system

Abstract

The system according to this embodiment aims to monitor the working conditions of foreign technical trainees and protect their rights. [Solution] The system according to this embodiment comprises a monitoring unit, a reception unit, and a provision unit. The monitoring unit monitors the working environment. The reception unit receives consultations and reports. The provision unit provides education and information on local labor laws and rights.

Description

Technical Field

[0006] , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, effective monitoring and support for preventing unfair treatment of foreign technical trainees have not been sufficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to monitor the working environment of foreign technical trainees and protect their rights.

Means for Solving the Problems

[0006] The system according to the embodiment includes a monitoring unit, a reception unit, and a provision unit. The monitoring unit monitors the working environment. The reception unit receives consultations and reports. The provision unit provides education and information on local labor laws and rights.

Effects of the Invention

[0007] The system according to this embodiment can monitor the working environment of foreign technical trainees and protect their rights. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The AI ​​agent service according to an embodiment of the present invention is a system designed to prevent foreign technical interns from being treated unfairly and to protect their rights. This system provides monitoring of the working environment, consultation and reporting support, education, and information. The AI ​​agent service is a system designed to prevent foreign technical interns from being treated unfairly and to protect their rights. Specifically, it consists of the following steps. First, the AI ​​agent monitors the working environment and issues a warning if there is an abnormality. Next, the problem is immediately reported to a 24 / 7 consultation service using an AI chatbot, and countermeasures are taken. It also has a multi-language function, eliminating language barriers and facilitating smooth information provision and consultation. Furthermore, it provides appropriate education and information to interns regarding local labor laws and rights. This mechanism protects the rights of foreign technical interns and provides a safe working environment. First, the AI ​​agent monitors the working environment. At this time, it monitors working conditions and the work environment in real time and issues a warning immediately if an abnormality is detected. For example, if excessive working hours or an inappropriate work environment are detected, the AI ​​agent issues a warning and prompts appropriate countermeasures. Next, a 24 / 7 consultation service using an AI chatbot will be available to immediately report any problems. For example, if a trainee is treated unfairly, they can consult the AI ​​chatbot to immediately report the problem and take action. This allows trainees to receive support quickly. The system also supports multiple languages, eliminating language barriers and facilitating smooth information provision and consultations. For example, a chatbot supporting over 20 languages ​​will be introduced, allowing trainees to receive consultations and information in their native language. This eliminates language barriers and provides a safe environment for trainees to seek advice. Furthermore, appropriate education and information will be provided to trainees regarding local labor laws and rights. For example, information on labor laws and rights will be provided to trainees so that they understand their rights and are not treated unfairly. This will give trainees the knowledge to protect their rights. Through this system, the rights of foreign technical trainees can be protected, and a safe working environment can be provided.For example, by monitoring working conditions, establishing consultation services, providing multilingual support, and offering education and information, it is possible to prevent trainees from being treated unfairly and to protect their rights. This will provide a safe working environment for trainees, allow them to make economic contributions, and contribute to the realization of a multicultural society. In this way, AI agent services can protect the rights of foreign technical trainees and provide a safe working environment.

[0029] The AI ​​agent service according to this embodiment comprises a monitoring unit, a reception unit, and a provision unit. The monitoring unit monitors the work environment. For example, the monitoring unit monitors working conditions and the work environment in real time and issues an immediate warning if an abnormality is detected. For example, if excessive working hours or an inappropriate work environment are detected, the monitoring unit will issue a warning and prompt appropriate countermeasures. The monitoring unit can also use AI to monitor the work environment. For example, the monitoring unit can use AI to analyze data on working conditions and the work environment and detect abnormalities. The reception unit receives consultations and reports. For example, the reception unit functions as a 24 / 7 consultation service and immediately reports problems. For example, if an intern is treated unfairly, the reception unit will receive a consultation and immediately report the problem. The reception unit can also use AI to receive consultations and reports. For example, the reception unit can use an AI chatbot to receive consultations from interns and report problems. The provision unit provides education and information on local labor laws and rights. The service provider, for example, provides trainees with information on labor laws and rights so that they understand their rights and are not subjected to unfair treatment. For example, the service provider conducts lectures and workshops on labor laws and rights to educate trainees. The service provider can also use AI to provide education and information. For example, the service provider can use AI to automatically provide information on labor laws and rights to trainees and educate them. In this way, the AI ​​agent service according to the embodiment can protect the rights of foreign technical trainees by monitoring their working environment, receiving consultations and reports, and providing education and information.

[0030] The monitoring unit monitors the work environment. For example, the monitoring unit monitors working conditions and the work environment in real time and issues immediate warnings if abnormalities are detected. Specifically, the monitoring unit collects environmental data such as temperature, humidity, noise level, and illuminance through sensors and cameras installed in each workplace. This data is transmitted to a central monitoring system, where AI performs real-time analysis. The AI ​​compares this data with past data and baseline values ​​to detect abnormal patterns and dangerous situations. For example, if excessive working hours are detected, the AI ​​analyzes the data and assesses the health risks to workers. Also, if an inappropriate work environment is detected, such as if the temperature is too high or the noise level exceeds the standard, an immediate warning is issued and the manager is notified. Furthermore, the monitoring unit can also use AI to monitor the work environment. For example, the AI ​​can analyze data on working conditions and the work environment, not only to detect abnormalities but also to perform predictive analysis and forecast future risks. This allows the monitoring unit to enhance the safety of the work environment and protect the health and safety of workers. In addition, the monitoring unit has a function to automatically propose countermeasures when abnormalities are detected. For example, if excessive working hours are detected, the AI ​​will send a notification to the worker prompting them to take a break and will suggest adjustments to working hours to the manager. Furthermore, if an inappropriate work environment is detected, the AI ​​will suggest specific measures to improve the environment and support a swift response. This allows the monitoring department to efficiently monitor and improve the work environment, protecting workers' rights and safety.

[0031] The reception department receives consultations and reports. For example, the reception department functions as a 24 / 7 consultation hotline and reports problems immediately. Specifically, the reception department receives consultations and reports from workers using multiple communication methods such as telephone, email, and chat. For example, if a worker is treated unfairly, the reception department will receive the consultation and immediately report the problem. The reception department can also use AI to receive consultations and reports. For example, the reception department can use an AI chatbot to receive consultations from workers and report problems. The AI ​​chatbot uses natural language processing technology to understand the content of the worker's consultation and take appropriate action. For example, if a worker consults about excessive working hours, the AI ​​chatbot will analyze the content and propose appropriate countermeasures. The AI ​​chatbot can also record the content of the worker's consultation and escalate it to a specialist counselor if necessary. This allows the reception department to respond to workers' consultations and reports quickly and appropriately, and to support the early resolution of problems. Furthermore, the reception department is equipped with functions to protect workers' privacy. For example, consultations and reports are transmitted via encrypted communication and securely stored in a database. The reception department also provides features to maintain worker anonymity, allowing workers to consult or report with confidence. This enables the reception department to protect workers' rights and provide a safe working environment.

[0032] The service provider provides education and information on local labor laws and rights. For example, the service provider provides workers with information on labor laws and rights so that they understand their rights and are not subjected to unfair treatment. Specifically, the service provider conducts lectures and workshops on labor laws and rights to educate workers. These lectures and workshops explain basic knowledge of labor law and workers' rights and obligations in detail. The service provider can also use AI to provide education and information. For example, the service provider can use AI to automatically provide information on labor laws and rights to educate workers. The AI ​​provides appropriate answers to workers' questions and helps deepen their knowledge of labor laws and rights. Furthermore, the service provider can provide information on labor laws and rights through an online platform. For example, workers can access the online platform to search for and learn about information on labor laws and rights. The service provider can also provide specific advice and support to help workers protect their rights. For example, if a worker is subjected to unfair treatment, the service provider will advise on appropriate countermeasures and legal procedures and help the worker protect their rights. This allows the service provider to provide education and information to help workers understand and protect their rights, creating a safe and secure working environment. Furthermore, the service provider can offer customized educational programs tailored to the needs of workers. For example, they can provide educational programs on labor laws and rights specific to particular industries or occupations, helping workers address specific issues they face in their workplaces. In this way, the service provider can play a vital role in protecting workers' rights and creating a comfortable working environment.

[0033] The multilingual department has multilingual support capabilities. For example, by supporting multiple languages, the multilingual department eliminates language barriers, allowing trainees to receive consultations and information with peace of mind. For instance, the multilingual department has introduced a chatbot that supports more than 20 languages, allowing trainees to receive consultations and information in their native language. The multilingual department can also use AI for multilingual support. For example, the multilingual department uses AI for automatic translation, allowing trainees to receive consultations and information in their native language. In this way, by supporting multiple languages, language barriers are eliminated, allowing trainees to receive consultations and information with peace of mind.

[0034] The reporting department will notify the appropriate agencies and support organizations in times of emergency. For example, by notifying the appropriate agencies and support organizations in times of emergency, the reporting department can enable a swift response. For instance, the reporting department can notify appropriate agencies and support organizations such as labor standards inspection offices and NPOs. Furthermore, the reporting department can also use AI to make emergency notifications. For example, the reporting department can use AI to analyze the situation in an emergency and notify the appropriate agencies and support organizations. This allows for a swift response by notifying the appropriate agencies and support organizations in times of emergency.

[0035] The voice dialogue unit utilizes speech recognition technology. For example, by using speech recognition technology, the voice dialogue unit allows trainees to make consultations and reports via voice. For instance, the voice dialogue unit uses a speech recognition algorithm to convert the trainee's voice into text and receive consultations and reports. Furthermore, the voice dialogue unit can also perform speech recognition using AI. For example, the voice dialogue unit uses AI to perform speech recognition and convert the trainee's voice into text. This allows trainees to make consultations and reports via voice using speech recognition technology.

[0036] The information acquisition unit utilizes two-dimensional codes (e.g., QR codes®). By utilizing two-dimensional codes, the information acquisition unit enables trainees to easily obtain information. For example, the information acquisition unit generates a two-dimensional code, which trainees can scan with their smartphones to acquire the information. Furthermore, the information acquisition unit can also analyze the information in the two-dimensional code using AI. For example, the information acquisition unit uses AI to analyze the information in the two-dimensional code and provides it to the trainees. This allows trainees to easily obtain information by utilizing two-dimensional codes.

[0037] The monitoring unit can monitor working conditions and the work environment in real time and issue immediate warnings if any abnormalities are detected. For example, if excessive working hours or an inappropriate work environment are detected, the monitoring unit will issue a warning and prompt appropriate countermeasures. The monitoring unit can also use AI to monitor the work environment. For example, the monitoring unit can use AI to analyze data on working conditions and the work environment and detect abnormalities. This allows for real-time monitoring of working conditions and the work environment, enabling immediate warnings if abnormalities are detected.

[0038] The reception desk functions as a 24 / 7 consultation service, allowing for immediate reporting of problems. For example, if an intern experiences unfair treatment, the reception desk will receive a consultation and immediately report the problem. Furthermore, the reception desk can utilize AI to handle consultations and reports. For example, the reception desk can use an AI chatbot to receive consultations from interns and report problems. This allows the reception desk to function as a 24 / 7 consultation service, enabling immediate reporting of problems.

[0039] The service provider can provide education and information on local labor laws and rights. For example, the service provider can provide trainees with information on labor laws and rights so that they understand their rights and are not subjected to unfair treatment. For example, the service provider can conduct lectures and workshops on labor laws and rights to educate trainees. The service provider can also use AI to provide education and information. For example, the service provider can use AI to automatically provide information on labor laws and rights to educate trainees. In this way, by providing education and information on local labor laws and rights, trainees can understand their rights and be prevented from being subjected to unfair treatment.

[0040] The monitoring unit can optimize its anomaly detection algorithm by referring to past anomaly data when monitoring the work environment. For example, the monitoring unit can analyze past anomaly data to improve the accuracy of the anomaly detection algorithm. For example, the monitoring unit can learn patterns in anomaly data to detect new anomalies early. The monitoring unit can also enhance anomaly detection in specific time periods or situations based on the anomaly data. This improves the accuracy of anomaly detection by optimizing the anomaly detection algorithm by referring to past anomaly data. Some or all of the above processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input past anomaly data into a generating AI and have the generating AI perform the optimization of the anomaly detection algorithm.

[0041] The monitoring unit can monitor the health status of trainees while monitoring the work environment and issue warnings if abnormalities are detected. For example, the monitoring unit can monitor trainees' heart rate and body temperature and issue warnings if abnormalities are detected. For example, the monitoring unit can monitor trainees' fatigue levels and issue warnings if there are signs of overwork. The monitoring unit can also periodically check the health status of trainees and take appropriate measures if abnormalities are detected. In this way, by monitoring the health status of trainees, warnings can be issued if abnormalities are detected. Some or all of the above processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input trainees' health data into a generating AI and have the generating AI perform abnormality detection.

[0042] The monitoring unit can perform anomaly detection while monitoring the work environment, taking into account the geographical location information of the trainees. For example, if a trainee is in a specific area, the monitoring unit can perform anomaly detection based on the characteristics of that area. For example, the monitoring unit can analyze the trainees' movement patterns and issue a warning if there is any abnormal movement. Furthermore, if a trainee is in a dangerous area, the monitoring unit can increase the sensitivity of anomaly detection and respond quickly. This makes it possible to perform anomaly detection with higher accuracy by taking into account the geographical location information of the trainees. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without using AI. For example, the monitoring unit can input the trainees' geographical location data into a generating AI and have the generating AI perform anomaly detection.

[0043] The monitoring unit can analyze the social media activities of trainees when monitoring the work environment and detect relevant anomalies. For example, the monitoring unit can analyze trainees' social media posts to detect signs of stress or dissatisfaction. For example, the monitoring unit can detect abnormal behavioral patterns from trainees' social media activities. The monitoring unit can also analyze trainees' communication on social media to detect abnormal situations early. In this way, by analyzing trainees' social media activities, relevant anomalies can be detected early. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input trainees' social media data into a generating AI and have the generating AI perform anomaly detection.

[0044] The reception department can select the most appropriate response method by referring to past consultation history at the time of reception. For example, the reception department can analyze the intern's past consultation history and propose the most appropriate response method. For example, the reception department can select a response method for similar problems from past consultation history. The reception department can also provide individually customized response methods based on the intern's past consultation history. This makes it possible to provide more appropriate responses by selecting the most appropriate response method by referring to past consultation history. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input past consultation history data into a generating AI and have the generating AI perform the selection of the most appropriate response method.

[0045] The reception department can customize its response method based on the trainee's current situation at the time of registration. For example, the reception department may propose the optimal response method considering the trainee's current work environment. For example, the reception department may select an appropriate response method considering the trainee's current health condition. The reception department may also customize the response method considering the trainee's current emotional state. This allows for more appropriate responses by customizing the response method based on the trainee's current situation. Some or all of the above processes at the reception department may be performed using AI, for example, or not using AI. For example, the reception department may input the trainee's current situation data into a generating AI and have the generating AI perform the customization of the response method.

[0046] The reception department can select the most appropriate response method at the time of registration, taking into account the trainee's geographical location information. For example, if the trainee is in a specific area, the reception department will select a response method based on the characteristics of that area. For example, the reception department may suggest the most suitable support organization based on the trainee's geographical location information. The reception department can also analyze the trainee's movement patterns and select an appropriate response method. By selecting the most appropriate response method while considering the trainee's geographical location information, a more appropriate response becomes possible. Some or all of the above processing at the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input the trainee's geographical location data into a generating AI and have the generating AI select a response method.

[0047] The reception department can analyze the intern's social media activity at the time of reception and prioritize the processing of relevant inquiries. For example, the reception department can analyze the intern's social media posts and prioritize the processing of urgent inquiries. For example, the reception department can extract relevant inquiries from the intern's social media activity and respond to them preferentially. The reception department can also analyze the intern's social media communications and prioritize the processing of important inquiries. In this way, by analyzing the intern's social media activity, relevant inquiries can be processed preferentially. Some or all of the above processing at the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input the intern's social media data into a generating AI and have the generating AI perform the preferential processing of inquiries.

[0048] The service provider can select the optimal teaching method by referring to past teaching history during training. For example, the service provider can analyze a trainee's past teaching history and propose the optimal teaching method. For example, the service provider can select a teaching method suitable for a trainee based on their past teaching history. The service provider can also provide individually customized teaching methods based on a trainee's past teaching history. This makes it possible to provide more appropriate training by selecting the optimal teaching method by referring to past teaching history. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider can input past teaching history data into a generating AI and have the generating AI select the optimal teaching method.

[0049] The service provider can customize the educational content based on the trainee's current situation during training. For example, the service provider can provide optimal educational content considering the trainee's current work environment. For example, the service provider can select appropriate educational content considering the trainee's current health condition. The service provider can also customize the educational content considering the trainee's current emotional state. This allows for more appropriate training by customizing the educational content based on the trainee's current situation. Some or all of the above processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the trainee's current situation data into a generating AI and have the generating AI perform the customization of the educational content.

[0050] The service provider can select the optimal teaching method during training by considering the geographical location information of the trainees. For example, if a trainee is in a specific area, the service provider can select a teaching method based on the characteristics of that area. For example, the service provider can suggest the most suitable educational institution based on the trainee's geographical location information. The service provider can also analyze the trainee's movement patterns and select an appropriate teaching method. By selecting the optimal teaching method while considering the trainee's geographical location information, more appropriate training becomes possible. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the trainee's geographical location data into a generating AI and have the generating AI perform the selection of the teaching method.

[0051] The service provider can analyze the social media activities of trainees during training and prioritize the provision of relevant educational content. For example, the service provider can analyze trainees' social media posts and prioritize the provision of urgent educational content. For example, the service provider can extract relevant educational content from trainees' social media activities and prioritize its provision. The service provider can also analyze trainees' social media communications and prioritize the provision of important educational content. In this way, by analyzing trainees' social media activities, relevant educational content can be prioritized. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input trainees' social media data into a generating AI and have the generating AI perform the priority provision of educational content.

[0052] The multilingual unit can select the optimal language selection method by referring to past usage history when providing multilingual support. For example, the multilingual unit can analyze the trainee's past language usage history and suggest the most suitable language. For example, the multilingual unit can select the language that the trainee finds easiest to understand based on past usage history. The multilingual unit can also provide individually customized language selection methods based on the trainee's past language usage history. This allows for more appropriate language selection by referring to past usage history to select the optimal language selection method. Some or all of the above processing in the multilingual unit may be performed using AI, for example, or without AI. For example, the multilingual unit can input past usage history data into a generating AI and have the generating AI select the optimal language selection method.

[0053] The multilingual department can select the optimal language selection method when providing multilingual support, taking into account the geographical location information of the trainees. For example, if a trainee is in a specific area, the multilingual department will select a language selection method based on the characteristics of that area. For example, the multilingual department will propose the optimal language based on the trainee's geographical location information. The multilingual department can also analyze the trainee's movement patterns and select an appropriate language selection method. By selecting the optimal language selection method while considering the trainee's geographical location information, a more appropriate language selection becomes possible. Some or all of the above processing in the multilingual department may be performed using AI, for example, or without AI. For example, the multilingual department can input the trainee's geographical location data into a generating AI and have the generating AI perform the selection of the language selection method.

[0054] The reporting department can select the most appropriate reporting method by referring to past reporting history when a report is made. For example, the reporting department can analyze an intern's past reporting history and propose the most appropriate reporting method. For example, the reporting department can select a reporting method for similar problems from past reporting history. The reporting department can also provide individually customized reporting methods based on an intern's past reporting history. This makes it possible to make more appropriate reports by selecting the most appropriate reporting method by referring to past reporting history. Some or all of the above processing in the reporting department may be performed using AI, for example, or not using AI. For example, the reporting department can input past reporting history data into a generating AI and have the generating AI select the most appropriate reporting method.

[0055] The reporting department can select the most appropriate reporting method when a report is made, taking into account the trainee's geographical location. For example, if the trainee is in a specific area, the reporting department will select a reporting method based on the characteristics of that area. For example, the reporting department will propose the most appropriate reporting agency based on the trainee's geographical location. The reporting department can also analyze the trainee's movement patterns and select an appropriate reporting method. By selecting the most appropriate reporting method while considering the trainee's geographical location, more appropriate reporting becomes possible. Some or all of the above processing in the reporting department may be performed using AI, for example, or without AI. For example, the reporting department can input the trainee's geographical location data into a generating AI and have the generating AI perform the selection of the reporting method.

[0056] The voice dialogue unit can select the optimal dialogue method by referring to past dialogue history during voice dialogue. For example, the voice dialogue unit can analyze the trainee's past dialogue history and propose the optimal dialogue method. For example, the voice dialogue unit can select a dialogue method for similar problems from past dialogue history. The voice dialogue unit can also provide individually customized dialogue methods based on the trainee's past dialogue history. This makes more appropriate voice dialogue possible by selecting the optimal dialogue method by referring to past dialogue history. Some or all of the above processing in the voice dialogue unit may be performed using AI, for example, or without AI. For example, the voice dialogue unit can input past dialogue history data into a generating AI and have the generating AI perform the selection of the optimal dialogue method.

[0057] The voice dialogue unit can select the optimal dialogue method during voice dialogue by considering the trainee's geographical location information. For example, if the trainee is in a specific area, the voice dialogue unit will select a dialogue method based on the characteristics of that area. For example, the voice dialogue unit will propose the optimal dialogue method based on the trainee's geographical location information. The voice dialogue unit can also analyze the trainee's movement patterns and select an appropriate dialogue method. By selecting the optimal dialogue method while considering the trainee's geographical location information, more appropriate voice dialogue becomes possible. Some or all of the above processing in the voice dialogue unit may be performed using AI, for example, or without AI. For example, the voice dialogue unit can input the trainee's geographical location data into a generating AI and have the generating AI perform the selection of the dialogue method.

[0058] The information acquisition unit can select the optimal acquisition method by referring to past acquisition history when acquiring information. For example, the information acquisition unit can analyze the trainee's past information acquisition history and propose the optimal acquisition method. For example, the information acquisition unit can select an information acquisition method suitable for the trainee from past acquisition history. The information acquisition unit can also provide individually customized information acquisition methods based on the trainee's past information acquisition history. This makes it possible to acquire more appropriate information by selecting the optimal acquisition method by referring to past acquisition history. Some or all of the above processing in the information acquisition unit may be performed using AI, for example, or without using AI. For example, the information acquisition unit can input past acquisition history data into a generating AI and have the generating AI select the optimal acquisition method.

[0059] The information acquisition unit can select the optimal acquisition method when acquiring information, taking into account the trainee's geographical location information. For example, if the trainee is in a specific area, the information acquisition unit will select an information acquisition method based on the characteristics of that area. For example, the information acquisition unit will propose the optimal information acquisition method based on the trainee's geographical location information. The information acquisition unit can also analyze the trainee's movement patterns and select an appropriate information acquisition method. By selecting the optimal acquisition method while considering the trainee's geographical location information, more appropriate information acquisition becomes possible. Some or all of the above processing in the information acquisition unit may be performed using AI, for example, or without AI. For example, the information acquisition unit can input the trainee's geographical location data into a generating AI and have the generating AI select the acquisition method.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] In addition to monitoring the working environment, the monitoring department can also monitor the health of the trainees. For example, it can monitor the trainees' heart rate and body temperature in real time and issue an immediate warning if an abnormality is detected. It can also monitor the trainees' fatigue levels and issue a warning if there are signs of overwork. Furthermore, it can periodically check the trainees' health and take appropriate measures if any abnormalities are found. In this way, by monitoring the trainees' health, a warning can be issued if any abnormalities are detected.

[0062] In addition to monitoring the work environment, the monitoring unit can perform anomaly detection by considering the geographical location of the trainees. For example, if a trainee is in a specific area, anomaly detection will be performed based on the characteristics of that area. The trainees' movement patterns will be analyzed, and a warning will be issued if any abnormal movement is detected. Furthermore, if a trainee is in a dangerous area, the sensitivity of anomaly detection can be increased to allow for a quicker response. By considering the geographical location of the trainees when performing anomaly detection, more accurate anomaly detection becomes possible.

[0063] The reception desk not only functions as a 24 / 7 consultation service, but can also customize its response based on the trainee's current situation. For example, it can propose the most suitable response considering the trainee's current work environment, select an appropriate response considering the trainee's current health condition, and even customize the response based on the trainee's current emotional state. This allows for more appropriate responses by customizing the response based on the trainee's current situation.

[0064] The reporting department can not only report to the appropriate agencies and support groups in emergencies, but can also select the most suitable reporting method by referring to past reporting history. For example, it can analyze an intern's past reporting history and propose the most suitable reporting method. It can also select a reporting method for similar problems based on past reporting history. Furthermore, it can provide individually customized reporting methods based on an intern's past reporting history. This allows for more appropriate reporting by selecting the most suitable reporting method by referring to past reporting history.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The monitoring unit monitors the work environment. For example, it monitors working conditions and the work environment in real time and issues an immediate warning if an abnormality is detected. If excessive working hours or an inappropriate work environment are detected, it issues a warning and prompts appropriate countermeasures. The monitoring unit can also use AI to monitor the work environment. Using AI, it can analyze data on working conditions and the work environment and detect abnormalities. Step 2: The reception desk receives consultations and reports. For example, it functions as a 24 / 7 consultation hotline and reports problems immediately. If an intern is treated unfairly, the reception desk will receive a consultation and report the problem immediately. The reception desk can also use AI to receive consultations and reports. An AI chatbot can be used to receive consultations from interns and report problems. Step 3: The service provider will provide education and information on local labor laws and rights. For example, they will provide trainees with information on labor laws and rights so that they understand their rights and are not subjected to unfair treatment. They will also conduct lectures and workshops on labor laws and rights to educate trainees. The service provider can also use AI to provide education and information. AI can be used to automatically provide information on labor laws and rights and educate trainees.

[0067] (Example of form 2) The AI ​​agent service according to an embodiment of the present invention is a system designed to prevent foreign technical interns from being treated unfairly and to protect their rights. This system provides monitoring of the working environment, consultation and reporting support, education, and information. The AI ​​agent service is a system designed to prevent foreign technical interns from being treated unfairly and to protect their rights. Specifically, it consists of the following steps. First, the AI ​​agent monitors the working environment and issues a warning if there is an abnormality. Next, the problem is immediately reported to a 24 / 7 consultation service using an AI chatbot, and countermeasures are taken. It also has a multi-language function, eliminating language barriers and facilitating smooth information provision and consultation. Furthermore, it provides appropriate education and information to interns regarding local labor laws and rights. This mechanism protects the rights of foreign technical interns and provides a safe working environment. First, the AI ​​agent monitors the working environment. At this time, it monitors working conditions and the work environment in real time and issues a warning immediately if an abnormality is detected. For example, if excessive working hours or an inappropriate work environment are detected, the AI ​​agent issues a warning and prompts appropriate countermeasures. Next, a 24 / 7 consultation service using an AI chatbot will be available to immediately report any problems. For example, if a trainee is treated unfairly, they can consult the AI ​​chatbot to immediately report the problem and take action. This allows trainees to receive support quickly. The system also supports multiple languages, eliminating language barriers and facilitating smooth information provision and consultations. For example, a chatbot supporting over 20 languages ​​will be introduced, allowing trainees to receive consultations and information in their native language. This eliminates language barriers and provides a safe environment for trainees to seek advice. Furthermore, appropriate education and information will be provided to trainees regarding local labor laws and rights. For example, information on labor laws and rights will be provided to trainees so that they understand their rights and are not treated unfairly. This will give trainees the knowledge to protect their rights. Through this system, the rights of foreign technical trainees can be protected, and a safe working environment can be provided.For example, by monitoring working conditions, establishing consultation services, providing multilingual support, and offering education and information, it is possible to prevent trainees from being treated unfairly and to protect their rights. This will provide a safe working environment for trainees, allow them to make economic contributions, and contribute to the realization of a multicultural society. In this way, AI agent services can protect the rights of foreign technical trainees and provide a safe working environment.

[0068] The AI ​​agent service according to this embodiment comprises a monitoring unit, a reception unit, and a provision unit. The monitoring unit monitors the work environment. For example, the monitoring unit monitors working conditions and the work environment in real time and issues an immediate warning if an abnormality is detected. For example, if excessive working hours or an inappropriate work environment are detected, the monitoring unit will issue a warning and prompt appropriate countermeasures. The monitoring unit can also use AI to monitor the work environment. For example, the monitoring unit can use AI to analyze data on working conditions and the work environment and detect abnormalities. The reception unit receives consultations and reports. For example, the reception unit functions as a 24 / 7 consultation service and immediately reports problems. For example, if an intern is treated unfairly, the reception unit will receive a consultation and immediately report the problem. The reception unit can also use AI to receive consultations and reports. For example, the reception unit can use an AI chatbot to receive consultations from interns and report problems. The provision unit provides education and information on local labor laws and rights. The service provider, for example, provides trainees with information on labor laws and rights so that they understand their rights and are not subjected to unfair treatment. For example, the service provider conducts lectures and workshops on labor laws and rights to educate trainees. The service provider can also use AI to provide education and information. For example, the service provider can use AI to automatically provide information on labor laws and rights to trainees and educate them. In this way, the AI ​​agent service according to the embodiment can protect the rights of foreign technical trainees by monitoring their working environment, receiving consultations and reports, and providing education and information.

[0069] The monitoring unit monitors the work environment. For example, the monitoring unit monitors working conditions and the work environment in real time and issues immediate warnings if abnormalities are detected. Specifically, the monitoring unit collects environmental data such as temperature, humidity, noise level, and illuminance through sensors and cameras installed in each workplace. This data is transmitted to a central monitoring system, where AI performs real-time analysis. The AI ​​compares this data with past data and baseline values ​​to detect abnormal patterns and dangerous situations. For example, if excessive working hours are detected, the AI ​​analyzes the data and assesses the health risks to workers. Also, if an inappropriate work environment is detected, such as if the temperature is too high or the noise level exceeds the standard, an immediate warning is issued and the manager is notified. Furthermore, the monitoring unit can also use AI to monitor the work environment. For example, the AI ​​can analyze data on working conditions and the work environment, not only to detect abnormalities but also to perform predictive analysis and forecast future risks. This allows the monitoring unit to enhance the safety of the work environment and protect the health and safety of workers. In addition, the monitoring unit has a function to automatically propose countermeasures when abnormalities are detected. For example, if excessive working hours are detected, the AI ​​will send a notification to the worker prompting them to take a break and will suggest adjustments to working hours to the manager. Furthermore, if an inappropriate work environment is detected, the AI ​​will suggest specific measures to improve the environment and support a swift response. This allows the monitoring department to efficiently monitor and improve the work environment, protecting workers' rights and safety.

[0070] The reception department receives consultations and reports. For example, the reception department functions as a 24 / 7 consultation hotline and reports problems immediately. Specifically, the reception department receives consultations and reports from workers using multiple communication methods such as telephone, email, and chat. For example, if a worker is treated unfairly, the reception department will receive the consultation and immediately report the problem. The reception department can also use AI to receive consultations and reports. For example, the reception department can use an AI chatbot to receive consultations from workers and report problems. The AI ​​chatbot uses natural language processing technology to understand the content of the worker's consultation and take appropriate action. For example, if a worker consults about excessive working hours, the AI ​​chatbot will analyze the content and propose appropriate countermeasures. The AI ​​chatbot can also record the content of the worker's consultation and escalate it to a specialist counselor if necessary. This allows the reception department to respond to workers' consultations and reports quickly and appropriately, and to support the early resolution of problems. Furthermore, the reception department is equipped with functions to protect workers' privacy. For example, consultations and reports are transmitted via encrypted communication and securely stored in a database. The reception department also provides features to maintain worker anonymity, allowing workers to consult or report with confidence. This enables the reception department to protect workers' rights and provide a safe working environment.

[0071] The service provider provides education and information on local labor laws and rights. For example, the service provider provides workers with information on labor laws and rights so that they understand their rights and are not subjected to unfair treatment. Specifically, the service provider conducts lectures and workshops on labor laws and rights to educate workers. These lectures and workshops explain basic knowledge of labor law and workers' rights and obligations in detail. The service provider can also use AI to provide education and information. For example, the service provider can use AI to automatically provide information on labor laws and rights to educate workers. The AI ​​provides appropriate answers to workers' questions and helps deepen their knowledge of labor laws and rights. Furthermore, the service provider can provide information on labor laws and rights through an online platform. For example, workers can access the online platform to search for and learn about information on labor laws and rights. The service provider can also provide specific advice and support to help workers protect their rights. For example, if a worker is subjected to unfair treatment, the service provider will advise on appropriate countermeasures and legal procedures and help the worker protect their rights. This allows the service provider to provide education and information to help workers understand and protect their rights, creating a safe and secure working environment. Furthermore, the service provider can offer customized educational programs tailored to the needs of workers. For example, they can provide educational programs on labor laws and rights specific to particular industries or occupations, helping workers address specific issues they face in their workplaces. In this way, the service provider can play a vital role in protecting workers' rights and creating a comfortable working environment.

[0072] The multilingual department has multilingual support capabilities. For example, by supporting multiple languages, the multilingual department eliminates language barriers, allowing trainees to receive consultations and information with peace of mind. For instance, the multilingual department has introduced a chatbot that supports more than 20 languages, allowing trainees to receive consultations and information in their native language. The multilingual department can also use AI for multilingual support. For example, the multilingual department uses AI for automatic translation, allowing trainees to receive consultations and information in their native language. In this way, by supporting multiple languages, language barriers are eliminated, allowing trainees to receive consultations and information with peace of mind.

[0073] The reporting department will notify the appropriate agencies and support organizations in times of emergency. For example, by notifying the appropriate agencies and support organizations in times of emergency, the reporting department can enable a swift response. For instance, the reporting department can notify appropriate agencies and support organizations such as labor standards inspection offices and NPOs. Furthermore, the reporting department can also use AI to make emergency notifications. For example, the reporting department can use AI to analyze the situation in an emergency and notify the appropriate agencies and support organizations. This allows for a swift response by notifying the appropriate agencies and support organizations in times of emergency.

[0074] The voice dialogue unit utilizes speech recognition technology. For example, by using speech recognition technology, the voice dialogue unit allows trainees to make consultations and reports via voice. For instance, the voice dialogue unit uses a speech recognition algorithm to convert the trainee's voice into text and receive consultations and reports. Furthermore, the voice dialogue unit can also perform speech recognition using AI. For example, the voice dialogue unit uses AI to perform speech recognition and convert the trainee's voice into text. This allows trainees to make consultations and reports via voice using speech recognition technology.

[0075] The information acquisition unit utilizes two-dimensional codes (e.g., QR codes). By using two-dimensional codes, the information acquisition unit allows trainees to easily obtain information. For example, the information acquisition unit generates a two-dimensional code, which trainees can scan with their smartphones to acquire the information. Furthermore, the information acquisition unit can also analyze the information in the two-dimensional code using AI. For example, the information acquisition unit uses AI to analyze the information in the two-dimensional code and provides it to the trainees. This allows trainees to easily obtain information by utilizing two-dimensional codes.

[0076] The monitoring unit can monitor working conditions and the work environment in real time and issue immediate warnings if any abnormalities are detected. For example, if excessive working hours or an inappropriate work environment are detected, the monitoring unit will issue a warning and prompt appropriate countermeasures. The monitoring unit can also use AI to monitor the work environment. For example, the monitoring unit can use AI to analyze data on working conditions and the work environment and detect abnormalities. This allows for real-time monitoring of working conditions and the work environment, enabling immediate warnings if abnormalities are detected.

[0077] The reception desk functions as a 24 / 7 consultation service, allowing for immediate reporting of problems. For example, if an intern experiences unfair treatment, the reception desk will receive a consultation and immediately report the problem. Furthermore, the reception desk can utilize AI to handle consultations and reports. For example, the reception desk can use an AI chatbot to receive consultations from interns and report problems. This allows the reception desk to function as a 24 / 7 consultation service, enabling immediate reporting of problems.

[0078] The service provider can provide education and information on local labor laws and rights. For example, the service provider can provide trainees with information on labor laws and rights so that they understand their rights and are not subjected to unfair treatment. For example, the service provider can conduct lectures and workshops on labor laws and rights to educate trainees. The service provider can also use AI to provide education and information. For example, the service provider can use AI to automatically provide information on labor laws and rights to educate trainees. In this way, by providing education and information on local labor laws and rights, trainees can understand their rights and be prevented from being subjected to unfair treatment.

[0079] The monitoring unit can estimate the emotions of trainees and adjust the monitoring frequency based on the estimated emotions. For example, if a trainee is stressed, the monitoring unit can increase the monitoring frequency to detect abnormalities early. For example, if a trainee is relaxed, the monitoring unit can reduce the monitoring frequency to respect their privacy. Also, if a trainee is tired, the monitoring unit can appropriately adjust the monitoring frequency to avoid excessive burden. This allows for more appropriate monitoring by adjusting the monitoring frequency based on the trainee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using AI or not using AI. For example, the monitoring unit can input trainee emotion data into a generative AI and have the generative AI perform emotion estimation.

[0080] The monitoring unit can optimize its anomaly detection algorithm by referring to past anomaly data when monitoring the work environment. For example, the monitoring unit can analyze past anomaly data to improve the accuracy of the anomaly detection algorithm. For example, the monitoring unit can learn patterns in anomaly data to detect new anomalies early. The monitoring unit can also enhance anomaly detection in specific time periods or situations based on the anomaly data. This improves the accuracy of anomaly detection by optimizing the anomaly detection algorithm by referring to past anomaly data. Some or all of the above processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input past anomaly data into a generating AI and have the generating AI perform the optimization of the anomaly detection algorithm.

[0081] The monitoring unit can monitor the health status of trainees while monitoring the work environment and issue warnings if abnormalities are detected. For example, the monitoring unit can monitor trainees' heart rate and body temperature and issue warnings if abnormalities are detected. For example, the monitoring unit can monitor trainees' fatigue levels and issue warnings if there are signs of overwork. The monitoring unit can also periodically check the health status of trainees and take appropriate measures if abnormalities are detected. In this way, by monitoring the health status of trainees, warnings can be issued if abnormalities are detected. Some or all of the above processes in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input trainees' health data into a generating AI and have the generating AI perform abnormality detection.

[0082] The monitoring unit can estimate the emotions of trainees and determine the priority of warnings based on the estimated emotions. For example, if a trainee is feeling anxious, the monitoring unit will increase the priority of the warning and respond quickly. For example, if a trainee is relaxed, the monitoring unit will lower the priority of the warning to respect their privacy. Also, if a trainee is feeling angry, the monitoring unit will adjust the priority of the warning to take an appropriate action. This allows for a more appropriate response by determining the priority of warnings based on the trainee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the monitoring unit may be performed using AI or not using AI. For example, the monitoring unit can input trainee emotion data into a generative AI and have the generative AI determine the priority of warnings.

[0083] The monitoring unit can perform anomaly detection while monitoring the work environment, taking into account the geographical location information of the trainees. For example, if a trainee is in a specific area, the monitoring unit can perform anomaly detection based on the characteristics of that area. For example, the monitoring unit can analyze the trainees' movement patterns and issue a warning if there is any abnormal movement. Furthermore, if a trainee is in a dangerous area, the monitoring unit can increase the sensitivity of anomaly detection and respond quickly. This makes it possible to perform anomaly detection with higher accuracy by taking into account the geographical location information of the trainees. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without using AI. For example, the monitoring unit can input the trainees' geographical location data into a generating AI and have the generating AI perform anomaly detection.

[0084] The monitoring unit can analyze the social media activities of trainees when monitoring the work environment and detect relevant anomalies. For example, the monitoring unit can analyze trainees' social media posts to detect signs of stress or dissatisfaction. For example, the monitoring unit can detect abnormal behavioral patterns from trainees' social media activities. The monitoring unit can also analyze trainees' communication on social media to detect abnormal situations early. In this way, by analyzing trainees' social media activities, relevant anomalies can be detected early. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input trainees' social media data into a generating AI and have the generating AI perform anomaly detection.

[0085] The reception desk can estimate the intern's emotions and prioritize the content of their consultation based on those estimated emotions. For example, if the intern is feeling anxious, the reception desk will prioritize the consultation and respond quickly. For example, if the intern is relaxed, the reception desk will prioritize the consultation lower to respect their privacy. Also, if the intern is feeling angry, the reception desk will adjust the priority of the consultation to provide an appropriate response. This allows for more appropriate responses by prioritizing consultations based on the intern's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input the intern's emotion data into a generative AI and have the generative AI determine the priority of consultations.

[0086] The reception department can select the most appropriate response method by referring to past consultation history at the time of reception. For example, the reception department can analyze the intern's past consultation history and propose the most appropriate response method. For example, the reception department can select a response method for similar problems from past consultation history. The reception department can also provide individually customized response methods based on the intern's past consultation history. This makes it possible to provide more appropriate responses by selecting the most appropriate response method by referring to past consultation history. Some or all of the above processing in the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input past consultation history data into a generating AI and have the generating AI perform the selection of the most appropriate response method.

[0087] The reception department can customize its response method based on the trainee's current situation at the time of registration. For example, the reception department may propose the optimal response method considering the trainee's current work environment. For example, the reception department may select an appropriate response method considering the trainee's current health condition. The reception department may also customize the response method considering the trainee's current emotional state. This allows for more appropriate responses by customizing the response method based on the trainee's current situation. Some or all of the above processes at the reception department may be performed using AI, for example, or not using AI. For example, the reception department may input the trainee's current situation data into a generating AI and have the generating AI perform the customization of the response method.

[0088] The reception desk can estimate the intern's emotions and adjust the display method of the consultation content based on the estimated emotions. For example, if the intern is nervous, the reception desk provides a simple and highly visible display method. For example, if the intern is relaxed, the reception desk provides a display method that includes detailed information. The reception desk can also provide a concise display method if the intern is in a hurry. By adjusting the display method of the consultation content based on the intern's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the intern's emotion data into the generative AI and have the generative AI perform the adjustment of the display method.

[0089] The reception department can select the most appropriate response method at the time of registration, taking into account the trainee's geographical location information. For example, if the trainee is in a specific area, the reception department will select a response method based on the characteristics of that area. For example, the reception department may suggest the most suitable support organization based on the trainee's geographical location information. The reception department can also analyze the trainee's movement patterns and select an appropriate response method. By selecting the most appropriate response method while considering the trainee's geographical location information, a more appropriate response becomes possible. Some or all of the above processing at the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input the trainee's geographical location data into a generating AI and have the generating AI select a response method.

[0090] The reception department can analyze the intern's social media activity at the time of reception and prioritize the processing of relevant inquiries. For example, the reception department can analyze the intern's social media posts and prioritize the processing of urgent inquiries. For example, the reception department can extract relevant inquiries from the intern's social media activity and respond to them preferentially. The reception department can also analyze the intern's social media communications and prioritize the processing of important inquiries. In this way, by analyzing the intern's social media activity, relevant inquiries can be processed preferentially. Some or all of the above processing at the reception department may be performed using AI, for example, or not using AI. For example, the reception department can input the intern's social media data into a generating AI and have the generating AI perform the preferential processing of inquiries.

[0091] The service provider can estimate the emotions of trainees and prioritize educational content based on those estimated emotions. For example, if a trainee is feeling anxious, the service provider will prioritize educational content related to important rights. For example, if a trainee is relaxed, the service provider will provide detailed educational content. The service provider can also provide visually stimulating educational content if a trainee is excited. This allows for more appropriate education by prioritizing educational content based on the trainee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI or not. For example, the service provider can input trainee emotion data into a generative AI and have the generative AI determine the priority of educational content.

[0092] The service provider can select the optimal teaching method by referring to past teaching history during training. For example, the service provider can analyze a trainee's past teaching history and propose the optimal teaching method. For example, the service provider can select a teaching method suitable for a trainee based on their past teaching history. The service provider can also provide individually customized teaching methods based on a trainee's past teaching history. This makes it possible to provide more appropriate training by selecting the optimal teaching method by referring to past teaching history. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider can input past teaching history data into a generating AI and have the generating AI select the optimal teaching method.

[0093] The service provider can customize the educational content based on the trainee's current situation during training. For example, the service provider can provide optimal educational content considering the trainee's current work environment. For example, the service provider can select appropriate educational content considering the trainee's current health condition. The service provider can also customize the educational content considering the trainee's current emotional state. This allows for more appropriate training by customizing the educational content based on the trainee's current situation. Some or all of the above processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the trainee's current situation data into a generating AI and have the generating AI perform the customization of the educational content.

[0094] The service provider can estimate the trainee's emotions and adjust the display method of the educational content based on the estimated emotions. For example, if the trainee is nervous, the service provider can provide a simple and highly visible display method. For example, if the trainee is relaxed, the service provider can provide a display method that includes detailed information. Furthermore, if the trainee is in a hurry, the service provider can provide a display method that focuses on the key points. By adjusting the display method of the educational content based on the trainee's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input trainee emotion data into a generative AI and have the generative AI perform the adjustment of the display method.

[0095] The service provider can select the optimal teaching method during training by considering the geographical location information of the trainees. For example, if a trainee is in a specific area, the service provider can select a teaching method based on the characteristics of that area. For example, the service provider can suggest the most suitable educational institution based on the trainee's geographical location information. The service provider can also analyze the trainee's movement patterns and select an appropriate teaching method. By selecting the optimal teaching method while considering the trainee's geographical location information, more appropriate training becomes possible. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the trainee's geographical location data into a generating AI and have the generating AI perform the selection of the teaching method.

[0096] The service provider can analyze the social media activities of trainees during training and prioritize the provision of relevant educational content. For example, the service provider can analyze trainees' social media posts and prioritize the provision of urgent educational content. For example, the service provider can extract relevant educational content from trainees' social media activities and prioritize its provision. The service provider can also analyze trainees' social media communications and prioritize the provision of important educational content. In this way, by analyzing trainees' social media activities, relevant educational content can be prioritized. Some or all of the above processing in the service provider may be performed using AI, for example, or not using AI. For example, the service provider can input trainees' social media data into a generating AI and have the generating AI perform the priority provision of educational content.

[0097] The multilingual unit can estimate the trainee's emotions and determine language selection priorities based on the estimated emotions. For example, if the trainee is feeling anxious, the multilingual unit will prioritize their native language. For example, if the trainee is relaxed, the multilingual unit will select the language they are currently learning. The multilingual unit can also select the language that is easiest to understand if the trainee is in a hurry. This allows for more appropriate language selection by determining language selection priorities based on the trainee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the multilingual unit may be performed using AI or not. For example, the multilingual unit can input trainee emotion data into a generative AI and have the generative AI determine language selection priorities.

[0098] The multilingual unit can select the optimal language selection method by referring to past usage history when providing multilingual support. For example, the multilingual unit can analyze the trainee's past language usage history and suggest the most suitable language. For example, the multilingual unit can select the language that the trainee finds easiest to understand based on past usage history. The multilingual unit can also provide individually customized language selection methods based on the trainee's past language usage history. This allows for more appropriate language selection by referring to past usage history to select the optimal language selection method. Some or all of the above processing in the multilingual unit may be performed using AI, for example, or without AI. For example, the multilingual unit can input past usage history data into a generating AI and have the generating AI select the optimal language selection method.

[0099] The multilingual unit can estimate the emotions of trainees and adjust the language display method based on the estimated emotions. For example, if a trainee is nervous, the multilingual unit provides a simple and highly visible display method. For example, if a trainee is relaxed, the multilingual unit provides a display method that includes detailed information. Furthermore, if a trainee is in a hurry, the multilingual unit can provide a display method that gets straight to the point. By adjusting the language display method based on the trainee's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the multilingual unit may be performed using AI, for example, or not using AI. For example, the multilingual unit can input trainee emotion data into a generative AI and have the generative AI perform the adjustment of the display method.

[0100] The multilingual department can select the optimal language selection method when providing multilingual support, taking into account the geographical location information of the trainees. For example, if a trainee is in a specific area, the multilingual department will select a language selection method based on the characteristics of that area. For example, the multilingual department will propose the optimal language based on the trainee's geographical location information. The multilingual department can also analyze the trainee's movement patterns and select an appropriate language selection method. By selecting the optimal language selection method while considering the trainee's geographical location information, a more appropriate language selection becomes possible. Some or all of the above processing in the multilingual department may be performed using AI, for example, or without AI. For example, the multilingual department can input the trainee's geographical location data into a generating AI and have the generating AI perform the selection of the language selection method.

[0101] The reporting department can estimate the intern's emotions and prioritize reports based on those estimated emotions. For example, if an intern is feeling anxious, the reporting department will prioritize the report and respond quickly. For example, if an intern is relaxed, the reporting department will prioritize the report less to respect their privacy. Also, if an intern is feeling angry, the reporting department will adjust the priority of the report to take an appropriate action. This allows for more appropriate reporting by prioritizing reports based on the intern's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reporting department may be performed using AI or not. For example, the reporting department can input intern emotion data into a generative AI and have the generative AI determine the priority of reports.

[0102] The reporting department can select the most appropriate reporting method by referring to past reporting history when a report is made. For example, the reporting department can analyze an intern's past reporting history and propose the most appropriate reporting method. For example, the reporting department can select a reporting method for similar problems from past reporting history. The reporting department can also provide individually customized reporting methods based on an intern's past reporting history. This makes it possible to make more appropriate reports by selecting the most appropriate reporting method by referring to past reporting history. Some or all of the above processing in the reporting department may be performed using AI, for example, or not using AI. For example, the reporting department can input past reporting history data into a generating AI and have the generating AI select the most appropriate reporting method.

[0103] The reporting unit can estimate the intern's emotions and adjust how the report is displayed based on the estimated emotions. For example, if the intern is nervous, the reporting unit provides a simple and highly visible display method. For example, if the intern is relaxed, the reporting unit provides a display method that includes detailed information. The reporting unit can also provide a concise display method if the intern is in a hurry. By adjusting how the report is displayed based on the intern's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reporting unit may be performed using AI or not using AI. For example, the reporting unit can input the intern's emotion data into a generative AI and have the generative AI perform the adjustment of the display method.

[0104] The reporting department can select the most appropriate reporting method when a report is made, taking into account the trainee's geographical location. For example, if the trainee is in a specific area, the reporting department will select a reporting method based on the characteristics of that area. For example, the reporting department will propose the most appropriate reporting agency based on the trainee's geographical location. The reporting department can also analyze the trainee's movement patterns and select an appropriate reporting method. By selecting the most appropriate reporting method while considering the trainee's geographical location, more appropriate reporting becomes possible. Some or all of the above processing in the reporting department may be performed using AI, for example, or without AI. For example, the reporting department can input the trainee's geographical location data into a generating AI and have the generating AI perform the selection of the reporting method.

[0105] The voice dialogue unit can estimate the intern's emotions and determine the priority of voice dialogues based on the estimated emotions. For example, if the intern is feeling anxious, the voice dialogue unit will increase the priority of the voice dialogue and respond quickly. For example, if the intern is relaxed, the voice dialogue unit will lower the priority of the voice dialogue to respect privacy. Also, if the intern is feeling angry, the voice dialogue unit will adjust the priority of the voice dialogue to respond appropriately. This allows for more appropriate voice dialogues by determining the priority of voice dialogues based on the intern's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the voice dialogue unit may be performed using AI, for example, or not using AI. For example, the voice dialogue unit can input the intern's emotion data into the generative AI and have the generative AI determine the priority of voice dialogues.

[0106] The voice dialogue unit can select the optimal dialogue method by referring to past dialogue history during voice dialogue. For example, the voice dialogue unit can analyze the trainee's past dialogue history and propose the optimal dialogue method. For example, the voice dialogue unit can select a dialogue method for similar problems from past dialogue history. The voice dialogue unit can also provide individually customized dialogue methods based on the trainee's past dialogue history. This makes more appropriate voice dialogue possible by selecting the optimal dialogue method by referring to past dialogue history. Some or all of the above processing in the voice dialogue unit may be performed using AI, for example, or without AI. For example, the voice dialogue unit can input past dialogue history data into a generating AI and have the generating AI perform the selection of the optimal dialogue method.

[0107] The voice dialogue unit can estimate the trainee's emotions and adjust the display method of the voice dialogue based on the estimated emotions. For example, if the trainee is nervous, the voice dialogue unit provides a simple and highly visible display method. For example, if the trainee is relaxed, the voice dialogue unit provides a display method that includes detailed information. Furthermore, if the trainee is in a hurry, the voice dialogue unit can provide a display method that gets straight to the point. By adjusting the display method of the voice dialogue based on the trainee's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the voice dialogue unit may be performed using AI, for example, or not using AI. For example, the voice dialogue unit can input the trainee's emotion data into the generative AI and have the generative AI perform the adjustment of the display method.

[0108] The voice dialogue unit can select the optimal dialogue method during voice dialogue by considering the trainee's geographical location information. For example, if the trainee is in a specific area, the voice dialogue unit will select a dialogue method based on the characteristics of that area. For example, the voice dialogue unit will propose the optimal dialogue method based on the trainee's geographical location information. The voice dialogue unit can also analyze the trainee's movement patterns and select an appropriate dialogue method. By selecting the optimal dialogue method while considering the trainee's geographical location information, more appropriate voice dialogue becomes possible. Some or all of the above processing in the voice dialogue unit may be performed using AI, for example, or without AI. For example, the voice dialogue unit can input the trainee's geographical location data into a generating AI and have the generating AI perform the selection of the dialogue method.

[0109] The information acquisition unit can estimate the trainee's emotions and determine the priority of information acquisition based on the estimated emotions. For example, if the trainee is feeling anxious, the information acquisition unit will prioritize acquiring important information. For example, if the trainee is relaxed, the information acquisition unit will prioritize acquiring detailed information. Also, if the trainee is in a hurry, the information acquisition unit can prioritize acquiring concise information. This makes it possible to acquire more appropriate information by determining the priority of information acquisition based on the trainee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the information acquisition unit may be performed using AI, for example, or without AI. For example, the information acquisition unit can input the trainee's emotion data into the generative AI and have the generative AI determine the priority of information acquisition.

[0110] The information acquisition unit can select the optimal acquisition method by referring to past acquisition history when acquiring information. For example, the information acquisition unit can analyze the trainee's past information acquisition history and propose the optimal acquisition method. For example, the information acquisition unit can select an information acquisition method suitable for the trainee from past acquisition history. The information acquisition unit can also provide individually customized information acquisition methods based on the trainee's past information acquisition history. This makes it possible to acquire more appropriate information by selecting the optimal acquisition method by referring to past acquisition history. Some or all of the above processing in the information acquisition unit may be performed using AI, for example, or without using AI. For example, the information acquisition unit can input past acquisition history data into a generating AI and have the generating AI select the optimal acquisition method.

[0111] The information acquisition unit can estimate the trainee's emotions and adjust the display method of the acquired information based on the estimated emotions. For example, if the trainee is nervous, the information acquisition unit provides a simple and highly visible display method. For example, if the trainee is relaxed, the information acquisition unit provides a display method that includes detailed information. Furthermore, if the trainee is in a hurry, the information acquisition unit can also provide a display method that gets straight to the point. By adjusting the display method of acquired information based on the trainee's emotions, a more appropriate display becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the information acquisition unit may be performed using AI, for example, or not using AI. For example, the information acquisition unit can input the trainee's emotion data into the generative AI and have the generative AI perform the adjustment of the display method.

[0112] The information acquisition unit can select the optimal acquisition method when acquiring information, taking into account the trainee's geographical location information. For example, if the trainee is in a specific area, the information acquisition unit will select an information acquisition method based on the characteristics of that area. For example, the information acquisition unit will propose the optimal information acquisition method based on the trainee's geographical location information. The information acquisition unit can also analyze the trainee's movement patterns and select an appropriate information acquisition method. By selecting the optimal acquisition method while considering the trainee's geographical location information, more appropriate information acquisition becomes possible. Some or all of the above processing in the information acquisition unit may be performed using AI, for example, or without AI. For example, the information acquisition unit can input the trainee's geographical location data into a generating AI and have the generating AI select the acquisition method.

[0113] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0114] In addition to monitoring the working environment, the monitoring department can also monitor the health of the trainees. For example, it can monitor the trainees' heart rate and body temperature in real time and issue an immediate warning if an abnormality is detected. It can also monitor the trainees' fatigue levels and issue a warning if there are signs of overwork. Furthermore, it can periodically check the trainees' health and take appropriate measures if any abnormalities are found. In this way, by monitoring the trainees' health, a warning can be issued if any abnormalities are detected.

[0115] The multilingual department can estimate the trainee's emotions and determine language selection priorities based on those estimates. For example, if a trainee is feeling anxious, their native language will be prioritized. If the trainee is relaxed, the language they are currently learning will be selected. Furthermore, if the trainee is in a hurry, the easiest language to understand may be chosen. This allows for more appropriate language selection by prioritizing language choices based on the trainee's emotions.

[0116] The reporting department can not only report to the appropriate agencies and support groups in emergencies, but also estimate the trainee's emotions and prioritize reports based on those estimates. For example, if a trainee is feeling anxious, the report will be given a higher priority and a quicker response will be made. If a trainee is relaxed, the report will be given a lower priority to respect their privacy. Also, if a trainee is feeling angry, the priority of the report will be adjusted to ensure an appropriate response. By prioritizing reports based on the trainee's emotions, more appropriate reports can be made.

[0117] The voice dialogue unit not only uses speech recognition technology but can also estimate the trainee's emotions and determine the priority of voice dialogue based on those estimated emotions. For example, if the trainee is feeling anxious, the voice dialogue priority is increased to provide a quick response. If the trainee is relaxed, the voice dialogue priority is lowered to respect their privacy. Furthermore, if the trainee is feeling angry, the voice dialogue priority is adjusted to provide an appropriate response. In this way, determining the priority of voice dialogue based on the trainee's emotions enables more appropriate voice dialogue.

[0118] The information retrieval unit not only utilizes 2D codes but can also estimate the trainee's emotions and determine the priority of information retrieval based on those emotions. For example, if the trainee is feeling anxious, it will prioritize retrieving important information. If the trainee is relaxed, it will prioritize retrieving detailed information. Furthermore, if the trainee is in a hurry, it can prioritize retrieving concise information. By determining the priority of information retrieval based on the trainee's emotions, it becomes possible to obtain more appropriate information.

[0119] In addition to monitoring the work environment, the monitoring unit can perform anomaly detection by considering the geographical location of the trainees. For example, if a trainee is in a specific area, anomaly detection will be performed based on the characteristics of that area. The trainees' movement patterns will be analyzed, and a warning will be issued if any abnormal movement is detected. Furthermore, if a trainee is in a dangerous area, the sensitivity of anomaly detection can be increased to allow for a quicker response. By considering the geographical location of the trainees when performing anomaly detection, more accurate anomaly detection becomes possible.

[0120] The reception desk not only functions as a 24 / 7 consultation service, but can also customize its response based on the trainee's current situation. For example, it can propose the most suitable response considering the trainee's current work environment, select an appropriate response considering the trainee's current health condition, and even customize the response based on the trainee's current emotional state. This allows for more appropriate responses by customizing the response based on the trainee's current situation.

[0121] The training department not only provides education and information on local labor laws and rights, but can also estimate the trainees' emotions and prioritize educational content based on those emotions. For example, if a trainee is feeling anxious, they will be given priority in receiving education on important rights. If a trainee is relaxed, they will receive detailed educational content. If a trainee is excited, they may also receive visually stimulating educational content. By prioritizing educational content based on the trainees' emotions, more appropriate education becomes possible.

[0122] The multilingual section not only has multilingual support capabilities, but can also estimate the emotions of trainees and adjust the language display method based on those estimates. For example, if a trainee is nervous, it provides a simple and highly visible display method. If a trainee is relaxed, it provides a display method that includes detailed information. It can also provide a concise display method if a trainee is in a hurry. In this way, by adjusting the language display method based on the trainee's emotions, more appropriate displays become possible.

[0123] The reporting department can not only report to the appropriate agencies and support groups in emergencies, but can also select the most suitable reporting method by referring to past reporting history. For example, it can analyze an intern's past reporting history and propose the most suitable reporting method. It can also select a reporting method for similar problems based on past reporting history. Furthermore, it can provide individually customized reporting methods based on an intern's past reporting history. This allows for more appropriate reporting by selecting the most suitable reporting method by referring to past reporting history.

[0124] The following briefly describes the processing flow for example form 2.

[0125] Step 1: The monitoring unit monitors the work environment. For example, it monitors working conditions and the work environment in real time and issues an immediate warning if an abnormality is detected. If excessive working hours or an inappropriate work environment are detected, it issues a warning and prompts appropriate countermeasures. The monitoring unit can also use AI to monitor the work environment. Using AI, it can analyze data on working conditions and the work environment and detect abnormalities. Step 2: The reception desk receives consultations and reports. For example, it functions as a 24 / 7 consultation hotline and reports problems immediately. If an intern is treated unfairly, the reception desk will receive a consultation and report the problem immediately. The reception desk can also use AI to receive consultations and reports. An AI chatbot can be used to receive consultations from interns and report problems. Step 3: The service provider will provide education and information on local labor laws and rights. For example, they will provide trainees with information on labor laws and rights so that they understand their rights and are not subjected to unfair treatment. They will also conduct lectures and workshops on labor laws and rights to educate trainees. The service provider can also use AI to provide education and information. AI can be used to automatically provide information on labor laws and rights and educate trainees.

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0127] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0128] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0129] Each of the multiple elements described above, including the monitoring unit, reception unit, provision unit, multilingual unit, reporting unit, voice dialogue unit, and information acquisition unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the monitoring unit monitors the work environment using the camera 42 and sensors of the smart device 14 and detects abnormalities using the specific processing unit 290 of the data processing unit 12. The reception unit functions as a 24 / 7 consultation service using the control unit 46A of the smart device 14 and reports problems immediately. The provision unit provides information and education on labor laws and rights using the specific processing unit 290 of the data processing unit 12. The multilingual unit supports multiple languages ​​using the control unit 46A of the smart device 14 and performs automatic translation using AI. The reporting unit notifies appropriate agencies and support organizations in emergencies using the specific processing unit 290 of the data processing unit 12. The voice dialogue unit performs voice recognition using the microphone 38B of the smart device 14 and accepts consultations and reports. The information acquisition unit scans the two-dimensional code using the camera 42 of the smart device 14, and the specific processing unit 290 of the data processing device 12 analyzes the information. The correspondence between each unit and the device and control unit is not limited to the example described above, and various changes are possible.

[0130] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0131] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0132] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0133] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0134] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0136] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0137] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0138] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0139] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0140] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0141] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0142] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0143] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0144] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0145] Each of the multiple elements described above, including the monitoring unit, reception unit, provision unit, multilingual unit, reporting unit, voice dialogue unit, and information acquisition unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the monitoring unit monitors the work environment using the camera 42 and sensors of the smart glasses 214 and detects abnormalities using the specific processing unit 290 of the data processing unit 12. The reception unit functions as a 24 / 7 consultation service using the control unit 46A of the smart glasses 214 and reports problems immediately. The provision unit provides information and education on labor laws and rights using the specific processing unit 290 of the data processing unit 12. The multilingual unit supports multiple languages ​​using the control unit 46A of the smart glasses 214 and performs automatic translation using AI. The reporting unit notifies appropriate agencies and support organizations in emergencies using the specific processing unit 290 of the data processing unit 12. The voice dialogue unit performs voice recognition using the microphone 238 of the smart glasses 214 and accepts consultations and reports. The information acquisition unit scans the 2D code using the camera 42 of the smart glasses 214, and the information is analyzed by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device and control unit is not limited to the example described above, and various modifications are possible.

[0146] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0147] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0148] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0149] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0150] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0152] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0153] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0154] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0155] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0156] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0157] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0158] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0159] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0160] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0161] Each of the multiple elements described above, including the monitoring unit, reception unit, provision unit, multilingual unit, notification unit, voice dialogue unit, and information acquisition unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the monitoring unit monitors the work environment using the camera 42 and sensors of the headset terminal 314 and detects abnormalities using the specific processing unit 290 of the data processing unit 12. The reception unit functions as a 24 / 7 consultation service using the control unit 46A of the headset terminal 314 and immediately reports problems. The provision unit provides information and education on labor laws and rights using the specific processing unit 290 of the data processing unit 12. The multilingual unit supports multiple languages ​​using the control unit 46A of the headset terminal 314 and performs automatic translation using AI. The notification unit notifies appropriate agencies and support organizations in emergencies using the specific processing unit 290 of the data processing unit 12. The voice dialogue unit performs voice recognition using the microphone 238 of the headset terminal 314 and accepts consultations and reports. The information acquisition unit scans the two-dimensional code using the camera 42 of the headset terminal 314, and the information is analyzed by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device and control unit is not limited to the example described above, and various modifications are possible.

[0162] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0163] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0164] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0165] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0166] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0167] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0168] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0169] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0170] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0173] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0174] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0175] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0176] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0177] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0178] Each of the multiple elements described above, including the monitoring unit, reception unit, provision unit, multilingual unit, reporting unit, voice dialogue unit, and information acquisition unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the monitoring unit monitors the work environment using the camera 42 and sensors of the robot 414 and detects abnormalities using the specific processing unit 290 of the data processing unit 12. The reception unit functions as a 24 / 7 consultation service using the control unit 46A of the robot 414 and reports problems immediately. The provision unit provides information and education on labor laws and rights using the specific processing unit 290 of the data processing unit 12. The multilingual unit supports multiple languages ​​using the control unit 46A of the robot 414 and performs automatic translation using AI. The reporting unit notifies appropriate agencies and support organizations in emergencies using the specific processing unit 290 of the data processing unit 12. The voice dialogue unit performs voice recognition using the microphone 238 of the robot 414 and accepts consultations and reports. The information acquisition unit scans the 2D code using the camera 42 of the robot 414, and the information is analyzed by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device and control unit is not limited to the example described above, and various modifications are possible.

[0179] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0180] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0181] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0182] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0183] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0184] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0185] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0186] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0187] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0188] 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.

[0189] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0190] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0191] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0192] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0193] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0194] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0195] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0196] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0197] (Note 1) The monitoring department that oversees the working environment, A reception desk that accepts consultations and reports, It includes a department that provides education and information on local labor laws and rights. A system characterized by the following features. (Note 2) It has a multilingual section with multilingual support capabilities. The system described in Appendix 1, characterized by the features described herein. (Note 3) It has a reporting department that contacts the appropriate agencies and support organizations in case of an emergency. The system described in Appendix 1, characterized by the features described herein. (Note 4) It is equipped with a voice dialogue unit that uses speech recognition technology. The system described in Appendix 1, characterized by the features described herein. (Note 5) It is equipped with an information acquisition unit that utilizes 2D codes. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned monitoring unit, It monitors working conditions and the work environment in real time and issues an immediate warning if any abnormalities are detected. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is It functions as a 24 / 7 consultation service and allows for immediate reporting of problems. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned supply unit is, Provide education and information on local labor laws and rights. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned monitoring unit, The system estimates the trainee's emotions and adjusts the frequency of monitoring based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned monitoring unit, When monitoring the work environment, the anomaly detection algorithm is optimized by referring to past anomaly data. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned monitoring unit, During monitoring of the work environment, the health status of trainees will be monitored, and warnings will be issued if any abnormalities are found. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned monitoring unit, The system estimates the trainee's emotions and determines the priority of warnings based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned monitoring unit, When monitoring the work environment, anomaly detection is performed while taking into account the geographical location information of the trainees. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned monitoring unit, During monitoring of the work environment, the social media activity of trainees is analyzed to detect any related anomalies. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned reception unit is We estimate the intern's emotions and prioritize the topics of consultation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned reception unit is Upon receiving a request, the most appropriate course of action will be selected by referring to past consultation history. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned reception unit is At the time of registration, the response method will be customized based on the intern's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned reception unit is The system estimates the intern's emotions and adjusts how the consultation content is displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned reception unit is At the time of registration, the most appropriate response method will be selected considering the geographical location information of the trainee. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned reception unit is Upon receiving an intern's application, we analyze their social media activity and prioritize processing related inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, The system estimates the trainees' emotions and prioritizes the educational content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, During education, the optimal teaching method is selected by referring to past educational records. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, During training, customize the curriculum based on the trainee's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, The system estimates the trainees' emotions and adjusts the way educational content is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, During training, the most suitable teaching method will be selected considering the geographical location of the trainees. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, During training, we analyze the social media activities of trainees and prioritize providing relevant educational content. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned multilingual unit is The system estimates the interns' emotions and determines language selection priorities based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned multilingual unit is When implementing multilingual support, the system selects the optimal language method by referring to past usage history. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned multilingual unit is The system estimates the trainee's emotions and adjusts the language display method based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned multilingual unit is When providing multilingual support, the optimal language selection method is chosen considering the geographical location information of the trainees. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned reporting unit, The system estimates the trainee's emotions and prioritizes the content of reports based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned reporting unit, When a report is made, the system will refer to past reporting history to select the most appropriate reporting method. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned reporting unit, The system estimates the trainee's emotions and adjusts how the report content is displayed based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned reporting unit, When reporting a problem, the most appropriate reporting method will be selected, taking into account the trainee's geographical location. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned voice dialogue unit is The system estimates the trainee's emotions and determines the priority of voice dialogues based on the estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 36) The aforementioned voice dialogue unit is During voice interaction, the system selects the optimal interaction method by referring to past conversation history. The system described in Appendix 4, characterized by the features described herein. (Note 37) The aforementioned voice dialogue unit is The system estimates the trainee's emotions and adjusts the display method of the voice dialogue based on the estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 38) The aforementioned voice dialogue unit is During voice dialogue, the system selects the optimal dialogue method while considering the trainee's geographical location. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned information acquisition unit, The system estimates the emotions of the trainees and determines the priority of information acquisition based on the estimated emotions of the trainees. The system described in Appendix 5, characterized by the features described herein. (Note 40) The aforementioned information acquisition unit, When acquiring information, the system selects the optimal acquisition method by referring to past acquisition history. The system described in Appendix 5, characterized by the features described herein. (Note 41) The aforementioned information acquisition unit, The system estimates the trainees' emotions and adjusts the display method of information acquisition based on the estimated emotions of the trainees. The system described in Appendix 5, characterized by the features described herein. (Note 42) The aforementioned information acquisition unit, When acquiring information, the most suitable acquisition method will be selected, taking into account the geographical location of the trainees. The system described in Appendix 5, characterized by the features described herein. [Explanation of symbols]

[0198] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The monitoring department that oversees the working environment, A reception desk that accepts consultations and reports, It includes a department that provides education and information on local labor laws and rights. A system characterized by the following features.

2. It has a multilingual section with multilingual support capabilities. The system according to feature 1.

3. It has a reporting department that contacts the appropriate agencies and support organizations in case of an emergency. The system according to feature 1.

4. It is equipped with a voice dialogue unit that uses speech recognition technology. The system according to feature 1.

5. It is equipped with an information acquisition unit that utilizes 2D codes. The system according to feature 1.

6. The aforementioned monitoring unit, It monitors working conditions and the work environment in real time and issues an immediate warning if any abnormalities are detected. The system according to feature 1.

7. The aforementioned reception unit is It functions as a 24 / 7 consultation service and allows for immediate reporting of problems. The system according to feature 1.

8. The aforementioned supply unit is, Provide education and information on local labor laws and rights. The system according to feature 1.

9. The aforementioned monitoring unit, The system estimates the trainee's emotions and adjusts the frequency of monitoring based on the estimated emotions. The system according to feature 1.

Images