System

Abstract

An object of a system according to an embodiment is to perform voice reproduction and immediate resolution of an unclear point according to a working speed of a staff member.SOLUTION: A system includes an adjustment unit, a reproduction unit, an answer unit, and an optimization unit. The adjustment unit detects the working speed of the staff. The reproduction unit adjusts the sound reproduction based on the work speed detected by the adjustment unit. The answering unit analyzes the question of the staff using a voice recognition technique and immediately provides an answer. The optimization unit records unclear points and questions that occur during the work, aggregates information, and improves the manual.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology does not adequately provide manuals that match the work speed of staff or immediately resolve any unclear points, so there is room for improvement.

[0005] The system according to the embodiment aims to reproduce audio in accordance with the working speed of the staff and to immediately resolve any unclear points. [Means for solving the problem]

[0006] The system according to the embodiment includes an adjustment unit, a playback unit, an answering unit, and an optimization unit. The adjustment unit detects the working speed of the staff member. The playback unit adjusts the audio playback based on the working speed detected by the adjustment unit. The answering unit analyzes the staff member's questions using voice recognition technology and provides immediate answers. The optimization unit records any unclear points or questions that arise during work, consolidates the information, and improves the manual. [Effects of the Invention]

[0007] The system according to the embodiment can play audio according to the working speed of the staff and immediately resolve any unclear points. [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 system according to an embodiment of the present invention plays back information from a manual aloud in accordance with the staff's work speed, allowing them to resolve any questions as they arise. When a staff member begins work, the system plays back information from the manual aloud. The audio playback is adjusted to match the staff member's work speed. When a staff member encounters a question, they ask it immediately, and the system provides an immediate answer. This allows the staff member to resolve the question without interrupting their work. Furthermore, the system records any questions or questions that arise during work and aggregates the information. Based on the aggregated information, points that may lead to errors are identified and the manual is automatically optimized. For example, if questions frequently arise about a particular procedure, the explanation for that procedure is detailed. In this way, the manual is always kept up to date, improving staff work efficiency. This allows the system to improve staff work efficiency and reduce the occurrence of errors. Furthermore, automatically optimizing the manual ensures that the latest information is always provided, contributing to the improvement of staff skills.

[0029] The work assistance system according to the embodiment includes an adjustment unit, a playback unit, a response unit, and an optimization unit. The adjustment unit detects the work speed of the staff member. For example, the adjustment unit can detect the work speed of the staff member using a sensor. The adjustment unit can also monitor the work speed of the staff member in real time and adjust the detection accuracy according to changes in the work speed. The playback unit adjusts audio playback based on the work speed detected by the adjustment unit. For example, the playback unit can change the speed of the audio playback to match the work speed of the staff member. The playback unit can also adjust the content of the audio playback according to the work progress of the staff member. Furthermore, the playback unit can adjust the volume of the audio playback according to the work environment of the staff member. The response unit analyzes the staff member's question using voice recognition technology and provides an answer immediately. For example, the response unit can provide an answer immediately from a pre-registered answer database. The response unit can also select and provide an optimal answer according to the content of the staff member's question. Furthermore, the response unit can quickly provide an answer to a question similar to a past question based on the staff member's question history. The optimization unit records any unclear points or questions that arise during work and aggregates the information to improve the manual. For example, the optimization unit can analyze the frequency and content of questions and automatically provide more detailed explanations for specific procedures. The optimization unit can also periodically update the content of the manual based on the aggregated information. Furthermore, the optimization unit can reflect staff feedback to identify areas for improvement in the manual and perform optimization. As a result, the work support system according to the embodiment adjusts audio playback to match the staff's work speed, instantly resolves any unclear points, and optimizes the manual, thereby improving work efficiency.

[0030] The adjustment unit can detect the working speed of the staff member using a sensor. Examples of sensors include, but are not limited to, an acceleration sensor, a gyro sensor, and a position sensor. The adjustment unit can detect the movement of the staff member using, for example, an acceleration sensor, and calculate the working speed. The adjustment unit can also detect the posture and movement of the staff member using a gyro sensor and calculate the working speed. The adjustment unit can also obtain position information of the staff member using a position sensor and calculate the working speed. In this way, the use of sensors can accurately detect the working speed of the staff member. Some or all of the above-mentioned processing in the adjustment unit can be performed using, for example, AI, or can be performed without using AI. For example, the adjustment unit can input data obtained from the sensor into the generation AI and cause the generation AI to detect the working speed.

[0031] The playback unit can adjust the audio playback to match the staff member's work speed. The playback unit, for example, changes the speed of the audio playback according to the staff member's work speed. For example, the playback unit can increase the audio playback speed if the staff member's work speed is fast. The playback unit can also slow down the audio playback speed if the staff member's work speed is slow. The playback unit can also adjust the content of the audio playback according to the staff member's work progress. For example, the playback unit can add instructions for the next step according to the staff member's work progress. The playback unit can also adjust the volume of the audio playback according to the staff member's work environment. For example, the playback unit can increase the volume of the audio playback if the work environment is noisy. The playback unit can also decrease the volume of the audio playback if the work environment is quiet. This improves work efficiency by adjusting the audio playback to match the staff member's work speed. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input staff member's work speed data to the generation AI and cause the generation AI to adjust the audio playback.

[0032] The answering unit can instantly provide an answer from a pre-registered answer database. The answer database may include, but is not limited to, past questions and their answers, the contents of a manual, and answers based on specialized knowledge. For example, the answering unit may analyze the content of the staff member's question using voice recognition technology and search the database for the most appropriate answer. The answering unit may also quickly provide an answer to a question similar to a past question based on the staff member's question history. The answering unit may also present multiple answers depending on the content of the staff member's question, allowing the staff member to select one. This allows the staff member's question to be instantly answered by using a pre-registered answer database. Some or all of the above-described processing in the answering unit may be performed using, for example, AI, or may be performed without AI. For example, the answering unit may input the staff member's question data into a generation AI and have the generation AI search for and provide the most appropriate answer.

[0033] The optimization unit can analyze the frequency and content of questions and automatically provide detailed explanations for specific procedures. For example, the optimization unit can add detailed explanations for procedures for which questions are frequently asked. For example, if questions frequently arise in a specific procedure, the optimization unit can provide detailed explanations for that procedure. The optimization unit can also analyze the content of questions, identify common problems, and perform optimization. For example, the optimization unit can analyze the content of questions, identify common problems in a specific procedure, and add explanations for those problems. The optimization unit can also periodically update the content of the manual based on the frequency and content of questions. For example, the optimization unit can periodically review the content of the manual based on the frequency and content of questions to reflect the latest information. By analyzing the frequency and content of questions, the optimization unit can automatically provide detailed explanations for specific procedures and improve the accuracy of the manual. Some or all of the above-described processing in the optimization unit may be performed using, for example, AI, or may be performed without AI. For example, the optimization unit can input question data into a generation AI and cause the generation AI to optimize the manual.

[0034] The adjustment unit can analyze the staff member's past work history and select the optimal work speed detection method. For example, the adjustment unit analyzes the staff member's past work history and selects a detection method that avoids a speed range in which mistakes frequently occur. For example, the adjustment unit analyzes the staff member's past work history, identifies a speed range in which mistakes are common, and selects a detection method that avoids that range. The adjustment unit can also identify a speed range in which work can be performed most efficiently from the staff member's past work history and detect within that range. For example, the adjustment unit analyzes the staff member's past work history, identifies an efficient speed range, and detects within that range. The adjustment unit can also select the optimal speed detection method for a specific task based on the staff member's past work history. For example, the adjustment unit selects the optimal speed detection method for a specific task based on the staff member's past work history. In this way, the optimal work speed detection method can be selected by analyzing the staff member's past work history. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input past work history data into the generation AI and have the generation AI select the optimal work speed detection method.

[0035] The adjustment unit can adjust the detection accuracy when detecting the work speed, taking into account the staff member's current physical condition and fatigue level. The adjustment unit, for example, acquires the staff member's physical condition data and reduces the detection accuracy if the staff member is in poor physical condition. For example, the adjustment unit acquires physical condition data such as the staff member's heart rate and blood pressure and reduces the detection accuracy if the staff member is in poor physical condition. The adjustment unit can also detect the staff member's fatigue level using a sensor and adjust the detection accuracy if fatigue is accumulating. For example, the adjustment unit acquires data such as the staff member's electrodermal activity and electromyogram and adjusts the detection accuracy if fatigue is accumulating. The adjustment unit can also periodically monitor the staff member's physical condition and fatigue level and adjust the detection accuracy in real time. For example, the adjustment unit periodically monitors the staff member's physical condition and fatigue level and adjusts the detection accuracy in real time. This enables more appropriate work speed detection by taking into account the staff member's physical condition and fatigue level. Some or all of the above-described processing by the adjustment unit may be performed, for example, using AI or without AI. For example, the adjustment unit can input physical condition and fatigue level data into the generation AI and have the generation AI adjust the detection accuracy.

[0036] When detecting the work speed, the adjustment unit can optimize the detection method based on the work environment of the staff member. For example, the adjustment unit detects the temperature of the work environment with a sensor and prioritizes the work speed within an appropriate temperature range. For example, the adjustment unit detects the temperature of the work environment with a sensor and prioritizes the work speed within an appropriate temperature range. The adjustment unit can also monitor the humidity of the work environment and adjust the detection accuracy when the humidity is high. For example, the adjustment unit can monitor the humidity of the work environment and adjust the detection accuracy when the humidity is high. The adjustment unit can also select the optimal detection method by taking into account the lighting conditions of the work environment. For example, the adjustment unit selects the optimal detection method by taking into account the lighting conditions of the work environment. This makes it possible to detect the optimal work speed by taking the work environment into consideration. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input work environment data to the generation AI and cause the generation AI to optimize the detection method.

[0037] When detecting the work speed, the adjustment unit can select the optimal detection method by taking into account the geographical location information of the staff member. For example, if the staff member is indoors, the adjustment unit selects an indoor detection method. For example, the adjustment unit acquires the geographical location information of the staff member, and selects an indoor detection method when the staff member is indoors. The adjustment unit can also select an outdoor detection method when the staff member is outdoors. For example, the adjustment unit acquires the geographical location information of the staff member, and selects an outdoor detection method when the staff member is outdoors. The adjustment unit can also select the optimal detection method in real time based on the geographical location information of the staff member. For example, the adjustment unit selects the optimal detection method in real time based on the geographical location information of the staff member. This makes it possible to detect the optimal work speed by taking the geographical location information into account. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input geographical location information data to the generation AI and cause the generation AI to select a detection method.

[0038] The adjustment unit can analyze the social media activities of the staff member and acquire related data when detecting the work speed. The adjustment unit, for example, estimates the current mood and physical condition from the staff member's social media activities and adjusts the detection method. For example, the adjustment unit analyzes the content of the staff member's social media posts to estimate the current mood and physical condition and adjusts the detection method. The adjustment unit can also analyze the content of the staff member's social media posts and reflect the results in detecting the work speed. For example, the adjustment unit analyzes the content of the staff member's social media posts and reflect the results in detecting the work speed. The adjustment unit can also adjust the detection method by referring to the activities of the staff member's friends on social media. For example, the adjustment unit adjusts the detection method by referring to the activities of the staff member's friends on social media. In this way, by analyzing social media activities, related data can be acquired and reflected in detecting the work speed. Some or all of the above-mentioned processing in the adjustment unit can be performed, for example, using AI or without AI. For example, the adjustment unit can input social media data into the generation AI and cause the generation AI to acquire related data and adjust the detection method.

[0039] When detecting the work speed, the adjustment unit can customize the detection method by reflecting past feedback from the staff. For example, the adjustment unit analyzes past feedback from the staff and selects the optimal detection method. For example, the adjustment unit analyzes past feedback from the staff and selects the optimal detection method. The adjustment unit can also customize the detection method based on staff feedback. For example, the adjustment unit customizes the detection method based on staff feedback. The adjustment unit can also adjust the detection method by reflecting past feedback from the staff in real time. For example, the adjustment unit adjusts the detection method by reflecting past feedback from the staff in real time. In this way, the optimal detection method can be customized by reflecting past feedback. Some or all of the above-mentioned processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI. For example, the adjustment unit can input past feedback data into the generation AI and cause the generation AI to customize the detection method.

[0040] The playback unit can adjust the level of detail of the playback content based on the importance of the task when playing back audio. For example, the playback unit plays back audio including a detailed description for an important task. For example, the playback unit evaluates the importance of the task and plays back audio including a detailed description for an important task. The playback unit can also play back audio including a concise description for a low-importance task. For example, the playback unit evaluates the importance of the task and plays back audio including a concise description for a low-importance task. The playback unit can also adjust the level of detail of the playback content in real time according to the importance of the task. For example, the playback unit evaluates the importance of the task in real time and adjusts the level of detail of the playback content. By adjusting the level of detail of the playback content based on the importance of the task, audio playback with more appropriate content can be performed. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input task importance data to a generation AI and cause the generation AI to adjust the level of detail of the playback content.

[0041] The playback unit can apply different audio playback algorithms depending on the task category when playing back audio. For example, in the case of technical tasks, the playback unit applies an audio playback algorithm including technical terms. For example, the playback unit evaluates the task category and applies an audio playback algorithm including technical terms for technical tasks. The playback unit can also apply an audio playback algorithm including a concise explanation for clerical tasks. For example, the playback unit evaluates the task category and applies an audio playback algorithm including a concise explanation for clerical tasks. The playback unit can also apply an optimal audio playback algorithm in real time depending on the task category. For example, the playback unit evaluates the task category in real time and applies an optimal audio playback algorithm. This allows for more effective audio playback by applying the optimal audio playback algorithm depending on the task category. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input task category data to a generation AI and cause the generation AI to apply an audio playback algorithm.

[0042] The playback unit can improve playback accuracy by referring to the staff member's past playback history when playing back audio. For example, the playback unit analyzes the staff member's past playback history and selects the optimal playback method. For example, the playback unit analyzes the staff member's past playback history and selects the optimal playback method. The playback unit can also prioritize playback of frequently played content based on the staff member's past playback history. For example, the playback unit analyzes the staff member's past playback history and prioritizes playback of frequently played content. The playback unit can also improve playback accuracy in real time based on the staff member's past playback history. For example, the playback unit analyzes the staff member's past playback history in real time and improves playback accuracy. By referring to the past playback history, playback accuracy is improved. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input past playback history data into a generation AI and cause the generation AI to improve playback accuracy.

[0043] The playback unit can determine playback priorities based on the submission dates of tasks when playing back audio. For example, the playback unit prioritizes playback of tasks with an approaching deadline. For example, the playback unit evaluates the submission dates of tasks and prioritizes playback of tasks with an approaching deadline. The playback unit can also postpone playback of tasks with a distant submission date. For example, the playback unit evaluates the submission dates of tasks and postpones playback of tasks with a distant submission date. The playback unit can also determine playback priorities in real time based on the submission dates of tasks. For example, the playback unit evaluates the submission dates of tasks in real time and determines playback priorities. This enables more efficient audio playback by determining playback priorities based on the submission dates of tasks. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without AI. For example, the playback unit can input task submission date data to a generation AI and have the generation AI determine playback priorities.

[0044] The playback unit can adjust the playback order based on the relevance of tasks when playing back audio. The playback unit, for example, prioritizes playback of highly relevant tasks. For example, the playback unit evaluates the relevance of tasks and prioritizes playback of highly relevant tasks. The playback unit can also postpone playback of less relevant tasks. For example, the playback unit evaluates the relevance of tasks and postpones playback of less relevant tasks. The playback unit can also adjust the playback order in real time according to the relevance of tasks. For example, the playback unit evaluates the relevance of tasks in real time and adjusts the playback order. In this way, more effective audio playback can be achieved by adjusting the playback order based on the relevance of tasks. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input task relevance data to a generation AI and cause the generation AI to adjust the playback order.

[0045] The playback unit can adjust the use of technical terms in the playback content during audio playback according to the staff member's level of expertise. For example, the playback unit provides playback content that uses a lot of technical terms to staff members with high expertise. For example, the playback unit evaluates the staff member's level of expertise and provides playback content that uses a lot of technical terms to staff members with high expertise. The playback unit can also provide playback content that explains things in simpler terms to staff members with low expertise. For example, the playback unit evaluates the staff member's level of expertise and provides playback content that explains things in simpler terms to staff members with low expertise. The playback unit can also adjust the use of technical terms in the playback content in real time according to the staff member's level of expertise. For example, the playback unit evaluates the staff member's level of expertise in real time and adjusts the use of technical terms in the playback content. By adjusting the use of technical terms in the playback content according to the staff member's level of expertise, audio playback with more appropriate content can be performed. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or without AI. For example, the playback unit can input staff member's level of expertise data into a generation AI and cause the generation AI to control the use of technical terms in the playback content.

[0046] When providing an answer, the answering unit can adjust the level of detail of the answer based on the importance of the question. For example, the answering unit provides a detailed answer to an important question. For example, the answering unit evaluates the importance of a question and provides a detailed answer to an important question. The answering unit can also provide a concise answer to a question of low importance. For example, the answering unit evaluates the importance of a question and provides a concise answer to a question of low importance. The answering unit can also adjust the level of detail of the answer in real time according to the importance of the question. For example, the answering unit evaluates the importance of a question in real time and adjusts the level of detail of the answer. In this way, by adjusting the level of detail of the answer based on the importance of the question, a more appropriate answer can be provided. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input question importance data to a generating AI and cause the generating AI to adjust the level of detail of the answer.

[0047] When providing an answer, the answering unit can apply different answering algorithms depending on the category of the question. For example, the answering unit applies a specialized answering algorithm to technical questions. For example, the answering unit evaluates the category of the question and applies a specialized answering algorithm to technical questions. The answering unit can also apply a concise answering algorithm to administrative questions. For example, the answering unit evaluates the category of the question and applies a concise answering algorithm to administrative questions. The answering unit can also apply an optimal answering algorithm in real time depending on the category of the question. For example, the answering unit evaluates the category of the question in real time and applies an optimal answering algorithm. In this way, a more appropriate answer can be provided by applying the optimal answering algorithm depending on the category of the question. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input question category data to a generation AI and have the generation AI apply an answering algorithm.

[0048] When providing an answer, the answering unit can improve the accuracy of the answer by referring to the staff member's past question history. The answering unit, for example, analyzes the staff member's past question history and provides the optimal answer. For example, the answering unit analyzes the staff member's past question history and provides the optimal answer. The answering unit can also prioritize answers to frequently asked questions from the staff member's past question history. For example, the answering unit analyzes the staff member's past question history and prioritizes answers to frequently asked questions. The answering unit can also improve the accuracy of the answer in real time based on the staff member's past question history. For example, the answering unit analyzes the staff member's past question history in real time and improves the accuracy of the answer. As a result, the accuracy of the answer is improved by referring to the past question history. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input past question history data into a generation AI and cause the generation AI to improve the accuracy of the answer.

[0049] When providing answers, the answering unit can determine the priority of answers based on the time when the question was submitted. For example, the answering unit prioritizes providing answers to urgent questions. For example, the answering unit evaluates the time when the question was submitted and prioritizes providing answers to urgent questions. The answering unit can also postpone providing answers to questions that are submitted further in the future. For example, the answering unit evaluates the time when the question was submitted and postpones providing answers to questions that are submitted further in the future. The answering unit can also determine the priority of answers in real time depending on the time when the question was submitted. For example, the answering unit evaluates the time when the question was submitted in real time and determines the priority of answers. In this way, by determining the priority of answers based on the time when the question was submitted, more efficient answers are provided. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input question submission time data to a generation AI and have the generation AI determine the priority of answers.

[0050] When providing an answer, the answering unit can adjust the order of answers based on the relevance of the question. For example, the answering unit prioritizes answers to highly relevant questions. For example, the answering unit evaluates the relevance of questions and prioritizes answers to highly relevant questions. The answering unit can also postpone answers to less relevant questions. For example, the answering unit evaluates the relevance of questions and postpones answers to less relevant questions. The answering unit can also adjust the order of answers in real time according to the relevance of questions. For example, the answering unit evaluates the relevance of questions in real time and adjusts the order of answers. In this way, by adjusting the order of answers based on the relevance of questions, a more appropriate answer is provided. Some or all of the above-described processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input question relevance data to a generation AI and cause the generation AI to adjust the order of answers.

[0051] When providing an answer, the answering unit can adjust the use of technical terms in the answer content according to the staff member's level of expertise. For example, the answering unit provides an answer that uses a lot of technical terms to staff members with high expertise. For example, the answering unit evaluates the staff member's level of expertise and provides an answer that uses a lot of technical terms to staff members with high expertise. The answering unit can also provide an answer that explains in simpler terms to staff members with low expertise. For example, the answering unit evaluates the staff member's level of expertise and provides an answer that explains in simpler terms to staff members with low expertise. The answering unit can also adjust the use of technical terms in the answer content in real time according to the staff member's level of expertise. For example, the answering unit evaluates the staff member's level of expertise in real time and adjusts the use of technical terms in the answer content. In this way, by adjusting the use of technical terms in the answer content according to the staff member's level of expertise, a more appropriate answer is provided. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without AI. For example, the answering unit can input staff member's expertise level data into a generation AI and have the generation AI execute the use of technical terms in the answer content.

[0052] During optimization, the optimization unit can optimize the optimization algorithm by referring to past optimization data. The optimization unit, for example, analyzes past optimization data and selects the most effective optimization algorithm. For example, the optimization unit analyzes past optimization data and selects the most effective optimization algorithm. The optimization unit can also identify frequently occurring problems from the past optimization data and adjust the optimization algorithm. For example, the optimization unit analyzes past optimization data, identifies frequently occurring problems, and adjusts the optimization algorithm. The optimization unit can also improve the optimization algorithm in real time based on the past optimization data. For example, the optimization unit analyzes past optimization data in real time and improves the optimization algorithm. In this way, the accuracy of the optimization algorithm is improved by referring to the past optimization data. Some or all of the above-mentioned processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input past optimization data to a generation AI and cause the generation AI to improve the optimization algorithm.

[0053] During optimization, the optimization unit can select the optimal optimization method by analyzing the frequency and content of questions. For example, the optimization unit adds detailed explanations to steps that are frequently asked about. For example, the optimization unit adds detailed explanations to steps that are frequently asked about. The optimization unit can also analyze the content of questions, identify common problems, and optimize them. For example, the optimization unit analyzes the content of questions, identify common problems, and optimize them. The optimization unit can also select the optimal optimization method in real time depending on the frequency and content of questions. For example, the optimization unit analyzes the frequency and content of questions in real time and selects the optimal optimization method. In this way, the optimal optimization method can be selected by analyzing the frequency and content of questions. Some or all of the above-mentioned processing in the optimization unit may be performed using, or without, AI. For example, the optimization unit can input question frequency and content data to the generation AI and cause the generation AI to select an optimization method.

[0054] The optimization unit can improve the optimization method by reflecting staff feedback during optimization. The optimization unit, for example, analyzes staff feedback and improves the optimization method. For example, the optimization unit analyzes staff feedback and improves the optimization method. The optimization unit can also adjust the optimization algorithm based on staff feedback. For example, the optimization unit adjusts the optimization algorithm based on staff feedback. The optimization unit can also reflect staff feedback in real time and improve the optimization method. For example, the optimization unit reflects staff feedback in real time and improves the optimization method. In this way, the optimization method is improved by reflecting staff feedback. Some or all of the above-mentioned processing in the optimization unit may be performed using AI, for example, or may be performed without using AI. For example, the optimization unit can input staff feedback data into the generation AI and cause the generation AI to improve the optimization method.

[0055] During optimization, the optimization unit can select the optimal optimization method by taking into account the geographic distribution of questions. For example, the optimization unit selects a region-specific optimization method for a region with a large number of questions. For example, the optimization unit evaluates the geographic distribution of questions and selects a region-specific optimization method for a region with a large number of questions. The optimization unit can also select a general optimization method for a region with a small number of questions. For example, the optimization unit evaluates the geographic distribution of questions and selects a general optimization method for a region with a small number of questions. The optimization unit can also select the optimal optimization method in real time based on the geographic distribution of questions. For example, the optimization unit evaluates the geographic distribution of questions in real time and selects the optimal optimization method. In this way, the optimal optimization method can be selected by taking the geographic distribution of questions into consideration. Some or all of the above-described processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input geographic distribution data of questions to the generation AI and cause the generation AI to select an optimization method.

[0056] The optimization unit can improve the accuracy of optimization by referring to literature related to the question during optimization. For example, the optimization unit improves the accuracy of optimization by referring to literature related to the question. For example, the optimization unit improves the accuracy of optimization by referring to literature related to the question. The optimization unit can also adjust the optimization method based on the related literature according to the content of the question. For example, the optimization unit adjusts the optimization method based on the related literature according to the content of the question. The optimization unit can also improve the accuracy of optimization by referring to literature related to the question in real time. For example, the optimization unit improves the accuracy of optimization by referring to literature related to the question in real time. As a result, the accuracy of optimization is improved by referring to literature related to the question. Some or all of the above-mentioned processing in the optimization unit may be performed using AI, for example, or may be performed without using AI. For example, the optimization unit can input literature data related to the question to the generation AI and cause the generation AI to adjust the optimization method.

[0057] The optimization unit can perform optimization taking into account the market value of the question during optimization. For example, the optimization unit performs detailed optimization for questions with high market value. For example, the optimization unit evaluates the market value of the question and performs detailed optimization for the question with high market value. The optimization unit can also perform simple optimization for questions with low market value. For example, the optimization unit evaluates the market value of the question and performs simple optimization for the question with low market value. The optimization unit can also adjust the optimization method in real time according to the market value of the question. For example, the optimization unit evaluates the market value of the question in real time and adjusts the optimization method. In this way, more effective optimization can be performed by taking the market value of the question into consideration. Some or all of the above-mentioned processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input market value data of the question to the generation AI and cause the generation AI to adjust the optimization method.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The adjustment unit not only detects the work speed of staff members, but also learns their work patterns and predicts the optimal work speed. For example, the adjustment unit analyzes the staff members' past work data and predicts fluctuations in work speed during specific times of the day or day of the week. The adjustment unit can also suggest the optimal work speed before the work begins, based on the staff members' work patterns. Furthermore, the adjustment unit can learn the staff members' work patterns and adapt to new work. In this way, by learning the staff members' work patterns, it becomes possible to detect and predict work speeds more efficiently.

[0060] The answering section can provide relevant videos and images depending on the staff member's question. For example, if a staff member asks about a specific procedure, the answering section can provide a video showing that procedure. Alternatively, if a staff member asks about how to operate a device, the answering section can provide an image showing how to operate that device. Furthermore, if a staff member asks about a complex concept, the answering section can provide an infographic that visually explains the concept. This can deepen the staff member's understanding by providing visual information.

[0061] The adjustment unit not only detects the working speed of the staff member, but also monitors the working environment of the staff member and adjusts the accuracy of detecting the working speed according to the environment. For example, the adjustment unit may use a sensor to detect the temperature and humidity of the working environment and prioritize the working speed under appropriate environmental conditions. The adjustment unit may also monitor the lighting conditions of the working environment and prioritize the working speed under optimal lighting conditions. Furthermore, the adjustment unit may monitor the noise level of the working environment and prioritize the working speed in a quiet environment. This allows for more accurate detection of the working speed by taking the working environment into consideration.

[0062] The answering section can provide links to relevant external resources depending on the content of the staff member's question. For example, if the staff member asks about a specific technology, the answering section can provide a link to an external specialist site on that technology. Also, if the staff member asks about a specific product, the answering section can provide a link to the official website of that product. Furthermore, if the staff member wants to learn more about a specific topic, the answering section can provide a link to an online course or webinar on that topic. This allows staff members to expand their knowledge by utilizing external resources.

[0063] The adjustment unit not only detects the work speed of the staff member, but also monitors the health condition of the staff member and adjusts the detection accuracy of the work speed according to the health condition. For example, the adjustment unit detects the heart rate and blood pressure of the staff member using a sensor, and increases the detection accuracy when the health condition is good. The adjustment unit can also relax the detection accuracy when the health condition of the staff member is poor. Furthermore, the adjustment unit can periodically monitor the health condition of the staff member and adjust the detection accuracy in real time. This makes it possible to detect a more appropriate work speed by taking the health condition of the staff member into consideration.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The adjustment unit detects the working speed of the staff. For example, it uses a sensor to monitor the working speed of the staff in real time and adjusts the detection accuracy according to changes in the working speed. Step 2: The playback unit adjusts the audio playback based on the work speed detected by the adjustment unit. For example, the playback unit changes the audio playback speed to match the work speed of the staff member, and adjusts the content and volume of the audio playback according to the progress of the work. Step 3: The answering department analyzes the staff member's question using voice recognition technology and provides an immediate answer. For example, it selects the most appropriate answer from a pre-registered answer database and provides a quick answer based on past question history. Step 4: The optimization section records any questions or concerns that arise during the work, consolidates the information, and improves the manual. For example, it analyzes the frequency and content of questions, automatically refines explanations of specific procedures, and periodically updates the manual based on the consolidated information.

[0066] (Example 2) A system according to an embodiment of the present invention plays back information from a manual aloud in accordance with the staff's work speed, allowing them to resolve any questions as they arise. When a staff member begins work, the system plays back information from the manual aloud. The audio playback is adjusted to match the staff member's work speed. When a staff member encounters a question, they ask it immediately, and the system provides an immediate answer. This allows the staff member to resolve the question without interrupting their work. Furthermore, the system records any questions or questions that arise during work and aggregates the information. Based on the aggregated information, points that may lead to errors are identified and the manual is automatically optimized. For example, if questions frequently arise about a particular procedure, the explanation for that procedure is detailed. In this way, the manual is always kept up to date, improving staff work efficiency. This allows the system to improve staff work efficiency and reduce the occurrence of errors. Furthermore, automatically optimizing the manual ensures that the latest information is always provided, contributing to the improvement of staff skills.

[0067] The work assistance system according to the embodiment includes an adjustment unit, a playback unit, a response unit, and an optimization unit. The adjustment unit detects the work speed of the staff member. For example, the adjustment unit can detect the work speed of the staff member using a sensor. The adjustment unit can also monitor the work speed of the staff member in real time and adjust the detection accuracy according to changes in the work speed. The playback unit adjusts audio playback based on the work speed detected by the adjustment unit. For example, the playback unit can change the speed of the audio playback to match the work speed of the staff member. The playback unit can also adjust the content of the audio playback according to the work progress of the staff member. Furthermore, the playback unit can adjust the volume of the audio playback according to the work environment of the staff member. The response unit analyzes the staff member's question using voice recognition technology and provides an answer immediately. For example, the response unit can provide an answer immediately from a pre-registered answer database. The response unit can also select and provide an optimal answer according to the content of the staff member's question. Furthermore, the response unit can quickly provide an answer to a question similar to a past question based on the staff member's question history. The optimization unit records any unclear points or questions that arise during work and aggregates the information to improve the manual. For example, the optimization unit can analyze the frequency and content of questions and automatically provide more detailed explanations for specific procedures. The optimization unit can also periodically update the content of the manual based on the aggregated information. Furthermore, the optimization unit can reflect staff feedback to identify areas for improvement in the manual and perform optimization. As a result, the work support system according to the embodiment adjusts audio playback to match the staff's work speed, instantly resolves any unclear points, and optimizes the manual, thereby improving work efficiency.

[0068] The adjustment unit can detect the working speed of the staff member using a sensor. Examples of sensors include, but are not limited to, an acceleration sensor, a gyro sensor, and a position sensor. The adjustment unit can detect the movement of the staff member using, for example, an acceleration sensor, and calculate the working speed. The adjustment unit can also detect the posture and movement of the staff member using a gyro sensor and calculate the working speed. The adjustment unit can also obtain position information of the staff member using a position sensor and calculate the working speed. In this way, the use of sensors can accurately detect the working speed of the staff member. Some or all of the above-mentioned processing in the adjustment unit can be performed using, for example, AI, or can be performed without using AI. For example, the adjustment unit can input data obtained from the sensor into the generation AI and cause the generation AI to detect the working speed.

[0069] The playback unit can adjust the audio playback to match the staff member's work speed. The playback unit, for example, changes the speed of the audio playback according to the staff member's work speed. For example, the playback unit can increase the audio playback speed if the staff member's work speed is fast. The playback unit can also slow down the audio playback speed if the staff member's work speed is slow. The playback unit can also adjust the content of the audio playback according to the staff member's work progress. For example, the playback unit can add instructions for the next step according to the staff member's work progress. The playback unit can also adjust the volume of the audio playback according to the staff member's work environment. For example, the playback unit can increase the volume of the audio playback if the work environment is noisy. The playback unit can also decrease the volume of the audio playback if the work environment is quiet. This improves work efficiency by adjusting the audio playback to match the staff member's work speed. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input staff member's work speed data to the generation AI and cause the generation AI to adjust the audio playback.

[0070] The answering unit can instantly provide an answer from a pre-registered answer database. The answer database may include, but is not limited to, past questions and their answers, the contents of a manual, and answers based on specialized knowledge. For example, the answering unit may analyze the content of the staff member's question using voice recognition technology and search the database for the most appropriate answer. The answering unit may also quickly provide an answer to a question similar to a past question based on the staff member's question history. The answering unit may also present multiple answers depending on the content of the staff member's question, allowing the staff member to select one. This allows the staff member's question to be instantly answered by using a pre-registered answer database. Some or all of the above-described processing in the answering unit may be performed using, for example, AI, or may be performed without AI. For example, the answering unit may input the staff member's question data into a generation AI and have the generation AI search for and provide the most appropriate answer.

[0071] The optimization unit can analyze the frequency and content of questions and automatically provide detailed explanations for specific procedures. For example, the optimization unit can add detailed explanations for procedures for which questions are frequently asked. For example, if questions frequently arise in a specific procedure, the optimization unit can provide detailed explanations for that procedure. The optimization unit can also analyze the content of questions, identify common problems, and perform optimization. For example, the optimization unit can analyze the content of questions, identify common problems in a specific procedure, and add explanations for those problems. The optimization unit can also periodically update the content of the manual based on the frequency and content of questions. For example, the optimization unit can periodically review the content of the manual based on the frequency and content of questions to reflect the latest information. By analyzing the frequency and content of questions, the optimization unit can automatically provide detailed explanations for specific procedures and improve the accuracy of the manual. Some or all of the above-described processing in the optimization unit may be performed using, for example, AI, or may be performed without AI. For example, the optimization unit can input question data into a generation AI and cause the generation AI to optimize the manual.

[0072] The adjustment unit can estimate the staff member's emotions and adjust the detection accuracy of the work speed based on the estimated staff member's emotions. For example, the adjustment unit captures the staff member's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the adjustment unit calculates an emotion score based on changes in facial expressions and adjusts the detection accuracy of the work speed. The adjustment unit can also record the staff member's voice and estimate the emotions using voice analysis technology. For example, the adjustment unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the detection accuracy of the work speed. The adjustment unit can also collect the staff member's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the adjustment unit calculates an emotion score based on fluctuations in heart rate and adjusts the detection accuracy of the work speed. This allows for more accurate detection of the work speed by adjusting the detection accuracy of the work speed based on the staff member's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the adjustment unit may be performed using AI, or may be performed without using AI. For example, the adjustment unit may input image data of a staff member taken with a camera into the generation AI and cause the generation AI to estimate emotions.

[0073] The adjustment unit can analyze the staff member's past work history and select the optimal work speed detection method. For example, the adjustment unit analyzes the staff member's past work history and selects a detection method that avoids a speed range in which mistakes frequently occur. For example, the adjustment unit analyzes the staff member's past work history, identifies a speed range in which mistakes are common, and selects a detection method that avoids that range. The adjustment unit can also identify a speed range in which work can be performed most efficiently from the staff member's past work history and detect within that range. For example, the adjustment unit analyzes the staff member's past work history, identifies an efficient speed range, and detects within that range. The adjustment unit can also select the optimal speed detection method for a specific task based on the staff member's past work history. For example, the adjustment unit selects the optimal speed detection method for a specific task based on the staff member's past work history. In this way, the optimal work speed detection method can be selected by analyzing the staff member's past work history. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input past work history data into the generation AI and have the generation AI select the optimal work speed detection method.

[0074] The adjustment unit can adjust the detection accuracy when detecting the work speed, taking into account the staff member's current physical condition and fatigue level. The adjustment unit, for example, acquires the staff member's physical condition data and reduces the detection accuracy if the staff member is in poor physical condition. For example, the adjustment unit acquires physical condition data such as the staff member's heart rate and blood pressure and reduces the detection accuracy if the staff member is in poor physical condition. The adjustment unit can also detect the staff member's fatigue level using a sensor and adjust the detection accuracy if fatigue is accumulating. For example, the adjustment unit acquires data such as the staff member's electrodermal activity and electromyogram and adjusts the detection accuracy if fatigue is accumulating. The adjustment unit can also periodically monitor the staff member's physical condition and fatigue level and adjust the detection accuracy in real time. For example, the adjustment unit periodically monitors the staff member's physical condition and fatigue level and adjusts the detection accuracy in real time. This enables more appropriate work speed detection by taking into account the staff member's physical condition and fatigue level. Some or all of the above-described processing by the adjustment unit may be performed, for example, using AI or without AI. For example, the adjustment unit can input physical condition and fatigue level data into the generation AI and have the generation AI adjust the detection accuracy.

[0075] When detecting the work speed, the adjustment unit can optimize the detection method based on the work environment of the staff member. For example, the adjustment unit detects the temperature of the work environment with a sensor and prioritizes the work speed within an appropriate temperature range. For example, the adjustment unit detects the temperature of the work environment with a sensor and prioritizes the work speed within an appropriate temperature range. The adjustment unit can also monitor the humidity of the work environment and adjust the detection accuracy when the humidity is high. For example, the adjustment unit can monitor the humidity of the work environment and adjust the detection accuracy when the humidity is high. The adjustment unit can also select the optimal detection method by taking into account the lighting conditions of the work environment. For example, the adjustment unit selects the optimal detection method by taking into account the lighting conditions of the work environment. This makes it possible to detect the optimal work speed by taking the work environment into consideration. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input work environment data to the generation AI and cause the generation AI to optimize the detection method.

[0076] The adjustment unit can estimate the staff member's emotions and adjust the timing of detecting the work speed based on the estimated staff member's emotions. For example, if the staff member is nervous, the adjustment unit uses an emotion engine to estimate the emotions and delay the detection timing. For example, the adjustment unit captures the staff member's facial expressions with a camera, estimates the emotions using an emotion estimation algorithm, and delays the detection timing if the staff member is nervous. The adjustment unit can also estimate the staff member's relaxed state using the emotion engine and advance the detection timing. For example, the adjustment unit records the staff member's voice, estimates the emotions using voice analysis technology, and advances the detection timing if the staff member is relaxed. The adjustment unit can also estimate the staff member's fatigue using the emotion engine and appropriately adjust the detection timing. For example, the adjustment unit collects the staff member's biometric data (heart rate and electrodermal activity) with a sensor, estimates the emotions using an emotion estimation algorithm, and appropriately adjusts the detection timing if the staff member is tired. In this way, by adjusting the detection timing of the work speed based on the staff member's emotions, the work speed can be detected at a more appropriate time. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI. For example, the adjustment unit may input image data of a staff member taken with a camera into the generation AI and cause the generation AI to estimate emotions.

[0077] When detecting the work speed, the adjustment unit can select the optimal detection method by taking into account the geographical location information of the staff member. For example, if the staff member is indoors, the adjustment unit selects an indoor detection method. For example, the adjustment unit acquires the geographical location information of the staff member, and selects an indoor detection method when the staff member is indoors. The adjustment unit can also select an outdoor detection method when the staff member is outdoors. For example, the adjustment unit acquires the geographical location information of the staff member, and selects an outdoor detection method when the staff member is outdoors. The adjustment unit can also select the optimal detection method in real time based on the geographical location information of the staff member. For example, the adjustment unit selects the optimal detection method in real time based on the geographical location information of the staff member. This makes it possible to detect the optimal work speed by taking the geographical location information into account. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input geographical location information data to the generation AI and cause the generation AI to select a detection method.

[0078] The adjustment unit can analyze the social media activities of the staff member and acquire related data when detecting the work speed. The adjustment unit, for example, estimates the current mood and physical condition from the staff member's social media activities and adjusts the detection method. For example, the adjustment unit analyzes the content of the staff member's social media posts to estimate the current mood and physical condition and adjusts the detection method. The adjustment unit can also analyze the content of the staff member's social media posts and reflect the results in detecting the work speed. For example, the adjustment unit analyzes the content of the staff member's social media posts and reflect the results in detecting the work speed. The adjustment unit can also adjust the detection method by referring to the activities of the staff member's friends on social media. For example, the adjustment unit adjusts the detection method by referring to the activities of the staff member's friends on social media. In this way, by analyzing social media activities, related data can be acquired and reflected in detecting the work speed. Some or all of the above-mentioned processing in the adjustment unit can be performed, for example, using AI or without AI. For example, the adjustment unit can input social media data into the generation AI and cause the generation AI to acquire related data and adjust the detection method.

[0079] When detecting the work speed, the adjustment unit can customize the detection method by reflecting past feedback from the staff. For example, the adjustment unit analyzes past feedback from the staff and selects the optimal detection method. For example, the adjustment unit analyzes past feedback from the staff and selects the optimal detection method. The adjustment unit can also customize the detection method based on staff feedback. For example, the adjustment unit customizes the detection method based on staff feedback. The adjustment unit can also adjust the detection method by reflecting past feedback from the staff in real time. For example, the adjustment unit adjusts the detection method by reflecting past feedback from the staff in real time. In this way, the optimal detection method can be customized by reflecting past feedback. Some or all of the above-mentioned processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI. For example, the adjustment unit can input past feedback data into the generation AI and cause the generation AI to customize the detection method.

[0080] The playback unit can estimate the staff member's emotions and adjust the audio playback speed based on the estimated staff member's emotions. For example, if the staff member is nervous, the playback unit estimates the emotions using an emotion engine and slows down the audio playback speed. For example, the playback unit captures the staff member's facial expressions with a camera, estimates the emotions using an emotion estimation algorithm, and slows down the audio playback speed if the staff member is nervous. The playback unit can also estimate the emotions using an emotion engine and speed up the audio playback speed if the staff member is relaxed. For example, the playback unit records the staff member's voice, estimates the emotions using voice analysis technology, and speeds up the audio playback speed if the staff member is relaxed. The playback unit can also estimate the tiredness of the staff member using an emotion engine and adjust the audio playback speed appropriately. For example, the playback unit collects the staff member's biometric data (heart rate and electrodermal activity) with a sensor, estimates the emotions using an emotion estimation algorithm, and adjusts the audio playback speed appropriately if the staff member is tired. In this way, by adjusting the audio playback speed based on the staff member's emotions, audio can be played at a more appropriate speed. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the playback unit may be performed using AI, for example, or may be performed without using AI. For example, the playback unit may input image data of a staff member captured by a camera into the generation AI and cause the generation AI to estimate emotions.

[0081] The playback unit can adjust the level of detail of the playback content based on the importance of the task when playing back audio. For example, the playback unit plays back audio including a detailed description for an important task. For example, the playback unit evaluates the importance of the task and plays back audio including a detailed description for an important task. The playback unit can also play back audio including a concise description for a low-importance task. For example, the playback unit evaluates the importance of the task and plays back audio including a concise description for a low-importance task. The playback unit can also adjust the level of detail of the playback content in real time according to the importance of the task. For example, the playback unit evaluates the importance of the task in real time and adjusts the level of detail of the playback content. By adjusting the level of detail of the playback content based on the importance of the task, audio playback with more appropriate content can be performed. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input task importance data to a generation AI and cause the generation AI to adjust the level of detail of the playback content.

[0082] The playback unit can apply different audio playback algorithms depending on the task category when playing back audio. For example, in the case of technical tasks, the playback unit applies an audio playback algorithm including technical terms. For example, the playback unit evaluates the task category and applies an audio playback algorithm including technical terms for technical tasks. The playback unit can also apply an audio playback algorithm including a concise explanation for clerical tasks. For example, the playback unit evaluates the task category and applies an audio playback algorithm including a concise explanation for clerical tasks. The playback unit can also apply an optimal audio playback algorithm in real time depending on the task category. For example, the playback unit evaluates the task category in real time and applies an optimal audio playback algorithm. This allows for more effective audio playback by applying the optimal audio playback algorithm depending on the task category. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input task category data to a generation AI and cause the generation AI to apply an audio playback algorithm.

[0083] The playback unit can improve playback accuracy by referring to the staff member's past playback history when playing back audio. For example, the playback unit analyzes the staff member's past playback history and selects the optimal playback method. For example, the playback unit analyzes the staff member's past playback history and selects the optimal playback method. The playback unit can also prioritize playback of frequently played content based on the staff member's past playback history. For example, the playback unit analyzes the staff member's past playback history and prioritizes playback of frequently played content. The playback unit can also improve playback accuracy in real time based on the staff member's past playback history. For example, the playback unit analyzes the staff member's past playback history in real time and improves playback accuracy. By referring to the past playback history, playback accuracy is improved. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input past playback history data into a generation AI and cause the generation AI to improve playback accuracy.

[0084] The playback unit can estimate the staff member's emotions and adjust the audio playback content based on the estimated staff member's emotions. For example, if the staff member is nervous, the playback unit uses an emotion engine to estimate the emotion and play back content that will relax them. For example, the playback unit captures the staff member's facial expressions with a camera, estimates their emotions using an emotion estimation algorithm, and plays back content that will relax them if they are nervous. The playback unit can also estimate the staff member's relaxed state using an emotion engine and play back content that will encourage them to focus on their work if they are relaxed. For example, the playback unit can record the staff member's voice, estimate their emotions using voice analysis technology, and play back content that will encourage them to focus on their work if they are relaxed. The playback unit can also estimate the staff member's tired state using an emotion engine and play back content that will encourage them. For example, the playback unit collects the staff member's biometric data (heart rate and electrodermal activity) with a sensor, estimates their emotions using an emotion estimation algorithm, and plays back content that will encourage them if they are tired. This allows the audio playback content to be adjusted based on the staff member's emotions, thereby enabling more appropriate audio playback. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the playback unit may be performed using AI, or may be performed without using AI. For example, the playback unit may input image data of a staff member captured by a camera into the generation AI and cause the generation AI to estimate emotions.

[0085] The playback unit can determine playback priorities based on the submission dates of tasks when playing back audio. For example, the playback unit prioritizes playback of tasks with an approaching deadline. For example, the playback unit evaluates the submission dates of tasks and prioritizes playback of tasks with an approaching deadline. The playback unit can also postpone playback of tasks with a distant submission date. For example, the playback unit evaluates the submission dates of tasks and postpones playback of tasks with a distant submission date. The playback unit can also determine playback priorities in real time based on the submission dates of tasks. For example, the playback unit evaluates the submission dates of tasks in real time and determines playback priorities. This enables more efficient audio playback by determining playback priorities based on the submission dates of tasks. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without AI. For example, the playback unit can input task submission date data to a generation AI and have the generation AI determine playback priorities.

[0086] The playback unit can adjust the playback order based on the relevance of tasks when playing back audio. The playback unit, for example, prioritizes playback of highly relevant tasks. For example, the playback unit evaluates the relevance of tasks and prioritizes playback of highly relevant tasks. The playback unit can also postpone playback of less relevant tasks. For example, the playback unit evaluates the relevance of tasks and postpones playback of less relevant tasks. The playback unit can also adjust the playback order in real time according to the relevance of tasks. For example, the playback unit evaluates the relevance of tasks in real time and adjusts the playback order. In this way, more effective audio playback can be achieved by adjusting the playback order based on the relevance of tasks. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or may be performed without using AI. For example, the playback unit can input task relevance data to a generation AI and cause the generation AI to adjust the playback order.

[0087] The playback unit can adjust the use of technical terms in the playback content during audio playback according to the staff member's level of expertise. For example, the playback unit provides playback content that uses a lot of technical terms to staff members with high expertise. For example, the playback unit evaluates the staff member's level of expertise and provides playback content that uses a lot of technical terms to staff members with high expertise. The playback unit can also provide playback content that explains things in simpler terms to staff members with low expertise. For example, the playback unit evaluates the staff member's level of expertise and provides playback content that explains things in simpler terms to staff members with low expertise. The playback unit can also adjust the use of technical terms in the playback content in real time according to the staff member's level of expertise. For example, the playback unit evaluates the staff member's level of expertise in real time and adjusts the use of technical terms in the playback content. By adjusting the use of technical terms in the playback content according to the staff member's level of expertise, audio playback with more appropriate content can be performed. Some or all of the above-described processing in the playback unit may be performed using, for example, AI, or without AI. For example, the playback unit can input staff member's level of expertise data into a generation AI and cause the generation AI to control the use of technical terms in the playback content.

[0088] The answering unit can estimate the staff member's emotions and adjust the way the answer is expressed based on the estimated staff member's emotions. For example, if the staff member is nervous, the answering unit uses an emotion engine to estimate the emotion and respond in a gentler way. For example, the answering unit captures the staff member's facial expression with a camera, estimates the emotion using an emotion estimation algorithm, and responds in a gentler way if the staff member is nervous. The answering unit can also estimate the staff member's relaxed state using an emotion engine and respond in a more detailed way. For example, the answering unit records the staff member's voice, estimates the emotion using voice analysis technology, and responds in a more detailed way if the staff member is relaxed. The answering unit can also estimate the staff member's tired state using an emotion engine and respond in a more concise way if the staff member is tired. For example, the answering unit collects the staff member's biometric data (heart rate and electrodermal activity) using a sensor, estimates the emotion using an emotion estimation algorithm, and responds in a more concise way if the staff member is tired. This allows the answering unit to adjust the way the answer is expressed based on the staff member's emotions, thereby providing a more appropriate answer. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the answering unit may be performed using AI, or may be performed without using AI. For example, the answering unit may input image data of a staff member taken with a camera into the generation AI and have the generation AI estimate their emotions.

[0089] When providing an answer, the answering unit can adjust the level of detail of the answer based on the importance of the question. For example, the answering unit provides a detailed answer to an important question. For example, the answering unit evaluates the importance of a question and provides a detailed answer to an important question. The answering unit can also provide a concise answer to a question of low importance. For example, the answering unit evaluates the importance of a question and provides a concise answer to a question of low importance. The answering unit can also adjust the level of detail of the answer in real time according to the importance of the question. For example, the answering unit evaluates the importance of a question in real time and adjusts the level of detail of the answer. In this way, by adjusting the level of detail of the answer based on the importance of the question, a more appropriate answer can be provided. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input question importance data to a generating AI and cause the generating AI to adjust the level of detail of the answer.

[0090] When providing an answer, the answering unit can apply different answering algorithms depending on the category of the question. For example, the answering unit applies a specialized answering algorithm to technical questions. For example, the answering unit evaluates the category of the question and applies a specialized answering algorithm to technical questions. The answering unit can also apply a concise answering algorithm to administrative questions. For example, the answering unit evaluates the category of the question and applies a concise answering algorithm to administrative questions. The answering unit can also apply an optimal answering algorithm in real time depending on the category of the question. For example, the answering unit evaluates the category of the question in real time and applies an optimal answering algorithm. In this way, a more appropriate answer can be provided by applying the optimal answering algorithm depending on the category of the question. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input question category data to a generation AI and have the generation AI apply an answering algorithm.

[0091] When providing an answer, the answering unit can improve the accuracy of the answer by referring to the staff member's past question history. The answering unit, for example, analyzes the staff member's past question history and provides the optimal answer. For example, the answering unit analyzes the staff member's past question history and provides the optimal answer. The answering unit can also prioritize answers to frequently asked questions from the staff member's past question history. For example, the answering unit analyzes the staff member's past question history and prioritizes answers to frequently asked questions. The answering unit can also improve the accuracy of the answer in real time based on the staff member's past question history. For example, the answering unit analyzes the staff member's past question history in real time and improves the accuracy of the answer. As a result, the accuracy of the answer is improved by referring to the past question history. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input past question history data into a generation AI and cause the generation AI to improve the accuracy of the answer.

[0092] The answering unit can estimate the staff member's emotions and adjust the length of the answer based on the estimated staff member's emotions. For example, if the staff member is nervous, the answering unit uses an emotion engine to estimate the emotion and provide a short answer. For example, the answering unit can capture the staff member's facial expression with a camera, estimate the emotion using an emotion estimation algorithm, and provide a short answer if the staff member is nervous. The answering unit can also estimate the staff member's relaxed state using an emotion engine and provide a long answer. For example, the answering unit can record the staff member's voice, estimate the emotion using voice analysis technology, and provide a long answer if the staff member is relaxed. The answering unit can also estimate the staff member's tired state using an emotion engine and provide a concise answer. For example, the answering unit can collect the staff member's biometric data (heart rate and electrodermal activity) with a sensor, estimate the emotion using an emotion estimation algorithm, and provide a concise answer if the staff member is tired. This allows the length of the answer to be adjusted based on the staff member's emotions, thereby providing a more appropriate answer. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the answering unit may be performed using AI, or may be performed without using AI. For example, the answering unit may input image data of a staff member taken with a camera into the generation AI and have the generation AI estimate their emotions.

[0093] When providing answers, the answering unit can determine the priority of answers based on the time when the question was submitted. For example, the answering unit prioritizes providing answers to urgent questions. For example, the answering unit evaluates the time when the question was submitted and prioritizes providing answers to urgent questions. The answering unit can also postpone providing answers to questions that are submitted further in the future. For example, the answering unit evaluates the time when the question was submitted and postpones providing answers to questions that are submitted further in the future. The answering unit can also determine the priority of answers in real time depending on the time when the question was submitted. For example, the answering unit evaluates the time when the question was submitted in real time and determines the priority of answers. In this way, by determining the priority of answers based on the time when the question was submitted, more efficient answers are provided. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input question submission time data to a generation AI and have the generation AI determine the priority of answers.

[0094] When providing an answer, the answering unit can adjust the order of answers based on the relevance of the question. For example, the answering unit prioritizes answers to highly relevant questions. For example, the answering unit evaluates the relevance of questions and prioritizes answers to highly relevant questions. The answering unit can also postpone answers to less relevant questions. For example, the answering unit evaluates the relevance of questions and postpones answers to less relevant questions. The answering unit can also adjust the order of answers in real time according to the relevance of questions. For example, the answering unit evaluates the relevance of questions in real time and adjusts the order of answers. In this way, by adjusting the order of answers based on the relevance of questions, a more appropriate answer is provided. Some or all of the above-described processing in the answering unit may be performed using, for example, AI, or may be performed without using AI. For example, the answering unit can input question relevance data to a generation AI and cause the generation AI to adjust the order of answers.

[0095] When providing an answer, the answering unit can adjust the use of technical terms in the answer content according to the staff member's level of expertise. For example, the answering unit provides an answer that uses a lot of technical terms to staff members with high expertise. For example, the answering unit evaluates the staff member's level of expertise and provides an answer that uses a lot of technical terms to staff members with high expertise. The answering unit can also provide an answer that explains in simpler terms to staff members with low expertise. For example, the answering unit evaluates the staff member's level of expertise and provides an answer that explains in simpler terms to staff members with low expertise. The answering unit can also adjust the use of technical terms in the answer content in real time according to the staff member's level of expertise. For example, the answering unit evaluates the staff member's level of expertise in real time and adjusts the use of technical terms in the answer content. In this way, by adjusting the use of technical terms in the answer content according to the staff member's level of expertise, a more appropriate answer is provided. Some or all of the above-mentioned processing in the answering unit may be performed using, for example, AI, or may be performed without AI. For example, the answering unit can input staff member's expertise level data into a generation AI and have the generation AI execute the use of technical terms in the answer content.

[0096] The optimization unit can estimate the staff's emotions and adjust the optimization method of the manual based on the estimated staff's emotions. For example, if the staff is nervous, the optimization unit uses an emotion engine to estimate the staff's emotions and provides a concise and easy-to-understand manual. For example, the optimization unit captures the staff's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm, and if the staff is nervous, the optimization unit provides a concise and easy-to-understand manual. The optimization unit can also estimate the staff's relaxed state using an emotion engine and provide a manual with detailed explanations. For example, the optimization unit can record the staff's voice and estimate their emotions using voice analysis technology, and if the staff is relaxed, the optimization unit can provide a manual with detailed explanations. The optimization unit can also estimate the staff's tired state using an emotion engine and provide a manual with a concise and easy-to-understand manual. For example, the optimization unit can collect the staff's biometric data (heart rate and electrodermal activity) with a sensor, estimate their emotions using an emotion estimation algorithm, and if the staff is tired, the optimization unit can provide a manual with a concise and easy-to-understand manual. This allows the optimization method of the manual to be adjusted based on the staff's emotions, thereby providing a more appropriate manual. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the optimization unit may be performed using AI, or may be performed without using AI. For example, the optimization unit may input image data of staff members taken with a camera into the generation AI and cause the generation AI to estimate their emotions.

[0097] During optimization, the optimization unit can optimize the optimization algorithm by referring to past optimization data. The optimization unit, for example, analyzes past optimization data and selects the most effective optimization algorithm. For example, the optimization unit analyzes past optimization data and selects the most effective optimization algorithm. The optimization unit can also identify frequently occurring problems from the past optimization data and adjust the optimization algorithm. For example, the optimization unit analyzes past optimization data, identifies frequently occurring problems, and adjusts the optimization algorithm. The optimization unit can also improve the optimization algorithm in real time based on the past optimization data. For example, the optimization unit analyzes past optimization data in real time and improves the optimization algorithm. In this way, the accuracy of the optimization algorithm is improved by referring to the past optimization data. Some or all of the above-mentioned processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input past optimization data to a generation AI and cause the generation AI to improve the optimization algorithm.

[0098] During optimization, the optimization unit can select the optimal optimization method by analyzing the frequency and content of questions. For example, the optimization unit adds detailed explanations to steps that are frequently asked about. For example, the optimization unit adds detailed explanations to steps that are frequently asked about. The optimization unit can also analyze the content of questions, identify common problems, and optimize them. For example, the optimization unit analyzes the content of questions, identify common problems, and optimize them. The optimization unit can also select the optimal optimization method in real time depending on the frequency and content of questions. For example, the optimization unit analyzes the frequency and content of questions in real time and selects the optimal optimization method. In this way, the optimal optimization method can be selected by analyzing the frequency and content of questions. Some or all of the above-mentioned processing in the optimization unit may be performed using, or without, AI. For example, the optimization unit can input question frequency and content data to the generation AI and cause the generation AI to select an optimization method.

[0099] The optimization unit can improve the optimization method by reflecting staff feedback during optimization. The optimization unit, for example, analyzes staff feedback and improves the optimization method. For example, the optimization unit analyzes staff feedback and improves the optimization method. The optimization unit can also adjust the optimization algorithm based on staff feedback. For example, the optimization unit adjusts the optimization algorithm based on staff feedback. The optimization unit can also reflect staff feedback in real time and improve the optimization method. For example, the optimization unit reflects staff feedback in real time and improves the optimization method. In this way, the optimization method is improved by reflecting staff feedback. Some or all of the above-mentioned processing in the optimization unit may be performed using AI, for example, or may be performed without using AI. For example, the optimization unit can input staff feedback data into the generation AI and cause the generation AI to improve the optimization method.

[0100] The optimization unit can estimate the emotions of staff members and determine optimization priorities based on the estimated emotions of the staff members. For example, if the staff member is nervous, the optimization unit estimates this using an emotion engine and prioritizes the optimization of important procedures. For example, the optimization unit captures the facial expressions of the staff members with a camera and estimates their emotions using an emotion estimation algorithm, and if the staff member is nervous, prioritizes the optimization of important procedures. The optimization unit can also estimate if the staff member is relaxed using an emotion engine and prioritize the optimization of detailed procedures. For example, the optimization unit records the voice of the staff member and estimates their emotions using voice analysis technology, and if the staff member is relaxed, prioritizes the optimization of detailed procedures. The optimization unit can also estimate if the staff member is tired using an emotion engine and prioritize the optimization of simple procedures. For example, the optimization unit collects biometric data of the staff member (heart rate and electrodermal activity) using a sensor and estimates their emotions using an emotion estimation algorithm, and if the staff member is tired, prioritizes the optimization of simple procedures. This allows for more appropriate optimization by determining the priorities of optimization based on the emotions of the staff members. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the optimization unit may be performed using, or without, an AI. For example, the optimization unit may input image data of a staff member taken with a camera into the generation AI and cause the generation AI to estimate emotions.

[0101] During optimization, the optimization unit can select the optimal optimization method by taking into account the geographic distribution of questions. For example, the optimization unit selects a region-specific optimization method for a region with a large number of questions. For example, the optimization unit evaluates the geographic distribution of questions and selects a region-specific optimization method for a region with a large number of questions. The optimization unit can also select a general optimization method for a region with a small number of questions. For example, the optimization unit evaluates the geographic distribution of questions and selects a general optimization method for a region with a small number of questions. The optimization unit can also select the optimal optimization method in real time based on the geographic distribution of questions. For example, the optimization unit evaluates the geographic distribution of questions in real time and selects the optimal optimization method. In this way, the optimal optimization method can be selected by taking the geographic distribution of questions into consideration. Some or all of the above-described processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input geographic distribution data of questions to the generation AI and cause the generation AI to select an optimization method.

[0102] The optimization unit can improve the accuracy of optimization by referring to literature related to the question during optimization. For example, the optimization unit improves the accuracy of optimization by referring to literature related to the question. For example, the optimization unit improves the accuracy of optimization by referring to literature related to the question. The optimization unit can also adjust the optimization method based on the related literature according to the content of the question. For example, the optimization unit adjusts the optimization method based on the related literature according to the content of the question. The optimization unit can also improve the accuracy of optimization by referring to literature related to the question in real time. For example, the optimization unit improves the accuracy of optimization by referring to literature related to the question in real time. As a result, the accuracy of optimization is improved by referring to literature related to the question. Some or all of the above-mentioned processing in the optimization unit may be performed using AI, for example, or may be performed without using AI. For example, the optimization unit can input literature data related to the question to the generation AI and cause the generation AI to adjust the optimization method.

[0103] The optimization unit can perform optimization taking into account the market value of the question during optimization. For example, the optimization unit performs detailed optimization for questions with high market value. For example, the optimization unit evaluates the market value of the question and performs detailed optimization for the question with high market value. The optimization unit can also perform simple optimization for questions with low market value. For example, the optimization unit evaluates the market value of the question and performs simple optimization for the question with low market value. The optimization unit can also adjust the optimization method in real time according to the market value of the question. For example, the optimization unit evaluates the market value of the question in real time and adjusts the optimization method. In this way, more effective optimization can be performed by taking the market value of the question into consideration. Some or all of the above-mentioned processing in the optimization unit may be performed using, for example, AI, or may be performed without using AI. For example, the optimization unit can input market value data of the question to the generation AI and cause the generation AI to adjust the optimization method. === Hard Collateral 1-1 === Each of the multiple elements including the adjustment unit, playback unit, response unit, and optimization unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the adjustment unit is realized by a sensor of the smart device 14 or the specific processing unit 290 of the data processing device 12. The playback unit is realized, for example, by the control unit 46A of the smart device 14, and adjusts the speed and content of audio playback. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and immediately answers staff questions using voice recognition technology. The optimization unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the frequency and content of questions and automatically optimizes the manual. === Hard Collateral 1-2 === Each of the multiple elements, including the adjustment unit, playback unit, response unit, and optimization unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the adjustment unit is realized by a sensor of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The playback unit is realized, for example, by the control unit 46A of the smart glasses 214, and adjusts the speed and content of audio playback. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and immediately answers staff questions using voice recognition technology. The optimization unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the frequency and content of questions and automatically optimizes the manual. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned adjustment unit, playback unit, response unit, and optimization unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the adjustment unit is realized by a sensor of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The playback unit is realized, for example, by the control unit 46A of the headset type terminal 314, and adjusts the speed and content of audio playback. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and immediately answers questions from staff members using voice recognition technology. The optimization unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the frequency and content of questions and automatically optimizes the manual. === Hard Collateral 1-4 === Each of the multiple elements including the adjustment unit, playback unit, response unit, and optimization unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the adjustment unit is realized by a sensor of the robot 414 or the specific processing unit 290 of the data processing device 12. The playback unit is realized, for example, by the control unit 46A of the robot 414, and adjusts the speed and content of the voice playback. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and immediately answers questions from staff members using voice recognition technology. The optimization unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the frequency and content of questions and automatically optimizes the manual.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The adjustment unit not only detects the work speed of staff members, but also learns their work patterns and predicts the optimal work speed. For example, the adjustment unit analyzes the staff members' past work data and predicts fluctuations in work speed during specific times of the day or day of the week. The adjustment unit can also suggest the optimal work speed before the work begins, based on the staff members' work patterns. Furthermore, the adjustment unit can learn the staff members' work patterns and adapt to new work. In this way, by learning the staff members' work patterns, it becomes possible to detect and predict work speeds more efficiently.

[0106] The playback unit can estimate the emotions of the staff and adjust the content of the audio playback based on the estimated emotions of the staff. For example, if the staff is nervous, the playback unit can play music or a message to help them relax. Also, if the staff is tired, the playback unit can play content to encourage them. Furthermore, if the staff is concentrating, the playback unit can play quiet environmental sounds to help them concentrate on their work. In this way, work efficiency can be improved by adjusting the content of the audio playback based on the emotions of the staff.

[0107] The answering section can provide relevant videos and images depending on the staff member's question. For example, if a staff member asks about a specific procedure, the answering section can provide a video showing that procedure. Alternatively, if a staff member asks about how to operate a device, the answering section can provide an image showing how to operate that device. Furthermore, if a staff member asks about a complex concept, the answering section can provide an infographic that visually explains the concept. This can deepen the staff member's understanding by providing visual information.

[0108] The optimization unit can estimate the emotions of the staff and adjust the optimization method of the manual based on the estimated emotions of the staff. For example, if the staff is nervous, the optimization unit can provide a concise and easy-to-understand manual. If the staff is relaxed, the optimization unit can also provide a manual with detailed explanations. Furthermore, if the staff is tired, the optimization unit can also provide a manual that focuses on the main points. In this way, by adjusting the optimization method of the manual based on the emotions of the staff, a more appropriate manual can be provided.

[0109] The adjustment unit not only detects the working speed of the staff member, but also monitors the working environment of the staff member and adjusts the accuracy of detecting the working speed according to the environment. For example, the adjustment unit may use a sensor to detect the temperature and humidity of the working environment and prioritize the working speed under appropriate environmental conditions. The adjustment unit may also monitor the lighting conditions of the working environment and prioritize the working speed under optimal lighting conditions. Furthermore, the adjustment unit may monitor the noise level of the working environment and prioritize the working speed in a quiet environment. This allows for more accurate detection of the working speed by taking the working environment into consideration.

[0110] The playback unit can estimate the emotions of the staff member and adjust the speed of the audio playback based on the estimated emotions of the staff member. For example, the playback unit can slow down the audio playback speed if the staff member is nervous. The playback unit can also speed up the audio playback speed if the staff member is relaxed. Furthermore, the playback unit can also adjust the audio playback speed appropriately if the staff member is tired. In this way, by adjusting the audio playback speed based on the emotions of the staff member, audio can be played back at a more appropriate speed.

[0111] The answering section can provide links to relevant external resources depending on the content of the staff member's question. For example, if the staff member asks about a specific technology, the answering section can provide a link to an external specialist site on that technology. Also, if the staff member asks about a specific product, the answering section can provide a link to the official website of that product. Furthermore, if the staff member wants to learn more about a specific topic, the answering section can provide a link to an online course or webinar on that topic. This allows staff members to expand their knowledge by utilizing external resources.

[0112] The optimization unit can estimate the emotions of the staff and determine the priority of optimization based on the estimated emotions of the staff. For example, if the staff is nervous, the optimization unit can prioritize the optimization of important procedures. Also, if the staff is relaxed, the optimization unit can prioritize the optimization of detailed procedures. Furthermore, if the staff is tired, the optimization unit can prioritize the optimization of simple procedures. In this way, by determining the priority of optimization based on the emotions of the staff, more appropriate optimization can be performed.

[0113] The adjustment unit not only detects the work speed of the staff member, but also monitors the health condition of the staff member and adjusts the detection accuracy of the work speed according to the health condition. For example, the adjustment unit detects the heart rate and blood pressure of the staff member using a sensor, and increases the detection accuracy when the health condition is good. The adjustment unit can also relax the detection accuracy when the health condition of the staff member is poor. Furthermore, the adjustment unit can periodically monitor the health condition of the staff member and adjust the detection accuracy in real time. This makes it possible to detect a more appropriate work speed by taking the health condition of the staff member into consideration.

[0114] The playback unit can estimate the emotions of the staff member and adjust the content of the audio playback based on the estimated emotions of the staff member. For example, if the staff member is tense, the playback unit can play content that will relax them. Also, if the staff member is relaxed, the playback unit can play content that will encourage them to concentrate on their work. Furthermore, if the staff member is tired, the playback unit can play content that will encourage them. In this way, by adjusting the content of the audio playback based on the emotions of the staff member, more appropriate content can be played back.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The adjustment unit detects the working speed of the staff. For example, it uses a sensor to monitor the working speed of the staff in real time and adjusts the detection accuracy according to changes in the working speed. Step 2: The playback unit adjusts the audio playback based on the work speed detected by the adjustment unit. For example, the playback unit changes the audio playback speed to match the work speed of the staff member, and adjusts the content and volume of the audio playback according to the progress of the work. Step 3: The answering department analyzes the staff member's question using voice recognition technology and provides an immediate answer. For example, it selects the most appropriate answer from a pre-registered answer database and provides a quick answer based on past question history. Step 4: The optimization section records any questions or concerns that arise during the work, consolidates the information, and improves the manual. For example, it analyzes the frequency and content of questions, automatically refines explanations of specific procedures, and periodically updates the manual based on the consolidated information.

[0117] 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.

[0118] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] 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.

[0120] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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).

[0174] 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.

[0175] 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."

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0187] 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.

[0188] [Explanation of symbols]

[0189] 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. An adjustment unit that detects the work speed of staff, a playback unit that adjusts audio playback based on the work speed detected by the adjustment unit; The answering department analyzes staff questions using voice recognition technology and provides immediate answers; An optimization unit that records any questions or concerns that arise during work and consolidates the information to improve the manual. A system characterized by:

2. The adjustment unit Use sensors to detect staff working speed 2. The system of claim 1.

3. The playback unit Adjust audio playback to match staff working speed 2. The system of claim 1.

4. The answering section Provides instant answers from a pre-registered answer database 2. The system of claim 1.

5. The optimization unit Analyzes the frequency and content of questions and automatically provides detailed explanations for specific procedures 2. The system of claim 1.

6. The adjustment unit Estimate the emotions of staff members and adjust the accuracy of work speed detection based on the estimated emotions of staff members 2. The system of claim 1.

7. The adjustment unit Analyze staff's past work history and select the optimal method for detecting work speed 2. The system of claim 1.

8. The adjustment unit When detecting work speed, the accuracy of detection is adjusted taking into account the current physical condition and fatigue level of the staff member.

2. The system of claim 1.

9. The adjustment unit When detecting work speed, optimize the detection method based on the staff's working environment.

2. The system of claim 1.

10. The adjustment unit Estimate the emotions of staff and adjust the timing of detecting work speed based on the estimated emotions of staff 2. The system of claim 1.

Images