in a database and analyzes the data to understand question trends. Based on the question trends, the optimal generation algorithm is selected. In this way, by applying different generation algorithms depending on the question category, more appropriate answers can be provided.

[0040] When generating answers, the generation unit can determine the priority of answers based on the time when the question was submitted. For example, the generation unit allows the generation AI to generate answers with priority for questions with high urgency. The generation unit can also allow the generation AI to generate answers with normal priority for normal questions. Furthermore, the generation unit can allow the generation AI to generate answers later for questions submitted in the past. For example, the generation unit stores the time when questions were submitted in a database and analyzes that data to understand question trends. Based on the question trends, the generation unit selects the optimal answer generation method. In this way, by determining the priority of answers based on the time when the question was submitted, answers can be provided in a more appropriate order.

[0041] When generating answers, the generation unit can adjust the order of answers based on the relevance of the question. For example, if the question is highly relevant, the generation unit can have the generation AI generate answers first. Also, if the question is general, the generation unit can have the generation AI generate answers in the normal order. Furthermore, if the question is less relevant, the generation unit can have the generation AI generate answers later. For example, the generation unit stores the relevance of questions in a database and analyzes that data to understand question trends. Based on the question trends, the generation unit selects the optimal answer generation method. As a result, by adjusting the order of answers based on the relevance of the question, answers can be provided in a more appropriate order.

[0042] When providing an answer, the providing unit can select the optimal method of providing the answer by referring to the newcomer's past learning history. For example, the providing unit provides the answer in a way that was easy for the newcomer to understand in the past. The providing unit can also provide learning methods that the newcomer has used in the past with priority. Furthermore, the providing unit can select the optimal method of providing the answer from the newcomer's past learning history. For example, the providing unit stores the newcomer's past learning history in a database and analyzes the data to understand learning trends. The optimal method of providing the answer is selected based on the learning trends. In this way, the optimal method of providing the answer can be selected by referring to the newcomer's past learning history.

[0043] When providing an answer, the providing unit can customize the means of providing the answer based on the new employee's current work situation. The providing unit, for example, provides an answer related to the work the new employee is currently working on. The providing unit can also select the optimal means of providing the answer based on the new employee's work situation. Furthermore, the providing unit can grasp the new employee's work situation in real time and provide an appropriate answer. For example, the providing unit stores the new employee's work situation in a database and analyzes the data to grasp work trends. The optimal means of providing the answer is selected based on the work trends. This makes it possible to provide an answer using the optimal means based on the new employee's current work situation.

[0044] When providing an answer, the providing unit can select a method of providing the answer based on the new employee's geographic location information. For example, if the new employee is in a specific office, the providing unit can provide an answer related to that office. Furthermore, if the new employee is on a business trip, the providing unit can also provide an answer related to the business trip destination. Furthermore, if the new employee is working remotely, the providing unit can also provide an answer related to work from home. For example, the providing unit obtains the new employee's geographic location information using GPS data or IP address, and selects a method of providing the answer based on that information. This makes it possible to provide an answer in the most optimal way by taking the new employee's geographic location information into consideration.

[0045] When providing an answer, the providing unit can analyze the new employee's social media activity and suggest a means of providing the answer. For example, the providing unit provides answers related to work that the new employee has shared on social media. The providing unit can also provide answers related to topics in which the new employee has shown interest on social media. Furthermore, the providing unit can predict and provide answers related to specific work from the new employee's social media activity. For example, the providing unit stores the new employee's social media activity in a database and analyzes the data to understand work trends. Based on the work trends, the providing unit selects the optimal means of providing the answer. In this way, by analyzing the new employee's social media activity, it is possible to provide answers via the optimal means.

[0046] When tracking progress, the progress tracking unit can select the optimal tracking method by referring to the new employee's past learning history. The progress tracking unit, for example, tracks progress using a method that the new employee found easy to understand in the past. The progress tracking unit can also prioritize tracking learning methods that the new employee has used in the past. Furthermore, the progress tracking unit can select the optimal tracking method from the new employee's past learning history. For example, the progress tracking unit stores the new employee's past learning history in a database and analyzes the data to understand learning trends. The optimal tracking method is selected based on the learning trends. In this way, the optimal tracking method can be selected by referring to the new employee's past learning history.

[0047] When tracking progress, the progress tracking unit can customize the tracking method based on the new employee's current work status. For example, the progress tracking unit prioritizes tracking of progress related to the work the new employee is currently working on. The progress tracking unit can also select the optimal tracking method depending on the new employee's work status. Furthermore, the progress tracking unit can grasp the new employee's work status in real time and track progress appropriately. For example, the progress tracking unit stores the new employee's work status in a database and analyzes the data to grasp work trends. The optimal tracking method is selected based on the work trends. This makes it possible to track progress using the optimal method depending on the new employee's current work status.

[0048] When tracking progress, the progress tracking unit can select the optimal tracking method by taking into account the geographic location information of the new employee. For example, if the new employee is in a specific office, the progress tracking unit can prioritize tracking progress related to that office. Also, if the new employee is on a business trip, the progress tracking unit can prioritize tracking progress related to the business trip destination. Furthermore, if the new employee is working remotely, the progress tracking unit can prioritize tracking progress related to work at home. For example, the progress tracking unit obtains the geographic location information of the new employee using GPS data or IP address, and selects the progress tracking method based on that information. In this way, progress can be tracked in the optimal way by taking into account the geographic location information of the new employee.

[0049] When tracking progress, the progress tracking unit can analyze the new employee's social media activities and suggest tracking methods. For example, the progress tracking unit prioritizes tracking work-related progress that the new employee has shared on social media. The progress tracking unit can also track progress related to topics in which the new employee has shown interest on social media. Furthermore, the progress tracking unit can predict and track progress related to specific work from the new employee's social media activities. For example, the progress tracking unit stores the new employee's social media activities in a database and analyzes the data to understand work trends. The optimal tracking method is selected based on the work trends. In this way, progress can be tracked using the optimal method by analyzing the new employee's social media activities.

[0050] During evaluation, the evaluation unit can select the optimal evaluation method by referring to the newcomer's past learning history. The evaluation unit, for example, performs evaluation using a method that the newcomer found easy to understand in the past. The evaluation unit can also prioritize evaluation of learning methods that the newcomer has used in the past. Furthermore, the evaluation unit can select the optimal evaluation method from the newcomer's past learning history. For example, the evaluation unit stores the newcomer's past learning history in a database and analyzes the data to understand learning trends. The optimal evaluation method is selected based on the learning trends. In this way, the optimal evaluation method can be selected by referring to the newcomer's past learning history.

[0051] At the time of evaluation, the evaluation department can customize the evaluation method based on the new employee's current work situation. For example, the evaluation department performs evaluation related to the work the new employee is currently working on. The evaluation department can also select the most appropriate evaluation method depending on the new employee's work situation. Furthermore, the evaluation department can grasp the new employee's work situation in real time and perform an appropriate evaluation. For example, the evaluation department stores the new employee's work situation in a database and analyzes the data to grasp work trends. The evaluation department selects the most appropriate evaluation method based on the work trends. This allows evaluation to be performed using the most appropriate method depending on the new employee's current work situation.

[0052] During the evaluation, the evaluation unit can select an evaluation method based on the new employee's geographic location information. For example, if the new employee is in a specific office, the evaluation unit performs an evaluation related to that office. In addition, if the new employee is on a business trip, the evaluation unit can also perform an evaluation related to the business trip destination. Furthermore, if the new employee is working remotely, the evaluation unit can also perform an evaluation related to work at home. For example, the evaluation unit obtains the new employee's geographic location information using GPS data or IP address, and selects an evaluation method based on that information. This allows the evaluation to be performed in the most optimal way by taking the new employee's geographic location information into consideration.

[0053] During the evaluation, the evaluation unit can analyze the new employee's social media activity and suggest evaluation methods. For example, the evaluation unit performs evaluations related to the work that the new employee shared on social media. The evaluation unit can also perform evaluations related to topics in which the new employee showed interest on social media. Furthermore, the evaluation unit can predict and evaluate evaluations related to specific work from the new employee's social media activity. For example, the evaluation unit stores the new employee's social media activity in a database and analyzes the data to understand work trends. Based on the work trends, the evaluation unit selects the most appropriate evaluation method. In this way, by analyzing the new employee's social media activity, evaluation can be performed using the most appropriate method.

[0054] When saving history, the history storage unit can select the optimal storage method by referring to the new employee's past question history. For example, the history storage unit allows the generation AI to automatically save related history based on the content of questions frequently asked by the new employee in the past. The history storage unit can also prioritize saving question formats (text, voice, etc.) used by the new employee in the past. Furthermore, the history storage unit can analyze the new employee's past question history to determine whether they tend to ask more questions during certain time periods and strengthen storage during those time periods. For example, the history storage unit stores the new employee's past question history in a database and analyzes that data to understand question trends. The optimal storage method is selected based on the question trends. In this way, the optimal storage method can be selected by referring to the new employee's past question history.

[0055] When saving history, the history saving unit can select the optimal saving method by taking into account the new employee's geographical location information. For example, if the new employee is in a specific office, the history saving unit can prioritize saving history related to that office. Also, if the new employee is on a business trip, the history saving unit can prioritize saving history related to the business trip destination. Furthermore, if the new employee is working remotely, the history saving unit can prioritize saving history related to work at home. For example, the history saving unit obtains the new employee's geographical location information using GPS data or IP address, and selects the saving method based on that information. In this way, the history can be saved in the optimal way by taking into account the new employee's geographical location information.

[0056] When updating manuals, the update department can select the optimal update method by referring to the new employee's past question history. For example, the update department uses the generation AI to automatically update the relevant manuals based on the content of questions frequently asked by the new employee in the past. The update department can also prioritize updating question formats (text, voice, etc.) that the new employee has used in the past. Furthermore, the update department can analyze the new employee's past question history to determine the tendency for questions to be asked frequently during specific time periods and strengthen updates during those time periods. For example, the update department stores the new employee's past question history in a database and analyzes that data to understand question trends. The optimal update method is selected based on the question trends. In this way, the optimal update method can be selected by referring to the new employee's past question history.

[0057] When updating manuals, the update unit can select the optimal update method by taking into account the new employee's geographic location information. For example, if the new employee is in a specific office, the update unit prioritizes updating manuals related to that office. Also, if the new employee is on a business trip, the update unit can prioritize updating manuals related to the business trip destination. Furthermore, if the new employee is working remotely, the update unit can prioritize updating manuals related to work at home. For example, the update unit obtains the new employee's geographic location information using GPS data or IP address, and selects the update method based on that information. In this way, the manuals can be updated in the optimal way by taking into account the new employee's geographic location information.

[0058] When providing supplementary explanations, the supplementary explanation unit can select the optimal explanation method by referring to the new employee's past question history. For example, the supplementary explanation unit uses the generation AI to automatically provide relevant supplementary explanations based on the content of questions frequently asked by the new employee in the past. The supplementary explanation unit can also prioritize explanations based on question formats (text, voice, etc.) used by the new employee in the past. Furthermore, the supplementary explanation unit can analyze the new employee's past question history to determine whether they tend to ask more questions during certain time periods, and strengthen explanations during those time periods. For example, the supplementary explanation unit stores the new employee's past question history in a database and analyzes that data to understand question trends. The optimal explanation method is selected based on the question trends. This makes it possible to select the optimal explanation method by referring to the new employee's past question history.

[0059] The supplemental explanation unit can customize the means of explanation based on the new employee's current work situation when providing supplemental explanation. The supplemental explanation unit provides supplemental explanation related to the work the new employee is currently working on, for example. The supplemental explanation unit can also select the optimal means of explanation depending on the new employee's work situation. Furthermore, the supplemental explanation unit can grasp the new employee's work situation in real time and provide appropriate supplemental explanation. For example, the supplemental explanation unit stores the new employee's work situation in a database and analyzes the data to grasp work trends. The optimal means of explanation is selected based on the work trends. This makes it possible to provide supplemental explanation using the optimal means depending on the new employee's current work situation.

[0060] When providing supplementary explanations, the supplementary explanation unit can select a method of explanation based on the new employee's geographical location information. For example, if the new employee is in a specific office, the supplementary explanation unit can provide supplementary explanations related to that office. Furthermore, if the new employee is on a business trip, the supplementary explanation unit can also provide supplementary explanations related to the business trip destination. Furthermore, if the new employee is working remotely, the supplementary explanation unit can also provide supplementary explanations related to work at home. For example, the supplementary explanation unit obtains the new employee's geographical location information using GPS data or IP address, and selects a method of explanation based on that information. This allows the new employee's geographical location information to be taken into consideration to provide supplementary explanations in the optimal manner.

[0061] The supplemental explanation unit can analyze the new employee's social media activity and suggest a means of explanation when providing supplemental explanation. For example, the supplemental explanation unit provides supplemental explanation related to the work that the new employee has shared on social media. The supplemental explanation unit can also provide supplemental explanation related to topics in which the new employee has shown interest on social media. Furthermore, the supplemental explanation unit can predict and provide supplemental explanation related to a specific work from the new employee's social media activity. For example, the supplemental explanation unit stores the new employee's social media activity in a database and analyzes the data to understand work trends. Based on the work trends, the optimal means of explanation is selected. In this way, by analyzing the new employee's social media activity, supplemental explanation can be provided using the optimal means.

[0062] When providing feedback, the feedback unit can select the optimal feedback method by referring to the new employee's past learning history. For example, the feedback unit provides feedback using a method that was easy for the new employee to understand in the past. The feedback unit can also prioritize feedback on learning methods that the new employee has used in the past. Furthermore, the feedback unit can select the optimal feedback method from the new employee's past learning history. For example, the feedback unit stores the new employee's past learning history in a database and analyzes the data to understand learning trends. The optimal feedback method is selected based on the learning trends. In this way, the optimal feedback method can be selected by referring to the new employee's past learning history.

[0063] When providing feedback, the feedback unit can customize the means of feedback based on the new employee's current work situation. For example, the feedback unit provides feedback related to the work the new employee is currently working on. The feedback unit can also select the optimal feedback means depending on the new employee's work situation. Furthermore, the feedback unit can grasp the new employee's work situation in real time and provide appropriate feedback. For example, the feedback unit stores the new employee's work situation in a database and analyzes the data to grasp work trends. The optimal feedback means is selected based on the work trends. This makes it possible to provide feedback using the optimal means depending on the new employee's current work situation.

[0064] When providing feedback, the feedback unit can select a feedback method based on the new employee's geographic location information. For example, if the new employee is in a specific office, the feedback unit provides feedback related to that office. Also, if the new employee is on a business trip, the feedback unit can provide feedback related to the business trip destination. Furthermore, if the new employee is working remotely, the feedback unit can provide feedback related to work at home. For example, the feedback unit obtains the new employee's geographic location information using GPS data or IP address, and selects a feedback method based on that information. This allows feedback to be provided in the optimal manner by taking the new employee's geographic location information into consideration.

[0065] When providing feedback, the feedback unit can analyze the new employee's social media activities and suggest a means of providing feedback. For example, the feedback unit provides feedback related to work that the new employee has shared on social media. The feedback unit can also provide feedback related to topics that the new employee has shown interest in on social media. Furthermore, the feedback unit can predict feedback related to specific work from the new employee's social media activities and provide the feedback. For example, the feedback unit stores the new employee's social media activities in a database and analyzes the data to understand work trends. Based on the work trends, the optimal means of feedback is selected. In this way, feedback can be provided using the optimal means by analyzing the new employee's social media activities.

[0066] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0067] The new employee training assistance system can further include an interactive simulation section. The simulation section allows new employees to experience actual work scenarios in a virtual environment. For example, the simulation section recreates specific work procedures in a virtual environment, allowing new employees to acquire practical skills by performing those procedures. The simulation section can also allow new employees to experience troubleshooting that may occur during work in a virtual environment. Furthermore, the simulation section can provide collaborative simulations in which multiple new employees can participate simultaneously, thereby improving teamwork skills. This allows new employees to learn in an environment that is closer to actual work, allowing them to acquire skills more effectively.

[0068] The new employee training assistance system can further include a planning unit that provides personalized learning plans. The planning unit analyzes the new employee's past learning history and question history to create a learning plan that is optimal for each individual new employee. For example, the planning unit can provide a learning plan that focuses on areas in which the new employee is weak. The planning unit can also adjust the learning plan to match the new employee's learning pace. Furthermore, the planning unit can customize the learning plan based on the new employee's goals. This allows the new employee to efficiently progress with their studies based on the learning plan that is optimal for them.

[0069] The new employee training assistance system can further include a style adaptation unit that provides content according to the new employee's learning style. The style adaptation unit analyzes the new employee's learning style and provides the most appropriate content. For example, the style adaptation unit can provide content that makes extensive use of illustrations and videos to a new employee who prefers visual learning. It can also provide content in the form of audio guides or podcasts to a new employee who prefers auditory learning. Furthermore, it can provide interactive simulations and practical training to a new employee who prefers practical learning. This allows a new employee to progress in their learning in a way that is best suited to them.

[0070] The new employee training assistance system can further include a dashboard section that visualizes the learning progress of new employees. The dashboard section visualizes and displays the learning progress of new employees in real time. For example, the dashboard section can display the learning progress of new employees in graphs and charts, making it possible to see at a glance in which areas progress is lagging behind. The dashboard section can also display the new employee's degree of achievement toward their learning goals. Furthermore, the dashboard section can display the new employee's learning history in chronological order, allowing the new employee to look back on their past learning performance. This allows the new employee to understand their learning progress and study efficiently.

[0071] The new employee training assistance system can further include a self-assessment unit for evaluating the new employee's learning outcomes. The self-assessment unit allows the new employee to evaluate their own learning outcomes. For example, the self-assessment unit can provide questions for the new employee to self-assess the content they have learned. The self-assessment unit can also record the results of the new employee's self-assessment and compare them with their learning progress. Furthermore, the self-assessment unit can suggest the new employee's next learning step based on the results of the new employee's self-assessment. This allows the new employee to evaluate their own learning outcomes and obtain guidelines for moving on to the next step.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The reception desk accepts questions from new employees about their work. Questions can be accepted in a variety of formats, including text, voice, and questions about specific topics. For example, questions entered in text format are analyzed using natural language processing technology, and questions entered in voice format are converted into text using speech recognition technology and then analyzed using natural language processing technology. Step 2: The generation unit analyzes the question received by the reception unit and searches for the relevant section of the appropriate manual. The generation unit uses natural language processing technology to analyze the content of the question and identify the relevant section of the manual. For example, it extracts keywords from the question and searches for the relevant section of the manual based on those keywords. It can also use context analysis to understand the content of the question and identify the relevant section of the manual. Step 3: The providing unit provides the answer generated by the generating unit. The providing unit can provide the answer in text format, audio format, diagram format, or the like. For example, the text format answer generated by the generating unit is provided as is. When providing the answer in audio format, the text format answer is converted into audio using speech synthesis technology and provided. Step 4: The progress tracking unit tracks the new employee's learning progress based on the answers provided by the providing unit. The progress tracking unit tracks the learning progress based on evaluation criteria such as test results, study time, and achievement level. For example, the progress tracking unit records the results of a test conducted by the new employee based on the answers provided, and evaluates the learning progress based on the results. It is also possible to record study time and achievement level and evaluate the learning progress based on these. Step 5: The evaluation unit evaluates the new employee's level of understanding based on the progress tracked by the progress tracking unit. The evaluation unit evaluates the level of understanding based on evaluation criteria such as the rate of correct answers on the test and the content of the feedback. For example, the evaluation unit may evaluate the new employee's level of understanding based on the rate of correct answers on the test. The evaluation unit may also evaluate the level of understanding based on the content of the feedback.

[0074] (Example 2) A new employee training assistance system according to an embodiment of the present invention uses a generation AI to assist new employee training in conjunction with a manual. In this new employee training assistance system, a new employee inputs questions or concerns about their work into the generation AI, which then searches for the relevant section of the appropriate manual and generates an answer. The generation AI then provides additional information and concrete examples related to the question, providing supplementary explanations to help the new employee understand. This mechanism allows new employees to quickly resolve their work-related concerns and progress efficiently. For example, a new employee inputs a question or concern about their work into the generation AI. For example, the new employee may input a specific question such as, "What are the procedures for this work?" or "Please tell me how to use this tool." This information is then input into the generation AI. The generation AI then analyzes the input question and searches for the relevant section of the appropriate manual. The generation AI then understands the content of the question and identifies the relevant section of the manual. For example, in response to the question, "What are the procedures for this work?", the generation AI searches for the relevant section of the manual regarding work procedures and generates the answer. The generation AI then provides additional information and concrete examples related to the question. For example, in response to a question such as "Please tell me how to use this tool," the generative AI provides supplementary explanations, including specific steps and important points on how to use the tool. This allows new employees to obtain not only the answer to their question but also related information, leading to a deeper understanding. This system allows new employees to quickly resolve questions about their work and progress efficiently in their learning. For example, if a new employee has a question while working, they can immediately enter the question into the generative AI and receive an appropriate answer. This allows new employees to progress in their learning at their own pace, improving work efficiency. This allows the new employee training assistance system to search for the relevant part of the manual in response to the new employee's question, provide an answer, track learning progress, and evaluate comprehension.

[0075] A new employee training assistance system according to an embodiment includes a reception unit, a generation unit, a provision unit, a progress tracking unit, and an evaluation unit. The reception unit receives questions from new employees regarding their work. Questions from new employees regarding their work include, but are not limited to, questions in text format, voice format, and questions about specific topics. The reception unit receives questions entered in text format, for example. The reception unit can also receive questions entered in voice format. The reception unit can also receive questions about specific topics. For example, the reception unit analyzes questions entered in text format using natural language processing technology to understand the content of the question. Questions entered in voice format are converted into text using speech recognition technology and then analyzed using natural language processing technology. The generation unit analyzes the questions received by the reception unit and searches for a relevant section of an appropriate manual. For example, the generation unit analyzes the content of the question using natural language processing technology and identifies a relevant section of the manual. For example, the generation unit extracts keywords from the question and searches for a relevant section of the manual based on the keywords. The generation unit can also use context analysis to understand the content of the question and identify the relevant section of the manual. The provision unit provides the answer generated by the generation unit. The provision unit can provide the answer, for example, in text format. The provision unit can also provide the answer in audio format. The provision unit can also provide the answer using diagrams. For example, the provision unit provides the text format answer generated by the generation unit as is. When providing the answer in audio format, the text format answer is converted into audio using speech synthesis technology and provided. The progress tracking unit tracks the new employee's learning progress based on the answers provided by the provision unit. The progress tracking unit tracks the learning progress based on evaluation criteria such as test results, study time, and achievement level. For example, the progress tracking unit records the results of a test conducted by the new employee based on the answers provided and evaluates the learning progress based on the results. It can also record study time and evaluate the learning progress based on the time. It can also record achievement level and evaluate the learning progress based on the achievement level. The evaluation unit evaluates the new employee's understanding based on the progress tracked by the progress tracking unit.The evaluation unit evaluates the level of understanding based on evaluation criteria such as the percentage of correct answers on a test and the content of feedback. For example, the evaluation unit evaluates the level of understanding of a new employee based on the percentage of correct answers on a test. The evaluation unit can also evaluate the level of understanding based on the content of feedback. As a result, the new employee training assistance system according to the embodiment can search for relevant parts of an appropriate manual in response to a question from a new employee, provide an answer, track learning progress, and evaluate the level of understanding.

[0076] The new employee training assistance system includes a history storage unit that stores a question history. The history storage unit stores the question history. The question history may be in a text format, a database structure, a storage period, or the like, but is not limited to these examples. The history storage unit stores, for example, a question history input in text format. The history storage unit can also store the question history based on the database structure. The history storage unit can also store the question history based on the storage period. For example, the history storage unit stores the question history input in text format in a database. The question history can also be classified and stored based on the database structure. The question history can also be periodically updated based on the storage period, and old question history can also be deleted. In this way, by storing the question history, past question content can be referenced.

[0077] The new employee training assistance system includes an update unit that updates the contents of the manual. The update unit updates the contents of the manual. The contents of the manual include, for example, update frequency, update criteria, update procedures, etc., but are not limited to these examples. The update unit, for example, periodically checks the contents of the manual and updates them as necessary. The update unit can also update the contents of the manual based on the update criteria. Furthermore, the update unit can also update the contents of the manual based on the update procedures. For example, the update unit periodically checks the contents of the manual and updates them based on the latest information. Important information can also be updated preferentially based on the update criteria. The contents of the manual can also be updated efficiently based on the update procedures. This allows the contents of the manual to be updated to the latest information.

[0078] The new employee training assistance system includes a supplementary explanation unit that provides additional information or specific examples related to the question. The supplementary explanation unit provides additional information or specific examples related to the question. Examples of additional information include, but are not limited to, related materials, links, and references. Examples of specific examples include, but are not limited to, actual case studies and simulation results. For example, the supplementary explanation unit provides materials related to the question. The supplementary explanation unit can also provide links related to the question. Furthermore, the supplementary explanation unit can provide references related to the question. For example, the supplementary explanation unit provides materials related to the question in digital form. When providing links, links to related web pages are provided. When providing references, information on related books and papers is provided. This makes it possible to provide related additional information and specific examples in addition to answers to questions.

[0079] The new employee training assistance system includes a feedback unit that provides regular feedback to new employees. The feedback unit provides regular feedback to new employees. Examples of feedback include, but are not limited to, regular reports, oral feedback, and feedback through an online platform. For example, the feedback unit provides regular reports. The feedback unit can also provide oral feedback. Furthermore, the feedback unit can provide feedback through an online platform. For example, the feedback unit sends regular reports by email. When providing oral feedback, the feedback is provided through regular meetings. When providing feedback through an online platform, a dedicated feedback system is used. By providing regular feedback to new employees, it is possible to check their learning progress and point out areas for improvement.

[0080] The reception unit can estimate the new employee's emotions and adjust the timing of accepting questions based on the estimated emotions. For example, if the new employee is feeling stressed, the generation AI can quickly accept questions and respond immediately. If the new employee is relaxed, the generation AI can accept questions at a normal pace and request more information. If the new employee is feeling anxious, the generation AI can prioritize accepting questions and provide quick answers. For example, the reception unit can capture the new employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the timing of accepting questions can be adjusted. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and adjust the timing of accepting questions. This allows the timing of accepting questions to be adjusted according to the new employee's emotions, allowing questions to be accepted at a more appropriate time.

[0081] The reception unit can analyze the new employee's past question history and select a question reception method. For example, the reception unit uses a generation AI to automatically predict and receive related questions based on the content of questions frequently asked by the new employee in the past. The reception unit can also prioritize receiving question formats (text, voice, etc.) that the new employee has used in the past. Furthermore, the reception unit can analyze the new employee's past question history to determine whether they tend to ask more questions during certain time periods and increase the number of questions received during those time periods. For example, the reception unit stores the new employee's past question history in a database and analyzes that data to understand question trends. Based on the question trends, the reception unit selects the optimal question reception method. In this way, the optimal question reception method can be selected by analyzing the new employee's past question history.

[0082] When receiving a question, the reception unit can filter the questions based on the new employee's current work situation and areas of interest. For example, the reception unit prioritizes receiving questions related to the work the new employee is currently working on. The reception unit can also filter and receive related questions based on the new employee's areas of interest. Furthermore, the reception unit can grasp the new employee's work situation in real time and receive appropriate questions. For example, the reception unit stores the new employee's work situation in a database and analyzes the data to grasp question trends. Based on the question trends, the reception unit selects the optimal question reception method. In this way, by filtering questions based on the new employee's current work situation and areas of interest, more relevant questions can be received.

[0083] The reception unit can estimate the new employee's emotions and prioritize the questions to be received based on the estimated emotions. For example, if the new employee is feeling stressed, the reception unit can have the generation AI prioritize important questions. Also, if the new employee is relaxed, the reception unit can have the generation AI prioritize ordinary questions. Furthermore, if the new employee is feeling anxious, the reception unit can have the generation AI prioritize urgent questions. For example, the reception unit can capture the new employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the priority of questions is determined. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and determine the priority of questions. This allows questions to be received in a more appropriate order by prioritizing questions according to the new employee's emotions.

[0084] When receiving questions, the reception unit can prioritize receiving highly relevant questions based on the new employee's geographical location information. For example, if the new employee is in a specific office, the reception unit can prioritize receiving questions related to that office. Also, if the new employee is on a business trip, the reception unit can prioritize receiving questions related to the business trip destination. Furthermore, if the new employee is working remotely, the reception unit can prioritize receiving questions related to work at home. For example, the reception unit obtains the new employee's geographical location information using GPS data or IP address, and determines the priority of questions based on that information. In this way, by taking the new employee's geographical location information into consideration, highly relevant questions can be prioritized.

[0085] When accepting a question, the reception unit can analyze the new employee's social media activity and accept related questions. For example, the reception unit prioritizes accepting questions related to work that the new employee has shared on social media. The reception unit can also accept questions related to topics in which the new employee has shown interest on social media. Furthermore, the reception unit can predict and accept questions related to specific work from the new employee's social media activity. For example, the reception unit stores the new employee's social media activity in a database and analyzes the data to understand question trends. Based on the question trends, the reception unit selects the optimal question acceptance method. In this way, relevant questions can be accepted by analyzing the new employee's social media activity.

[0086] The generation unit can estimate the new employee's emotions and adjust the way the answer is expressed based on the estimated emotions. For example, if the new employee is feeling stressed, the generation AI can generate a concise and easy-to-understand answer. Furthermore, if the new employee is relaxed, the generation unit can generate an answer that includes a detailed explanation. Furthermore, if the new employee is anxious, the generation unit can generate an answer that is quickly understandable. For example, the generation unit captures the new employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the way the answer is expressed can be adjusted. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and adjust the way the answer is expressed. This makes it possible to provide more appropriate answers by adjusting the way the answer is expressed according to the new employee's emotions.

[0087] When generating an answer, the generation unit can adjust the level of detail of the answer based on the importance of the question. For example, the generation unit allows the generation AI to generate a detailed answer to an important question. The generation unit can also allow the generation AI to generate a concise answer to a general question. Furthermore, the generation unit can also allow the generation AI to generate an answer that can be quickly addressed to a question with a high degree of urgency. For example, the generation unit stores the importance of the question in a database and analyzes the data to understand the trend of questions. Based on the trend of questions, the generation unit selects the optimal answer generation method. In this way, by adjusting the level of detail of the answer based on the importance of the question, it is possible to provide a more appropriate answer.

[0088] When generating an answer, the generation unit can apply different generation algorithms depending on the question category. For example, in the generation unit, the generation AI applies a specialized algorithm to generate an answer to a technical question. In addition, in the generation unit, the generation AI can apply an algorithm specialized for procedures to generate an answer to a question about business procedures. Furthermore, in the generation unit, the generation AI can apply an algorithm specialized for the tool to generate an answer to a question about how to use a tool. For example, the generation unit stores the question categories in a database and analyzes the data to understand question trends. Based on the question trends, the optimal generation algorithm is selected. In this way, by applying different generation algorithms depending on the question category, more appropriate answers can be provided.

[0089] The generation unit can estimate the new employee's emotions and adjust the length of the answer based on the estimated emotions. For example, if the new employee is feeling stressed, the generation AI can generate a short, to-the-point answer. Furthermore, if the new employee is relaxed, the generation unit can generate a longer answer with detailed explanations. Furthermore, if the new employee is anxious, the generation unit can generate a short answer that can be quickly understood. For example, the generation unit captures the new employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. The generation unit calculates an emotion score based on changes in facial expressions and adjusts the length of the answer. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and adjust the length of the answer. This allows the system to provide more appropriate answers by adjusting the length of the answer according to the new employee's emotions.

[0090] When generating answers, the generation unit can determine the priority of answers based on the time when the question was submitted. For example, the generation unit allows the generation AI to generate answers with priority for questions with high urgency. The generation unit can also allow the generation AI to generate answers with normal priority for normal questions. Furthermore, the generation unit can allow the generation AI to generate answers later for questions submitted in the past. For example, the generation unit stores the time when questions were submitted in a database and analyzes that data to understand question trends. Based on the question trends, the generation unit selects the optimal answer generation method. In this way, by determining the priority of answers based on the time when the question was submitted, answers can be provided in a more appropriate order.

[0091] When generating answers, the generation unit can adjust the order of answers based on the relevance of the question. For example, if the question is highly relevant, the generation unit can have the generation AI generate answers first. Also, if the question is general, the generation unit can have the generation AI generate answers in the normal order. Furthermore, if the question is less relevant, the generation unit can have the generation AI generate answers later. For example, the generation unit stores the relevance of questions in a database and analyzes that data to understand question trends. Based on the question trends, the generation unit selects the optimal answer generation method. As a result, by adjusting the order of answers based on the relevance of the question, answers can be provided in a more appropriate order.

[0092] The provision unit can estimate the new employee's emotions and adjust the way in which the answer is provided based on the estimated emotions. For example, if the new employee is feeling stressed, the provision unit can cause the generation AI to provide an answer in a concise and easy-to-understand manner. Furthermore, if the new employee is relaxed, the provision unit can cause the generation AI to provide an answer in a manner that includes detailed explanations. Furthermore, if the new employee is anxious, the provision unit can provide an answer in a manner that the generation AI can quickly understand. For example, the provision unit can capture the new employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the way in which the answer is provided can be adjusted. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and adjust the way in which the answer is provided. This makes it possible to provide answers in a more appropriate manner by adjusting the way in which the answer is provided according to the new employee's emotions.

[0093] When providing an answer, the providing unit can select the optimal method of providing the answer by referring to the newcomer's past learning history. For example, the providing unit provides the answer in a way that was easy for the newcomer to understand in the past. The providing unit can also provide learning methods that the newcomer has used in the past with priority. Furthermore, the providing unit can select the optimal method of providing the answer from the newcomer's past learning history. For example, the providing unit stores the newcomer's past learning history in a database and analyzes the data to understand learning trends. The optimal method of providing the answer is selected based on the learning trends. In this way, the optimal method of providing the answer can be selected by referring to the newcomer's past learning history.

[0094] When providing an answer, the providing unit can customize the means of providing the answer based on the new employee's current work situation. The providing unit, for example, provides an answer related to the work the new employee is currently working on. The providing unit can also select the optimal means of providing the answer based on the new employee's work situation. Furthermore, the providing unit can grasp the new employee's work situation in real time and provide an appropriate answer. For example, the providing unit stores the new employee's work situation in a database and analyzes the data to grasp work trends. The optimal means of providing the answer is selected based on the work trends. This makes it possible to provide an answer using the optimal means based on the new employee's current work situation.

[0095] The provision unit can estimate the new employee's emotions and determine the order in which answers will be provided based on the estimated emotions. For example, if the new employee is feeling stressed, the provision unit can cause the generation AI to prioritize important answers. Furthermore, if the new employee is relaxed, the provision unit can cause the generation AI to provide answers in the normal order. Furthermore, if the new employee is feeling anxious, the provision unit can cause the generation AI to prioritize urgent answers. For example, the provision unit can capture the new employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the order in which answers will be provided is determined. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and determine the order in which answers will be provided. In this way, by determining the order in which answers are provided according to the new employee's emotions, answers can be provided in a more appropriate order.

[0096] When providing an answer, the providing unit can select a method of providing the answer based on the new employee's geographic location information. For example, if the new employee is in a specific office, the providing unit can provide an answer related to that office. Furthermore, if the new employee is on a business trip, the providing unit can also provide an answer related to the business trip destination. Furthermore, if the new employee is working remotely, the providing unit can also provide an answer related to work from home. For example, the providing unit obtains the new employee's geographic location information using GPS data or IP address, and selects a method of providing the answer based on that information. This makes it possible to provide an answer in the most optimal way by taking the new employee's geographic location information into consideration.

[0097] When providing an answer, the providing unit can analyze the new employee's social media activity and suggest a means of providing the answer. For example, the providing unit provides answers related to work that the new employee has shared on social media. The providing unit can also provide answers related to topics in which the new employee has shown interest on social media. Furthermore, the providing unit can predict and provide answers related to specific work from the new employee's social media activity. For example, the providing unit stores the new employee's social media activity in a database and analyzes the data to understand work trends. Based on the work trends, the providing unit selects the optimal means of providing the answer. In this way, by analyzing the new employee's social media activity, it is possible to provide answers via the optimal means.

[0098] The progress tracking unit can estimate the new employee's emotions and adjust the progress tracking method based on the estimated emotions. For example, if the new employee is feeling stressed, the progress tracking unit allows the generation AI to track their progress in a concise and easy-to-understand manner. Furthermore, if the new employee is relaxed, the progress tracking unit can also allow the generation AI to track their progress in a manner that includes detailed explanations. Furthermore, if the new employee is feeling anxious, the progress tracking unit can track their progress in a manner that the generation AI can quickly understand. For example, the progress tracking unit captures the new employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the progress tracking method is adjusted. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and adjust the progress tracking method. This allows the progress tracking method to be adjusted according to the new employee's emotions, thereby tracking their progress in a more appropriate manner.

[0099] When tracking progress, the progress tracking unit can select the optimal tracking method by referring to the new employee's past learning history. The progress tracking unit, for example, tracks progress using a method that the new employee found easy to understand in the past. The progress tracking unit can also prioritize tracking learning methods that the new employee has used in the past. Furthermore, the progress tracking unit can select the optimal tracking method from the new employee's past learning history. For example, the progress tracking unit stores the new employee's past learning history in a database and analyzes the data to understand learning trends. The optimal tracking method is selected based on the learning trends. In this way, the optimal tracking method can be selected by referring to the new employee's past learning history.

[0100] When tracking progress, the progress tracking unit can customize the tracking method based on the new employee's current work status. For example, the progress tracking unit prioritizes tracking of progress related to the work the new employee is currently working on. The progress tracking unit can also select the optimal tracking method depending on the new employee's work status. Furthermore, the progress tracking unit can grasp the new employee's work status in real time and track progress appropriately. For example, the progress tracking unit stores the new employee's work status in a database and analyzes the data to grasp work trends. The optimal tracking method is selected based on the work trends. This makes it possible to track progress using the optimal method depending on the new employee's current work status.

[0101] The progress tracking unit can estimate the new employee's emotions and determine the priority of progress tracking based on the estimated emotions. For example, if the new employee is feeling stressed, the generation AI can prioritize tracking important progress. In addition, if the new employee is relaxed, the generation AI can prioritize tracking normal progress. Furthermore, if the new employee is feeling anxious, the generation AI can prioritize tracking urgent progress. For example, the progress tracking unit captures the new employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the priority of progress tracking is determined. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and determine the priority of progress tracking. This allows progress tracking to be tracked in a more appropriate order by prioritizing progress tracking according to the new employee's emotions.

[0102] When tracking progress, the progress tracking unit can select the optimal tracking method by taking into account the geographic location information of the new employee. For example, if the new employee is in a specific office, the progress tracking unit can prioritize tracking progress related to that office. Also, if the new employee is on a business trip, the progress tracking unit can prioritize tracking progress related to the business trip destination. Furthermore, if the new employee is working remotely, the progress tracking unit can prioritize tracking progress related to work at home. For example, the progress tracking unit obtains the geographic location information of the new employee using GPS data or IP address, and selects the progress tracking method based on that information. In this way, progress can be tracked in the optimal way by taking into account the geographic location information of the new employee.

[0103] When tracking progress, the progress tracking unit can analyze the new employee's social media activities and suggest tracking methods. For example, the progress tracking unit prioritizes tracking work-related progress that the new employee has shared on social media. The progress tracking unit can also track progress related to topics in which the new employee has shown interest on social media. Furthermore, the progress tracking unit can predict and track progress related to specific work from the new employee's social media activities. For example, the progress tracking unit stores the new employee's social media activities in a database and analyzes the data to understand work trends. The optimal tracking method is selected based on the work trends. In this way, progress can be tracked using the optimal method by analyzing the new employee's social media activities.

[0104] The evaluation unit can estimate the new employee's emotions and adjust the evaluation method based on the estimated emotions. For example, if the new employee is feeling stressed, the evaluation unit can have the generation AI evaluate them in a concise and easy-to-understand manner. If the new employee is relaxed, the evaluation unit can also have the generation AI evaluate them in a way that includes detailed explanations. Furthermore, if the new employee is anxious, the evaluation unit can also evaluate them in a way that the generation AI can quickly understand. For example, the evaluation unit can capture the new employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the evaluation method is adjusted. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and adjust the evaluation method. This allows the evaluation method to be adjusted according to the new employee's emotions, making it possible to perform a more appropriate evaluation.

[0105] During evaluation, the evaluation unit can select the optimal evaluation method by referring to the newcomer's past learning history. The evaluation unit, for example, performs evaluation using a method that the newcomer found easy to understand in the past. The evaluation unit can also prioritize evaluation of learning methods that the newcomer has used in the past. Furthermore, the evaluation unit can select the optimal evaluation method from the newcomer's past learning history. For example, the evaluation unit stores the newcomer's past learning history in a database and analyzes the data to understand learning trends. The optimal evaluation method is selected based on the learning trends. In this way, the optimal evaluation method can be selected by referring to the newcomer's past learning history.

[0106] At the time of evaluation, the evaluation department can customize the evaluation method based on the new employee's current work situation. For example, the evaluation department performs evaluation related to the work the new employee is currently working on. The evaluation department can also select the most appropriate evaluation method depending on the new employee's work situation. Furthermore, the evaluation department can grasp the new employee's work situation in real time and perform an appropriate evaluation. For example, the evaluation department stores the new employee's work situation in a database and analyzes the data to grasp work trends. The evaluation department selects the most appropriate evaluation method based on the work trends. This allows evaluation to be performed using the most appropriate method depending on the new employee's current work situation.

[0107] The evaluation unit can estimate the new employee's emotions and determine the priority of the evaluations based on the estimated emotions. For example, if the new employee is feeling stressed, the evaluation unit can have the generation AI prioritize important evaluations. Also, if the new employee is relaxed, the evaluation unit can have the generation AI prioritize normal evaluations. Furthermore, if the new employee is feeling anxious, the evaluation unit can have the generation AI prioritize urgent evaluations. For example, the evaluation unit can capture the new employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the priority of the evaluations is determined. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and determine the priority of the evaluations. This allows the evaluations to be performed in a more appropriate order by prioritizing the evaluations according to the new employee's emotions.

[0108] During the evaluation, the evaluation unit can select an evaluation method based on the new employee's geographic location information. For example, if the new employee is in a specific office, the evaluation unit performs an evaluation related to that office. In addition, if the new employee is on a business trip, the evaluation unit can also perform an evaluation related to the business trip destination. Furthermore, if the new employee is working remotely, the evaluation unit can also perform an evaluation related to work at home. For example, the evaluation unit obtains the new employee's geographic location information using GPS data or IP address, and selects an evaluation method based on that information. This allows the evaluation to be performed in the most optimal way by taking the new employee's geographic location information into consideration.

[0109] During the evaluation, the evaluation unit can analyze the new employee's social media activity and suggest evaluation methods. For example, the evaluation unit performs evaluations related to the work that the new employee shared on social media. The evaluation unit can also perform evaluations related to topics in which the new employee showed interest on social media. Furthermore, the evaluation unit can predict and evaluate evaluations related to specific work from the new employee's social media activity. For example, the evaluation unit stores the new employee's social media activity in a database and analyzes the data to understand work trends. Based on the work trends, the evaluation unit selects the most appropriate evaluation method. In this way, by analyzing the new employee's social media activity, evaluation can be performed using the most appropriate method.

[0110] The history storage unit can estimate the new employee's emotions and adjust the history storage method based on the estimated emotions. For example, if the new employee is feeling stressed, the history storage unit can store the history in a concise and easy-to-understand manner for the generation AI. Furthermore, if the new employee is relaxed, the history storage unit can store the history in a way that includes detailed explanations for the generation AI. Furthermore, if the new employee is feeling anxious, the history storage unit can store the history in a way that the generation AI can quickly understand. For example, the history storage unit can capture the new employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the history storage method is adjusted accordingly. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and adjust the history storage method. This allows the history storage method to be adjusted according to the new employee's emotions, thereby saving the history in a more appropriate manner.

[0111] When saving history, the history storage unit can select the optimal storage method by referring to the new employee's past question history. For example, the history storage unit allows the generation AI to automatically save related history based on the content of questions frequently asked by the new employee in the past. The history storage unit can also prioritize saving question formats (text, voice, etc.) used by the new employee in the past. Furthermore, the history storage unit can analyze the new employee's past question history to determine whether they tend to ask more questions during certain time periods and strengthen storage during those time periods. For example, the history storage unit stores the new employee's past question history in a database and analyzes that data to understand question trends. The optimal storage method is selected based on the question trends. In this way, the optimal storage method can be selected by referring to the new employee's past question history.

[0112] The history storage unit can estimate the new employee's emotions and determine the priority of history storage based on the estimated emotions. For example, if the new employee is feeling stressed, the generation AI can prioritize saving important history. Furthermore, if the new employee is relaxed, the generation AI can prioritize saving regular history. Furthermore, if the new employee is feeling anxious, the generation AI can prioritize saving urgent history. For example, the history storage unit captures the new employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the priority of history storage is determined. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and determine the priority of history storage. This allows history storage to be prioritized according to the new employee's emotions, allowing the history to be stored in a more appropriate order.

[0113] When saving history, the history saving unit can select the optimal saving method by taking into account the new employee's geographical location information. For example, if the new employee is in a specific office, the history saving unit can prioritize saving history related to that office. Also, if the new employee is on a business trip, the history saving unit can prioritize saving history related to the business trip destination. Furthermore, if the new employee is working remotely, the history saving unit can prioritize saving history related to work at home. For example, the history saving unit obtains the new employee's geographical location information using GPS data or IP address, and selects the saving method based on that information. In this way, the history can be saved in the optimal way by taking into account the new employee's geographical location information.

[0114] The update unit can estimate the new employee's emotions and adjust the method for updating the manual based on the estimated emotions. For example, if the new employee is feeling stressed, the update unit causes the generation AI to update the manual in a concise and easy-to-understand manner. Furthermore, if the new employee is relaxed, the update unit can also cause the generation AI to update the manual in a manner that includes detailed explanations. Furthermore, if the new employee is feeling anxious, the update unit can also update the manual in a manner that the generation AI can quickly understand. For example, the update unit captures the new employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the method for updating the manual is adjusted. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and adjust the method for updating the manual. This allows the manual to be updated in a more appropriate manner by adjusting the method for updating the manual according to the new employee's emotions.

[0115] When updating manuals, the update department can select the optimal update method by referring to the new employee's past question history. For example, the update department uses the generation AI to automatically update the relevant manuals based on the content of questions frequently asked by the new employee in the past. The update department can also prioritize updating question formats (text, voice, etc.) that the new employee has used in the past. Furthermore, the update department can analyze the new employee's past question history to determine the tendency for questions to be asked frequently during specific time periods and strengthen updates during those time periods. For example, the update department stores the new employee's past question history in a database and analyzes that data to understand question trends. The optimal update method is selected based on the question trends. In this way, the optimal update method can be selected by referring to the new employee's past question history.

[0116] The update unit can estimate the new employee's emotions and determine the priority of manual update based on the estimated emotions. For example, if the new employee is feeling stressed, the generation AI can prioritize updating important manuals. Furthermore, if the new employee is relaxed, the generation AI can prioritize updating regular manuals. Furthermore, if the new employee is feeling anxious, the generation AI can prioritize updating manuals with high urgency. For example, the update unit can capture the new employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the priority of manual update is determined. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and determine the priority of manual update. This allows manual update priorities to be determined according to the new employee's emotions, making it possible to update manuals in a more appropriate order.

[0117] When updating manuals, the update unit can select the optimal update method by taking into account the new employee's geographic location information. For example, if the new employee is in a specific office, the update unit prioritizes updating manuals related to that office. Also, if the new employee is on a business trip, the update unit can prioritize updating manuals related to the business trip destination. Furthermore, if the new employee is working remotely, the update unit can prioritize updating manuals related to work at home. For example, the update unit obtains the new employee's geographic location information using GPS data or IP address, and selects the update method based on that information. In this way, the manuals can be updated in the optimal way by taking into account the new employee's geographic location information.

[0118] The supplementary explanation unit can estimate the new employee's emotions and adjust the method of supplementary explanation based on the estimated emotions. For example, if the new employee is feeling stressed, the supplementary explanation unit can cause the generation AI to provide supplementary explanation in a concise and easy-to-understand manner. Furthermore, if the new employee is relaxed, the supplementary explanation unit can cause the generation AI to provide supplementary explanation in a manner that includes detailed explanations. Furthermore, if the new employee is anxious, the supplementary explanation unit can provide supplementary explanation in a manner that the generation AI can quickly understand. For example, the supplementary explanation unit can capture the new employee's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expression, and the method of supplementary explanation is adjusted. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and adjust the method of supplementary explanation. In this way, by adjusting the method of supplementary explanation according to the new employee's emotions, supplementary explanation can be provided in a more appropriate manner.

[0119] When providing supplementary explanations, the supplementary explanation unit can select the optimal explanation method by referring to the new employee's past question history. For example, the supplementary explanation unit uses the generation AI to automatically provide relevant supplementary explanations based on the content of questions frequently asked by the new employee in the past. The supplementary explanation unit can also prioritize explanations based on question formats (text, voice, etc.) used by the new employee in the past. Furthermore, the supplementary explanation unit can analyze the new employee's past question history to determine whether they tend to ask more questions during certain time periods, and strengthen explanations during those time periods. For example, the supplementary explanation unit stores the new employee's past question history in a database and analyzes that data to understand question trends. The optimal explanation method is selected based on the question trends. This makes it possible to select the optimal explanation method by referring to the new employee's past question history.

[0120] The supplemental explanation unit can customize the means of explanation based on the new employee's current work situation when providing supplemental explanation. The supplemental explanation unit provides supplemental explanation related to the work the new employee is currently working on, for example. The supplemental explanation unit can also select the optimal means of explanation depending on the new employee's work situation. Furthermore, the supplemental explanation unit can grasp the new employee's work situation in real time and provide appropriate supplemental explanation. For example, the supplemental explanation unit stores the new employee's work situation in a database and analyzes the data to grasp work trends. The optimal means of explanation is selected based on the work trends. This makes it possible to provide supplemental explanation using the optimal means depending on the new employee's current work situation.

[0121] The supplemental explanation unit can estimate the new employee's emotions and determine the priority of supplemental explanations based on the estimated emotions. For example, if the new employee is feeling stressed, the supplemental explanation unit can cause the generation AI to prioritize important supplemental explanations. Furthermore, if the new employee is relaxed, the supplemental explanation unit can cause the generation AI to prioritize regular supplemental explanations. Furthermore, if the new employee is feeling anxious, the supplemental explanation unit can cause the generation AI to prioritize urgent supplemental explanations. For example, the supplemental explanation unit can capture the new employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the priority of supplemental explanations is determined. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and determine the priority of supplemental explanations. This allows supplemental explanations to be provided in a more appropriate order by prioritizing supplemental explanations according to the new employee's emotions.

[0122] When providing supplementary explanations, the supplementary explanation unit can select a method of explanation based on the new employee's geographical location information. For example, if the new employee is in a specific office, the supplementary explanation unit can provide supplementary explanations related to that office. Furthermore, if the new employee is on a business trip, the supplementary explanation unit can also provide supplementary explanations related to the business trip destination. Furthermore, if the new employee is working remotely, the supplementary explanation unit can also provide supplementary explanations related to work at home. For example, the supplementary explanation unit obtains the new employee's geographical location information using GPS data or IP address, and selects a method of explanation based on that information. This allows the new employee's geographical location information to be taken into consideration to provide supplementary explanations in the optimal manner.

[0123] The supplemental explanation unit can analyze the new employee's social media activity and suggest a means of explanation when providing supplemental explanation. For example, the supplemental explanation unit provides supplemental explanation related to the work that the new employee has shared on social media. The supplemental explanation unit can also provide supplemental explanation related to topics in which the new employee has shown interest on social media. Furthermore, the supplemental explanation unit can predict and provide supplemental explanation related to a specific work from the new employee's social media activity. For example, the supplemental explanation unit stores the new employee's social media activity in a database and analyzes the data to understand work trends. Based on the work trends, the optimal means of explanation is selected. In this way, by analyzing the new employee's social media activity, supplemental explanation can be provided using the optimal means.

[0124] The feedback unit can estimate the new employee's emotions and adjust the feedback method based on the estimated emotions. For example, if the new employee is feeling stressed, the feedback unit allows the generation AI to provide feedback in a concise and easy-to-understand manner. Also, if the new employee is relaxed, the feedback unit can provide feedback in a manner that includes detailed explanations. Furthermore, if the new employee is feeling anxious, the feedback unit can provide feedback in a manner that the generation AI can quickly understand. For example, the feedback unit captures the new employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and the feedback method is adjusted. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and adjust the feedback method. This allows feedback to be provided in a more appropriate manner by adjusting the feedback method according to the new employee's emotions.

[0125] When providing feedback, the feedback unit can select the optimal feedback method by referring to the new employee's past learning history. For example, the feedback unit provides feedback using a method that was easy for the new employee to understand in the past. The feedback unit can also prioritize feedback on learning methods that the new employee has used in the past. Furthermore, the feedback unit can select the optimal feedback method from the new employee's past learning history. For example, the feedback unit stores the new employee's past learning history in a database and analyzes the data to understand learning trends. The optimal feedback method is selected based on the learning trends. In this way, the optimal feedback method can be selected by referring to the new employee's past learning history.

[0126] When providing feedback, the feedback unit can customize the means of feedback based on the new employee's current work situation. For example, the feedback unit provides feedback related to the work the new employee is currently working on. The feedback unit can also select the optimal feedback means depending on the new employee's work situation. Furthermore, the feedback unit can grasp the new employee's work situation in real time and provide appropriate feedback. For example, the feedback unit stores the new employee's work situation in a database and analyzes the data to grasp work trends. The optimal feedback means is selected based on the work trends. This makes it possible to provide feedback using the optimal means depending on the new employee's current work situation.

[0127] The feedback unit can estimate the new employee's emotions and determine the priority of feedback based on the estimated emotions. For example, if the new employee is feeling stressed, the feedback unit can have the generation AI prioritize important feedback. Also, if the new employee is relaxed, the feedback unit can have the generation AI prioritize regular feedback. Furthermore, if the new employee is feeling anxious, the feedback unit can have the generation AI prioritize urgent feedback. For example, the feedback unit can capture the new employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. An emotion score is calculated based on changes in facial expressions, and feedback priorities are determined. Voice analysis technology can also be used to analyze the tone and speed of the new employee's voice, calculate an emotion score, and determine feedback priorities. This allows feedback to be provided in a more appropriate order by prioritizing feedback according to the new employee's emotions.

[0128] When providing feedback, the feedback unit can select a feedback method based on the new employee's geographic location information. For example, if the new employee is in a specific office, the feedback unit provides feedback related to that office. Also, if the new employee is on a business trip, the feedback unit can provide feedback related to the business trip destination. Furthermore, if the new employee is working remotely, the feedback unit can provide feedback related to work at home. For example, the feedback unit obtains the new employee's geographic location information using GPS data or IP address, and selects a feedback method based on that information. This allows feedback to be provided in the optimal manner by taking the new employee's geographic location information into consideration.

[0129] When providing feedback, the feedback unit can analyze the new employee's social media activities and suggest a means of providing feedback. For example, the feedback unit provides feedback related to work that the new employee has shared on social media. The feedback unit can also provide feedback related to topics that the new employee has shown interest in on social media. Furthermore, the feedback unit can predict feedback related to specific work from the new employee's social media activities and provide the feedback. For example, the feedback unit stores the new employee's social media activities in a database and analyzes the data to understand work trends. Based on the work trends, the optimal means of feedback is selected. In this way, feedback can be provided using the optimal means by analyzing the new employee's social media activities. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned receiving unit, generating unit, providing unit, progress tracking unit, evaluating unit, history saving unit, updating unit, supplementary explanation unit, and feedback unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the receiving unit is realized by the control unit 46A of the smart device 14, and the new employee inputs a question about the job. The generating unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the question and searches for the corresponding part of the appropriate manual. The providing unit is realized by the control unit 46A of the smart device 14, and provides the generated answer to the new employee. The progress tracking unit is realized by the specific processing unit 290 of the data processing device 12, and tracks the new employee's learning progress. The evaluating unit is realized by the specific processing unit 290 of the data processing device 12, and evaluates the new employee's level of understanding. The history saving unit is realized by the specific processing unit 290 of the data processing device 12, and stores the question history. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and updates the contents of the manual. The supplementary explanation unit is realized, for example, by the control unit 46A of the smart device 14 and provides additional information and specific examples related to questions. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides regular feedback to new employees. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, provision unit, progress tracking unit, evaluation unit, history storage unit, update unit, supplemental explanation unit, and feedback unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214, and the new employee inputs a question related to the work. The generation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes the question and searches for the corresponding portion of the appropriate manual. The provision unit is realized by, for example, the control unit 46A of the smart glasses 214, and provides the generated answer to the new employee. The progress tracking unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and tracks the new employee's learning progress. The evaluation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and evaluates the new employee's level of understanding. The history storage unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and stores the question history. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and updates the contents of the manual. The supplementary explanation unit is realized, for example, by the control unit 46A of the smart glasses 214, and provides additional information and specific examples related to questions. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides regular feedback to new employees. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned receiving unit, generating unit, providing unit, progress tracking unit, evaluating unit, history saving unit, updating unit, supplementary explanation unit, and feedback unit, is implemented, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the receiving unit is implemented by the control unit 46A of the headset-type terminal 314, and the new employee inputs a question related to the work. The generating unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the question and searches for the corresponding part of the appropriate manual. The providing unit is implemented, for example, by the control unit 46A of the headset-type terminal 314, and provides the generated answer to the new employee. The progress tracking unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and tracks the new employee's learning progress. The evaluating unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the new employee's level of understanding. The history saving unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and saves the question history. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and updates the contents of the manual. The supplementary explanation unit is realized, for example, by the control unit 46A of the headset terminal 314, and provides additional information and specific examples related to questions. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides regular feedback to new employees. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned receiving unit, generating unit, providing unit, progress tracking unit, evaluating unit, history saving unit, updating unit, supplementary explanation unit, and feedback unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the receiving unit is realized by the control unit 46A of the robot 414, and the new employee inputs a question related to the work. The generating unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the question and searches for the corresponding part of the appropriate manual. The providing unit is realized, for example, by the control unit 46A of the robot 414, and provides the generated answer to the new employee. The progress tracking unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and tracks the new employee's learning progress. The evaluating unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and evaluates the new employee's level of understanding. The history saving unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and saves the question history. The update unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and updates the contents of the manual. The supplementary explanation unit is realized, for example, by the control unit 46A of the robot 414, and provides additional information and specific examples related to questions. The feedback unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and provides regular feedback to new employees.

[0130] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0131] The new employee training assistance system can further include an interactive simulation section. The simulation section allows new employees to experience actual work scenarios in a virtual environment. For example, the simulation section recreates specific work procedures in a virtual environment, allowing new employees to acquire practical skills by performing those procedures. The simulation section can also allow new employees to experience troubleshooting that may occur during work in a virtual environment. Furthermore, the simulation section can provide collaborative simulations in which multiple new employees can participate simultaneously, thereby improving teamwork skills. This allows new employees to learn in an environment that is closer to actual work, allowing them to acquire skills more effectively.

[0132] The new employee training assistance system can further include a planning unit that provides personalized learning plans. The planning unit analyzes the new employee's past learning history and question history to create a learning plan that is optimal for each individual new employee. For example, the planning unit can provide a learning plan that focuses on areas in which the new employee is weak. The planning unit can also adjust the learning plan to match the new employee's learning pace. Furthermore, the planning unit can customize the learning plan based on the new employee's goals. This allows the new employee to efficiently progress with their studies based on the learning plan that is optimal for them.

[0133] The new employee training assistance system can further include a motivation unit that uses the emotion estimation function to improve the motivation of new employees. The motivation unit estimates the emotions of the new employee and provides feedback and actions to improve motivation based on the estimated emotions. For example, if the new employee is feeling stressed, the motivation unit can suggest an activity that will help the new employee relax. Also, if the new employee feels a sense of accomplishment, the motivation unit can provide feedback that encourages the new employee to take further challenges. Furthermore, if the new employee is tired, the motivation unit can encourage the new employee to take a break. This allows the new employee to continue learning while always maintaining high motivation.

[0134] The new employee training assistance system can further include a health management unit that monitors the health status of new employees. The health management unit monitors the health status of new employees in real time and issues alerts as necessary. For example, the health management unit can monitor the new employee's heart rate and stress level and issue an alert if an abnormality is detected. The health management unit can also issue an alert to encourage a new employee to take a break if the new employee has been working continuously for a long period of time. Furthermore, the health management unit can suggest appropriate actions based on the new employee's health status. This allows new employees to efficiently progress with their studies while maintaining their health.

[0135] The new employee training assistance system can further include a style adaptation unit that provides content according to the new employee's learning style. The style adaptation unit analyzes the new employee's learning style and provides the most appropriate content. For example, the style adaptation unit can provide content that makes extensive use of illustrations and videos to a new employee who prefers visual learning. It can also provide content in the form of audio guides or podcasts to a new employee who prefers auditory learning. Furthermore, it can provide interactive simulations and practical training to a new employee who prefers practical learning. This allows a new employee to progress in their learning in a way that is best suited to them.

[0136] The new employee training assistance system can further include a stress management unit that uses the emotion estimation function to manage the new employee's stress level. The stress management unit estimates the new employee's emotion and manages the stress level based on the estimated emotion. For example, if the new employee is feeling high stress, the stress management unit can suggest an activity that will help the new employee relax. If the new employee is not feeling stressed, the stress management unit can also continue with the regular study plan. Furthermore, if the new employee is feeling moderate stress, the stress management unit can suggest actions to reduce stress. This allows the new employee to efficiently progress with their studies while managing their stress.

[0137] The new employee training assistance system can further include a dashboard section that visualizes the learning progress of new employees. The dashboard section visualizes and displays the learning progress of new employees in real time. For example, the dashboard section can display the learning progress of new employees in graphs and charts, making it possible to see at a glance in which areas progress is lagging behind. The dashboard section can also display the new employee's degree of achievement toward their learning goals. Furthermore, the dashboard section can display the new employee's learning history in chronological order, allowing the new employee to look back on their past learning performance. This allows the new employee to understand their learning progress and study efficiently.

[0138] The new employee training assistance system may further include a feedback personalization unit that personalizes the feedback to the new employee using the emotion estimation function. The feedback personalization unit estimates the emotion of the new employee and personalizes the feedback based on the estimated emotion. For example, if the new employee is feeling stressed, the feedback personalization unit may provide feedback that includes encouraging words. If the new employee is relaxed, the feedback personalization unit may also provide detailed feedback. Furthermore, if the new employee is feeling impatient, the feedback personalization unit may provide feedback that is easy to understand quickly. This allows the new employee to receive feedback that corresponds to their emotions and progress in learning efficiently.

[0139] The new employee training assistance system can further include a self-assessment unit for evaluating the new employee's learning outcomes. The self-assessment unit allows the new employee to evaluate their own learning outcomes. For example, the self-assessment unit can provide questions for the new employee to self-assess the content they have learned. The self-assessment unit can also record the results of the new employee's self-assessment and compare them with their learning progress. Furthermore, the self-assessment unit can suggest the new employee's next learning step based on the results of the new employee's self-assessment. This allows the new employee to evaluate their own learning outcomes and obtain guidelines for moving on to the next step.

[0140] The new employee training assistance system can further include an environment optimization unit that optimizes the new employee's learning environment using the emotion estimation function. The environment optimization unit estimates the new employee's emotions and optimizes the learning environment based on the estimated emotions. For example, if the new employee is feeling stressed, the environment optimization unit can suggest an environment that helps the new employee relax. Also, if the new employee is relaxed, the environment optimization unit can suggest an environment that helps the new employee improve their concentration. Furthermore, if the new employee is feeling anxious, the environment optimization unit can suggest an environment where the new employee can study calmly. This allows the new employee to efficiently progress with their studies in an optimal learning environment.

[0141] The processing flow of the second embodiment will be briefly explained below.

[0142] Step 1: The reception desk accepts questions from new employees about their work. Questions can be accepted in a variety of formats, including text, voice, and questions about specific topics. For example, questions entered in text format are analyzed using natural language processing technology, and questions entered in voice format are converted into text using speech recognition technology and then analyzed using natural language processing technology. Step 2: The generation unit analyzes the question received by the reception unit and searches for the relevant section of the appropriate manual. The generation unit uses natural language processing technology to analyze the content of the question and identify the relevant section of the manual. For example, it extracts keywords from the question and searches for the relevant section of the manual based on those keywords. It can also use context analysis to understand the content of the question and identify the relevant section of the manual. Step 3: The providing unit provides the answer generated by the generating unit. The providing unit can provide the answer in text format, audio format, diagram format, or the like. For example, the text format answer generated by the generating unit is provided as is. When providing the answer in audio format, the text format answer is converted into audio using speech synthesis technology and provided. Step 4: The progress tracking unit tracks the new employee's learning progress based on the answers provided by the providing unit. The progress tracking unit tracks the learning progress based on evaluation criteria such as test results, study time, and achievement level. For example, the progress tracking unit records the results of a test conducted by the new employee based on the answers provided, and evaluates the learning progress based on the results. It is also possible to record study time and achievement level and evaluate the learning progress based on these. Step 5: The evaluation unit evaluates the new employee's level of understanding based on the progress tracked by the progress tracking unit. The evaluation unit evaluates the level of understanding based on evaluation criteria such as the rate of correct answers on the test and the content of the feedback. For example, the evaluation unit may evaluate the new employee's level of understanding based on the rate of correct answers on the test. The evaluation unit may also evaluate the level of understanding based on the content of the feedback.

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0145] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0148] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0154] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0157] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0161] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0164] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0165] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0166] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0167] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0169] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0170] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0171] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0172] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0173] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0174] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0175] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0176] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0177] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0178] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0179] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0180] 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.

[0181] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0182] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0183] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0184] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0185] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0186] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0187] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0188] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0189] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0190] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0191] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0192] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0193] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0194] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0195] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0196] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0197] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0198] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0199] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0200] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0201] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0202] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0203] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0204] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0205] 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.

[0206] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0207] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0208] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0209] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0210] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0211] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0212] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0213] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0214] [Explanation of symbols]

[0215] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception section for accepting questions; a generation unit that analyzes the question received by the reception unit and searches for a corresponding part of the manual; a providing unit that provides the answer generated by the generating unit; a progress tracking unit that tracks the learning progress of the newcomer based on the answers provided by the providing unit; an evaluation unit that evaluates the new employee's understanding level based on the progress tracked by the progress tracking unit; Equipped with A system characterized by:

2. Equipped with a history storage unit that stores question history The system of claim 1 .

3. Equipped with an update section to update the contents of the manual The system of claim 1 .

4. Provide a supplemental explanation section that provides additional information or examples related to the question The system of claim 1 .

5. Have a feedback department that provides regular feedback to new employees The system of claim 1 .

6. The reception unit Estimate the emotions of new employees and adjust the timing of accepting questions based on the estimated emotions. The system of claim 1 .

7. The reception unit Analyze past question history of new employees and decide how to accept questions The system of claim 1 .

8. The reception unit When accepting questions, filter them based on the new hire's current work situation and areas of interest. The system of claim 1 .

9. The reception unit Estimate the emotions of new employees and prioritize the questions they should ask based on the estimated emotions. The system of claim 1 .

Images