system

Abstract

The system according to this embodiment aims to appropriately understand the physical and mental condition of employees and to respond promptly. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a scoring unit, an alert unit, and a provision unit. The reception unit receives the content of the employee's consultation. The analysis unit analyzes the content of the consultation received by the reception unit. The scoring unit scores the mental and physical state based on the content of the consultation analyzed by the analysis unit. The alert unit automatically generates an alert if the score is low, as determined by the scoring unit. The provision unit provides information to the human resources unit based on the alert generated by the alert unit.

Description

Technical Field

[0004] ,

[0006] , , , ,

[0005] , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to appropriately grasp the physical and mental state of employees and respond promptly.

[0005] The system according to the embodiment aims to appropriately grasp the physical and mental state of employees and respond promptly.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a scoring unit, an alert unit, and a provision unit. The reception unit receives the content of an employee's consultation. The analysis unit analyzes the content of the consultation received by the reception unit. The scoring unit scores the mental and physical state based on the content of the consultation analyzed by the analysis unit. The alert unit automatically generates an alert if the score is low, as determined by the scoring unit. The provision unit provides information to the human resources unit based on the alert generated by the alert unit. [Effects of the Invention]

[0007] The system according to this embodiment can appropriately grasp the physical and mental state of employees and respond quickly. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An AI workplace consultation concierge according to an embodiment of the present invention is an AI-based consultation platform that allows employees to anonymously consult about the workplace environment, supervisors, colleagues, job content, health, future career, etc. The AI ​​workplace consultation concierge scores the mental and physical state of employees and automatically generates an alert if the score is low, enabling the human resources department to take appropriate follow-up action. Because an AI acts as the consultant, employees are more likely to express their true feelings, and the human resources department can more easily grasp the genuine voices of employees. For example, by providing an environment where employees can consult anonymously, employees can consult with peace of mind. In addition, by scoring the mental and physical health state and automatically generating an alert if the score is low, the human resources department can respond quickly. This supports the mental and physical health of employees and contributes to improving the workplace environment. As a result, the AI ​​workplace consultation concierge can efficiently receive and analyze employee consultations, score their mental and physical state, generate alerts, and provide information to the human resources department.

[0029] The AI ​​workplace consultation concierge according to this embodiment comprises a reception unit, an analysis unit, a scoring unit, an alert unit, and a provision unit. The reception unit receives consultation content from employees. Employee consultation content includes, but is not limited to, work-related consultations, health-related consultations, and personal problems. The reception unit provides, for example, an interface for employees to make anonymous consultations. The reception unit may also provide a form or chatbot for employees to input consultation content. Furthermore, the reception unit may include a function that allows employees to make consultations via voice input or video call. For example, the reception unit provides a web interface for employees to make anonymous consultations and displays a form for employees to input consultation content. A chatbot provides an interactive interface for employees to make consultations in real time. The function of making consultations via voice input or video call provides a means for employees to make consultations more directly. The analysis unit analyzes the consultation content received by the reception unit. Analysis is performed by, for example, text analysis, sentiment analysis, pattern recognition, etc., but is not limited to these methods. For example, the analysis unit extracts keywords from the consultation content using text analysis and identifies the category of the consultation content. The analysis unit can also identify the emotions contained in the consultation content using sentiment analysis. Furthermore, the analysis unit can identify similar consultation content by comparing it with past consultation data using pattern recognition. For example, the analysis unit extracts keywords from the consultation content using text analysis and identifies the category of the consultation content. Sentiment analysis identifies the emotions contained in the consultation content and provides information for evaluating the employee's mental and physical state. Pattern recognition performs a more accurate analysis by comparing it with past consultation data and identifying similar consultation content. The scoring unit scores the mental and physical state based on the consultation content analyzed by the analysis unit. Scoring is performed based on, for example, a range of scores, evaluation criteria, and the algorithm used, but is not limited to such examples. For example, the scoring unit scores the employee's mental and physical state on a scale from 0 to 100. The scoring unit can also score the employee's mental and physical state on a scale from A to F.Furthermore, the scoring unit can also score employees' mental and physical health using percentiles. For example, the scoring unit can score employees' mental and physical health on a scale from 0 to 100 and generate an alert if the score is low. The A to F rating is used as a means of concisely evaluating employees' mental and physical health. Percentiles are used as an indicator to evaluate employees' mental and physical health in comparison to other employees. The alert unit automatically generates an alert when the scoring unit generates a low score. Alerts are generated based on, but are not limited to, the score threshold, notification method, and alert type. For example, the alert unit generates an alert if the score is below 50. The alert unit can also generate an emergency alert if the score is below 30. Furthermore, the alert unit can also generate a caution alert if the score is below 70. For example, the alert unit generates an alert and notifies the HR department if the score is below 50. An emergency alert is generated when the score is below 30 and is used when immediate action is required. A caution alert is generated when the score is below 70 and is used when caution is required. The service provider provides information to the human resources department based on alerts generated by the alert provider. This information may include, but is not limited to, the format of reports, notification methods, and the types of information provided. For example, the service provider may notify the human resources department via email when an alert occurs. The service provider may also automatically generate and provide a report containing details of the alert. Furthermore, the service provider may display the alert status on a dashboard, allowing the human resources department to understand the situation in real time. For example, the service provider may notify the human resources department via email when an alert occurs and automatically generate a report containing details of the alert. The dashboard displays the alert status in real time and is used as a tool to enable the human resources department to respond quickly. This allows the AI ​​workplace consultation concierge according to the embodiment to efficiently receive and analyze employee consultations, score their mental and physical state, generate alerts, and provide information to the human resources department.

[0030] The reception desk receives inquiries from employees. These inquiries may include, but are not limited to, work-related questions, health-related questions, or personal issues. The reception desk may provide an interface for employees to make anonymous inquiries. It may also provide forms or chatbots for employees to input their inquiries. Furthermore, the reception desk may include features that allow employees to make inquiries via voice input or video calls. For example, the reception desk may provide a web interface for employees to make anonymous inquiries and display a form for employees to input their inquiries. A chatbot may provide an interactive interface for employees to make real-time inquiries. Features that allow employees to make inquiries via voice input or video calls provide a means for employees to make inquiries more directly. To ensure a safe environment for employees to make inquiries, the reception desk implements encryption technology for privacy protection. For example, inquiries are encrypted using the SSL / TLS protocol to prevent unauthorized access by third parties. The reception desk also provides a function for employees to record their inquiries for later reference. This allows employees to review past inquiries and make additional inquiries as needed. Furthermore, the reception area will provide a multilingual interface, enabling employees who speak different languages ​​to seek advice smoothly. For example, consultations will be available in multiple languages, such as English, Japanese, and Spanish, catering to the diverse needs of employees. This allows the reception area to provide an environment where employees can feel comfortable seeking advice and to efficiently process inquiries.

[0031] The analysis unit analyzes the consultation content received by the reception unit. Analysis is performed using methods such as text analysis, sentiment analysis, and pattern recognition, but is not limited to these examples. For instance, the analysis unit can use text analysis to extract keywords from the consultation content and identify its category. It can also use sentiment analysis to identify the emotions contained in the consultation content. Furthermore, it can use pattern recognition to compare the current consultation with past consultation data and identify similar consultations. For example, the analysis unit can use text analysis to extract keywords from the consultation content and identify its category. Sentiment analysis identifies the emotions contained in the consultation content and provides information for evaluating the employee's mental and physical state. Pattern recognition allows for more accurate analysis by comparing the current consultation with past consultation data and identifying similar consultations. The analysis unit utilizes natural language processing (NLP) technology to understand the context of the consultation content and perform more detailed analysis. For example, NLP technology is used to analyze the context of the consultation content and identify the root cause of the employee's problem. Furthermore, the analysis unit can use machine learning algorithms to learn patterns in consultation content and predict future consultation content. This allows the analysis unit to quickly and accurately analyze employee consultation content and provide information for evaluating employees' mental and physical health. In addition, the analysis unit can leverage high-performance computing resources for real-time analysis, enabling rapid response. For example, it can use a cloud-based analysis platform to quickly process large amounts of data and provide real-time analysis results. This allows the analysis unit to quickly and accurately analyze employee consultation content and provide information for evaluating employees' mental and physical health.

[0032] The scoring unit scores the mental and physical state of an employee based on the consultation content analyzed by the analysis unit. Scoring is performed based on, for example, a score range, evaluation criteria, and the algorithm used, but is not limited to these examples. For example, the scoring unit scores an employee's mental and physical state on a scale from 0 to 100. The scoring unit can also score an employee's mental and physical state using a rating system from A to F. Furthermore, the scoring unit can score an employee's mental and physical state using percentiles. For example, the scoring unit scores an employee's mental and physical state on a scale from 0 to 100 and generates an alert if the score is low. The A to F rating system is used as a means of concisely evaluating an employee's mental and physical state. Percentiles are used as an indicator to evaluate an employee's mental and physical state in comparison to other employees. The scoring unit uses machine learning algorithms to build a model for scoring employees' mental and physical states. For example, it trains a model to predict an employee's mental and physical state using past consultation data and then scores new consultation content. Furthermore, the scoring unit can calculate an overall score by combining multiple indicators to evaluate an employee's mental and physical state. For example, it can comprehensively evaluate an employee's mental and physical state by combining the results of emotion analysis, the category of the consultation content, and past consultation history. In addition, the scoring unit can visualize the scoring results, allowing for an intuitive understanding of changes in an employee's mental and physical state. For example, the scoring results can be displayed in graphs or charts, allowing for a visual confirmation of changes in an employee's mental and physical state. This enables the scoring unit to accurately evaluate an employee's mental and physical state and provide information for taking appropriate action.

[0033] The alerting unit automatically generates an alert when the scoring unit generates a low score. Alerts are generated based on, but are not limited to, a score threshold, notification method, and alert type. For example, the alerting unit might generate an alert if the score is below 50. It can also generate an emergency alert if the score is below 30. Furthermore, it can generate a cautionary alert if the score is below 70. For example, the alerting unit might generate an alert and notify the HR department if the score is below 50. An emergency alert is generated when the score is below 30 and is used when immediate action is required. A cautionary alert is generated when the score is below 70 and is used when attention is needed. The alerting unit uses multiple notification methods to ensure rapid and reliable alert generation. For example, it might combine email, SMS, and push notifications to ensure alerts are delivered reliably. The alerting unit can also provide detailed alert content, indicating specific actions that need to be taken. For example, alert content might include a detailed assessment of the employee's physical and mental condition and recommended actions. Furthermore, the alerting unit records the history of alerts for later reference. This allows for reviewing past alert occurrences and evaluating the effectiveness of responses. The alert unit can also analyze the frequency and content of alerts to help improve the system. For example, it can analyze alert patterns and predict alert occurrences under specific conditions. This enables the alert unit to quickly understand the physical and mental state of employees and provide information to take appropriate action.

[0034] The Service Provider provides information to the Human Resources Department based on alerts generated by the Alerts Department. This information may include, but is not limited to, the format of reports, notification methods, and the types of information provided. For example, the Service Provider may notify the Human Resources Department via email when an alert occurs. The Service Provider may also automatically generate and provide reports containing details of the alerts. Furthermore, the Service Provider may display alert status on a dashboard, allowing the Human Resources Department to stay informed in real time. For example, the Service Provider may notify the Human Resources Department via email when an alert occurs and automatically generate reports containing details of the alerts. The dashboard is used as a tool to display alert status in real time, enabling the Human Resources Department to respond quickly. The Service Provider can provide detailed information about the alerts, indicating specific actions required. For example, alert content may include detailed assessments of employees' physical and mental health and recommended actions. Additionally, the Service Provider records the history of alerts for later reference. This allows for reviewing past alert occurrences and evaluating the effectiveness of responses. The Service Provider can also analyze the frequency and content of alerts to help improve the system. For example, by analyzing alert patterns, it's possible to predict when alerts will occur under specific conditions. This allows the service provider to quickly understand the physical and mental state of employees and provide information to take appropriate action.

[0035] The analysis unit includes a learning unit that learns from past consultation data. The learning unit learns from past consultation data using, for example, a machine learning algorithm. For example, the learning unit learns patterns in consultation content using past consultation data to improve the accuracy of the analysis. The learning unit can also learn based on the type of dataset. For example, the learning unit learns using different types of datasets, such as consultation data related to work, consultation data related to health, and consultation data related to personal problems. Furthermore, the learning unit can adjust the frequency of learning. For example, the learning unit periodically learns from past consultation data and updates the analysis algorithm. This improves the accuracy of the analysis by learning from past consultation data. Some or all of the above processes in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can input past consultation data into a generating AI and have the generating AI perform learning of patterns in consultation content.

[0036] The analysis unit includes an analysis unit that statistically analyzes employees' health status and consultation content. The analysis unit analyzes employees' health status and consultation content using the statistical methods it employs. For example, the analysis unit uses regression analysis to analyze the relationship between employees' health status and consultation content. The analysis unit can also group employees' consultation content using cluster analysis. Furthermore, the analysis unit can track changes in employees' health status using time series analysis. For example, the analysis unit uses regression analysis to analyze the relationship between employees' health status and consultation content and evaluate the impact of health deterioration on consultation content. Cluster analysis is used to group employees' consultation content and identify common problems. Time series analysis is used to track changes in employees' health status and grasp long-term trends. This allows for an understanding of the overall health of the company by statistically analyzing employees' health status and consultation content. Some or all of the above processes in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input employee health status and consultation content data into a generating AI and have the generating AI perform the statistical analysis.

[0037] The service unit includes a support unit that analyzes employee consultation trends and provides preventative support. The support unit, for example, performs frequency analysis to analyze employee consultation trends. For example, the support unit analyzes the frequency of employee consultations and evaluates whether a particular problem occurs frequently. The support unit can also use trend analysis to grasp trends in employee consultations. Furthermore, the support unit can use pattern recognition to identify commonalities in employee consultations. For example, the support unit uses frequency analysis to analyze the frequency of employee consultations and evaluates whether a particular problem occurs frequently. Trend analysis is used to grasp trends in employee consultations and predict future problems. Pattern recognition is used to identify commonalities in employee consultations and provide preventative support. This allows for supporting employee health by analyzing employee consultation trends and providing preventative support. Some or all of the above processes in the support unit may be performed using AI, for example, or not using AI. For example, the support unit can input employee consultation data into a generating AI and have the generating AI perform a consultation trend analysis.

[0038] The reception department analyzes the employee's past consultation history and selects the most suitable consultation method. For example, the reception department prioritizes suggesting consultation methods (chat, voice, etc.) that the employee has used in the past. For example, the reception department stores the employee's past consultation history in a database and analyzes past consultation methods. The reception department can also automatically suggest relevant topics based on the content of the employee's past consultations. For example, the reception department analyzes the content of the employee's past consultations and extracts relevant topics. Furthermore, the reception department can prompt the employee for consultation at the appropriate time based on the employee's past consultation frequency. For example, the reception department analyzes the employee's past consultation frequency and sends reminders at the appropriate time. This allows the reception department to select the most suitable consultation method by analyzing the employee's past consultation history. Some or all of the above processes in the reception department may be performed using AI, or not. For example, the reception department can input the employee's past consultation history into a generating AI and have the generating AI select the most suitable consultation method.

[0039] The reception desk filters incoming consultations based on the employee's current work situation and areas of interest. For example, the reception desk prioritizes receiving consultations based on the employee's current project status. For example, the reception desk stores the employee's current project status in a database and extracts relevant consultations. The reception desk can also suggest appropriate consultation topics based on the employee's areas of interest. For example, the reception desk analyzes the employee's areas of interest and extracts relevant consultation topics. Furthermore, the reception desk can filter specific consultations based on the employee's work environment. For example, the reception desk stores the employee's work environment in a database and extracts relevant consultations. This allows the reception desk to prioritize receiving relevant consultations by filtering based on the employee's current work situation and areas of interest. 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 data on the employee's current work situation and areas of interest into a generating AI and have the generating AI perform the filtering.

[0040] The reception desk prioritizes receiving inquiries based on the employee's geographical location information. For example, if an employee is in a specific office, the reception desk will prioritize inquiries related to that office. For example, the reception desk may obtain the employee's geographical location information using GPS data and extract relevant inquiries. The reception desk can also prioritize inquiries related to remote work if the employee is working remotely. For example, the reception desk may obtain the employee's geographical location information using location services and extract relevant inquiries. Furthermore, if an employee is on a business trip, the reception desk may prioritize inquiries related to the business trip destination. For example, the reception desk may store the employee's geographical location information in a database and extract relevant inquiries. This allows for more appropriate inquiries to be received by prioritizing inquiries based on the employee's geographical location information. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input employees' geographical location information into a generating AI and have the AI ​​extract highly relevant inquiries.

[0041] The reception department analyzes employees' social media activity when receiving inquiries and accepts relevant inquiries. For example, the reception department suggests relevant inquiries based on the interests expressed by employees on social media. For example, the reception department stores employees' social media activity in a database and extracts their interests. The reception department can also prompt employees for inquiries at the appropriate time based on the amount of time they spend on social media. For example, the reception department analyzes the amount of time employees spend on social media and sends reminders at the appropriate time. Furthermore, the reception department can suggest appropriate inquiries based on the emotional expressions of employees on social media. For example, the reception department analyzes the emotional expressions of employees on social media and extracts relevant inquiries. In this way, relevant inquiries can be suggested by analyzing employees' social media activity. Some or all of the above processes in the reception department may be performed using AI, or not. For example, the reception department can input data on employees' social media activity into a generating AI and have the generating AI extract relevant inquiries.

[0042] The analysis unit adjusts the level of detail of the analysis based on the importance of the consultation content. For example, the analysis unit performs a detailed analysis for consultation content of high importance. For example, the analysis unit evaluates the importance of the consultation content and performs a detailed analysis for consultation content of high importance. The analysis unit can also perform a concise analysis for consultation content of low importance. For example, the analysis unit evaluates the importance of the consultation content and performs a concise analysis for consultation content of low importance. Furthermore, the analysis unit can perform an analysis with an appropriate level of detail for consultation content of moderate importance. For example, the analysis unit evaluates the importance of the consultation content and performs an analysis with an appropriate level of detail for consultation content of moderate importance. In this way, by adjusting the level of detail of the analysis based on the importance of the consultation content, a detailed analysis can be performed for important consultation content. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the importance of the consultation content into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0043] The analysis unit applies different analysis algorithms depending on the category of the consultation content during analysis. For example, the analysis unit applies a health-related analysis algorithm to consultations about health. For example, the analysis unit uses a health-related analysis algorithm to analyze consultations about health. The analysis unit can also apply a career-related analysis algorithm to consultations about careers. For example, the analysis unit uses a career-related analysis algorithm to analyze consultations about careers. Furthermore, the analysis unit can apply a workplace environment-related analysis algorithm to consultations about the workplace environment. For example, the analysis unit uses a workplace environment-related analysis algorithm to analyze consultations about the workplace environment. By applying different analysis algorithms depending on the category of the consultation content, more appropriate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of the consultation content into a generating AI and have the generating AI execute the application of different analysis algorithms.

[0044] The analysis unit determines the priority of analysis based on the submission date of the consultation content. For example, the analysis unit prioritizes the analysis of recently submitted consultation content. For example, the analysis unit stores the submission date and time of the consultation content in a database and prioritizes the analysis of recently submitted consultation content. The analysis unit can also postpone the analysis of older consultation content. For example, the analysis unit evaluates the submission date and time of the consultation content and postpones the analysis of older consultation content. Furthermore, the analysis unit can analyze consultation content of moderate age to a reasonable extent. For example, the analysis unit evaluates the submission date and time of the consultation content and analyzes consultation content of moderate age to a reasonable extent. In this way, by determining the priority of analysis based on the submission date of the consultation content, consultation content that requires a quicker response can be prioritized. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the submission date and time of the consultation content into a generating AI and have the generating AI perform the determination of the analysis priority.

[0045] The analysis unit adjusts the order of analysis based on the relevance of the consultation content during the analysis. For example, the analysis unit prioritizes the analysis of highly relevant consultation content. For example, the analysis unit evaluates the relevance of the consultation content and prioritizes the analysis of highly relevant consultation content. The analysis unit can also postpone the analysis of less relevant consultation content. For example, the analysis unit evaluates the relevance of the consultation content and postpones the analysis of less relevant consultation content. Furthermore, the analysis unit can appropriately analyze consultation content of moderate relevance. For example, the analysis unit evaluates the relevance of the consultation content and appropriately analyzes consultation content of moderate relevance. In this way, by adjusting the order of analysis based on the relevance of the consultation content, highly relevant consultation content can be prioritized. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the relevance of the consultation content into a generating AI and have the generating AI perform the adjustment of the analysis order.

[0046] The scoring unit improves the accuracy of scoring by considering the interrelationships of the consultation content during the scoring process. For example, if the consultation content spans multiple categories, the scoring unit considers the interrelationships when scoring. For example, the scoring unit evaluates the interrelationships of the consultation content and scores the consultation content that spans multiple categories. The scoring unit can also consider the relevance of the consultation content when it is related. For example, the scoring unit evaluates the relevance of the consultation content and scores the related consultation content. Furthermore, if the consultation content is independent, the scoring unit can also consider its independence when scoring. For example, the scoring unit evaluates the independence of the consultation content and scores the independent consultation content. This improves the accuracy of scoring by considering the interrelationships of the consultation content. Some or all of the above processing in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input the interrelationships of the consultation content into a generating AI and have the generating AI perform the scoring accuracy improvement.

[0047] The scoring unit performs scoring while considering the client's attribute information. For example, the scoring unit may score based on the client's age. For example, the scoring unit may store the client's age in a database and perform scoring based on age. The scoring unit may also score based on the client's job title. For example, the scoring unit may store the client's job title in a database and perform scoring based on job title. Furthermore, the scoring unit may also score based on the client's years of service. For example, the scoring unit may store the client's years of service in a database and perform scoring based on years of service. This improves the accuracy of scoring by considering the client's attribute information. Some or all of the above processing in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit may input the client's attribute information into a generating AI and have the generating AI perform the scoring.

[0048] The scoring unit considers the geographical distribution of consultation content when scoring. For example, if the consultation content is concentrated in a particular region, the scoring unit applies scoring criteria related to that region. For example, the scoring unit stores the geographical distribution of consultation content in a database and applies scoring criteria related to that particular region. The scoring unit can also apply region-specific scoring criteria if the consultation content is widely distributed. For example, the scoring unit evaluates the geographical distribution of consultation content and applies region-specific scoring criteria. Furthermore, if the consultation content is not biased towards a particular region, the scoring unit can also apply normal scoring criteria. For example, the scoring unit evaluates the geographical distribution of consultation content and applies normal scoring criteria to consultation content that is not biased towards a particular region. This improves the accuracy of scoring by considering the geographical distribution of consultation content. Some or all of the above processing in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input the geographical distribution of consultation content into a generating AI and have the generating AI perform the scoring.

[0049] The scoring unit improves the accuracy of scoring by referring to relevant literature on the consultation content during the scoring process. For example, the scoring unit scores by referring to the latest research papers related to the consultation content. For example, the scoring unit stores the latest research papers related to the consultation content in a database and uses them for scoring. The scoring unit can also score by referring to past cases related to the consultation content. For example, the scoring unit stores past cases related to the consultation content in a database and uses them for scoring. Furthermore, the scoring unit can score by referring to industry best practices related to the consultation content. For example, the scoring unit stores industry best practices related to the consultation content in a database and uses them for scoring. This improves the accuracy of scoring by referring to relevant literature on the consultation content. Some or all of the above processes in the scoring unit may be performed using AI, for example, or not using AI. For example, the scoring unit can input relevant literature on the consultation content into a generating AI and have the generating AI perform the improvement of scoring accuracy.

[0050] The alert unit predicts the current alert by referring to past alert data when an alert occurs. For example, the alert unit predicts the probability of the current alert occurring based on past alert data. For example, the alert unit saves past alert data to a database and predicts the probability of the current alert occurring. The alert unit can also predict the scope of impact of the current alert based on past alert data. For example, the alert unit evaluates past alert data and predicts the scope of impact of the current alert. Furthermore, the alert unit can propose a response method for the current alert based on past alert data. For example, the alert unit evaluates past alert data and proposes a response method for the current alert. In this way, by referring to past alert data, the probability of the current alert occurring and the scope of impact can be predicted. Some or all of the above processing in the alert unit may be performed using AI, for example, or without using AI. For example, the alert unit can input past alert data into a generating AI and have the generating AI perform the prediction of the current alert.

[0051] The alert unit applies different alert methods depending on the category of the consultation content when an alert occurs. For example, the alert unit applies health-related alert methods to consultations about health. For example, the alert unit stores the consultation content in a database and applies health-related alert methods. The alert unit can also apply career-related alert methods to consultations about careers. For example, the alert unit stores the consultation content in a database and applies career-related alert methods. Furthermore, the alert unit can apply workplace environment-related alert methods to consultations about the workplace environment. For example, the alert unit stores the consultation content in a database and applies workplace environment-related alert methods. By applying different alert methods depending on the category of the consultation content, more appropriate alerts can be provided. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input the category of the consultation content into a generating AI and have the generating AI execute the application of different alert methods.

[0052] The alert unit analyzes changes in alerts based on the submission date of the consultation content when an alert occurs. For example, the alert unit analyzes changes in alerts based on recently submitted consultation content. For example, the alert unit stores the submission date and time of the consultation content in a database and analyzes changes in alerts based on recently submitted consultation content. The alert unit can also analyze changes in alerts based on older consultation content. For example, the alert unit evaluates the submission date and time of the consultation content and analyzes changes in alerts based on older consultation content. Furthermore, the alert unit can also analyze changes in alerts based on consultation content of moderate age. For example, the alert unit evaluates the submission date and time of the consultation content and analyzes changes in alerts based on moderate age. This allows for more appropriate responses by analyzing changes in alerts based on the submission date of the consultation content. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input the submission date and time of the consultation content into a generating AI and have the generating AI perform the analysis of changes in alerts.

[0053] The alert unit analyzes the alert when it occurs by referring to relevant market data related to the consultation content. For example, the alert unit analyzes the impact of the alert based on market data related to the consultation content. For example, the alert unit stores market data related to the consultation content in a database and analyzes the impact of the alert. The alert unit can also analyze the probability of an alert occurring based on market data related to the consultation content. For example, the alert unit evaluates market data related to the consultation content and analyzes the probability of an alert occurring. Furthermore, the alert unit can propose a response method to the alert based on market data related to the consultation content. For example, the alert unit evaluates market data related to the consultation content and proposes a response method to the alert. This allows for the analysis of the impact and probability of an alert occurring by referring to relevant market data related to the consultation content. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input market data related to the consultation content into a generating AI and have the generating AI perform the alert analysis.

[0054] The information provider improves the accuracy of information provision by considering the interrelationships of the consultation content. For example, if the consultation content spans multiple categories, the information provider provides information while considering the interrelationships. For example, the information provider evaluates the interrelationships of the consultation content and provides information based on the consultation content that spans multiple categories. The information provider can also provide information while considering the relevance of the consultation content if it is related. For example, the information provider evaluates the relevance of the consultation content and provides information based on the related consultation content. Furthermore, if the consultation content is independent, the information provider can provide information while considering its independence. For example, the information provider evaluates the independence of the consultation content and provides information based on the independent consultation content. As a result, the accuracy of the information provided is improved by considering the interrelationships of the consultation content. Some or all of the above processing in the information provider may be performed using AI, for example, or without using AI. For example, the information provider can input the interrelationships of the consultation content into a generating AI and have the generating AI perform the improvement of the accuracy of information provision.

[0055] The information provider takes into account the client's attribute information when providing information. For example, the provider may provide information based on the client's age. For example, the provider may store the client's age in a database and provide information based on age. The provider may also provide information based on the client's job title. For example, the provider may store the client's job title in a database and provide information based on job title. Furthermore, the provider may also provide information based on the client's years of service. For example, the provider may store the client's years of service in a database and provide information based on years of service. This improves the accuracy of the information provided by taking the client's attribute information into consideration. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the provider may input the client's attribute information into a generating AI and have the generating AI perform the information provision.

[0056] The information provider considers the geographical distribution of the consultation content when providing information. For example, if the consultation content is concentrated in a particular area, the provider will provide information related to that area. For example, the provider may store the geographical distribution of the consultation content in a database and provide information related to that specific area. The provider may also provide information for each region if the consultation content is widely distributed. For example, the provider may evaluate the geographical distribution of the consultation content and provide information for each region. Furthermore, if the consultation content is not biased towards a particular region, the provider may provide normal information. For example, the provider may evaluate the geographical distribution of the consultation content and provide normal information for consultation content that is not biased towards a particular region. This improves the accuracy of the information provided by considering the geographical distribution of the consultation content. Some or all of the above processing in the information provider may be performed using AI, for example, or not using AI. For example, the provider may input the geographical distribution of the consultation content into a generating AI and have the generating AI perform the information provision.

[0057] The information provider improves the accuracy of the information provided by referring to relevant literature on the consultation topic. For example, the information provider provides information by referring to the latest research papers related to the consultation topic. For example, the information provider stores the latest research papers related to the consultation topic in a database and uses them for information provision. The information provider can also provide information by referring to past cases related to the consultation topic. For example, the information provider stores past cases related to the consultation topic in a database and uses them for information provision. Furthermore, the information provider can also provide information by referring to industry best practices related to the consultation topic. For example, the information provider stores industry best practices related to the consultation topic in a database and uses them for information provision. This improves the accuracy of the information provided by referring to relevant literature on the consultation topic. Some or all of the above processing in the information provider may be performed using AI, for example, or not using AI. For example, the information provider can input relevant literature on the consultation topic into a generating AI and have the generating AI perform the improvement of the accuracy of information provision.

[0058] The learning unit optimizes the learning algorithm by referring to past learning data during the learning process. For example, the learning unit optimizes the current learning algorithm based on past learning data. For example, the learning unit saves past learning data to a database and optimizes the current learning algorithm. The learning unit can also improve the accuracy of the learning algorithm based on past learning data. For example, the learning unit evaluates past learning data and improves the accuracy of the learning algorithm. Furthermore, the learning unit can improve the efficiency of the learning algorithm based on past learning data. For example, the learning unit evaluates past learning data and improves the efficiency of the learning algorithm. As a result, the accuracy and efficiency of the learning algorithm are improved by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0059] The learning unit weights the training data based on the submission date of the consultations during training. For example, the learning unit may weight the training data by giving more weight to recently submitted consultations. For example, the learning unit may store the submission date and time of the consultations in a database and weight the training data by giving more weight to recently submitted consultations. The learning unit may also lighten the weight of older consultations. For example, the learning unit may evaluate the submission date and time of the consultations and lighten the weight of older consultations. Furthermore, the learning unit may also appropriately weight consultations that were submitted at a moderate time. For example, the learning unit may evaluate the submission date and time of the consultations and appropriately weight consultations that were submitted at a moderate time. This allows for more appropriate training by weighting the training data based on the submission date of the consultations. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit may input the submission date and time of the consultations into a generating AI and have the generating AI perform the weighting of the training data.

[0060] The analysis unit optimizes the analysis algorithm by referring to past consultation data during analysis. For example, the analysis unit optimizes the current analysis algorithm based on past consultation data. For example, the analysis unit saves past consultation data to a database and optimizes the current analysis algorithm. The analysis unit can also improve the accuracy of the analysis algorithm based on past consultation data. For example, the analysis unit evaluates past consultation data and improves the accuracy of the analysis algorithm. Furthermore, the analysis unit can improve the efficiency of the analysis algorithm based on past consultation data. For example, the analysis unit evaluates past consultation data and improves the efficiency of the analysis algorithm. As a result, the accuracy and efficiency of the analysis algorithm are improved by referring to past consultation data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input past consultation data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0061] The analysis department weights the analysis data based on when the consultation content was submitted. For example, the analysis department may weight the analysis data by giving more weight to recently submitted consultation content. For example, the analysis department may store the submission date and time of the consultation content in a database and weight the analysis data by giving more weight to recently submitted consultation content. The analysis department may also lighten the weight of older consultation content. For example, the analysis department may evaluate the submission date and time of the consultation content and lighten the weight of older consultation content. Furthermore, the analysis department may also appropriately weight consultation content that was submitted at a moderate time. For example, the analysis department may evaluate the submission date and time of the consultation content and appropriately weight consultation content that was submitted at a moderate time. This allows for more appropriate analysis by weighting the analysis data based on when the consultation content was submitted. Some or all of the above processing in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department may input the submission date and time of the consultation content into a generating AI and have the generating AI perform the weighting of the analysis data.

[0062] The support unit optimizes the support algorithm by referring to past consultation data during support. For example, the support unit optimizes the current support algorithm based on past consultation data. For example, the support unit saves past consultation data to a database and optimizes the current support algorithm. The support unit can also improve the accuracy of the support algorithm based on past consultation data. For example, the support unit evaluates past consultation data and improves the accuracy of the support algorithm. Furthermore, the support unit can improve the efficiency of the support algorithm based on past consultation data. For example, the support unit evaluates past consultation data and improves the efficiency of the support algorithm. As a result, the accuracy and efficiency of the support algorithm are improved by referring to past consultation data. Some or all of the above processes in the support unit may be performed using AI, for example, or without using AI. For example, the support unit can input past consultation data into a generating AI and have the generating AI perform the optimization of the support algorithm.

[0063] The support department weights support data based on when the consultation content was submitted. For example, the support department may weight support data by giving more weight to recently submitted consultations. For example, the support department may store the submission date and time of the consultation content in a database and weight the support data by giving more weight to recently submitted consultations. The support department may also lighten the weight of older consultations. For example, the support department may evaluate the submission date and time of the consultation content and lighten the weight of older consultations. Furthermore, the support department may also appropriately weight consultations that were submitted at a moderate time. For example, the support department may evaluate the submission date and time of the consultation content and appropriately weight consultations that were submitted at a moderate time. In this way, by weighting support data based on when the consultation content was submitted, more appropriate support can be provided. Some or all of the above processing in the support department may be performed using AI, for example, or not using AI. For example, the support department may input the submission date and time of the consultation content into a generating AI and have the generating AI perform the weighting of the support data.

[0064] The support department improves the accuracy of its support by referring to relevant literature related to the consultation content. For example, the support department provides support by referring to the latest research papers related to the consultation content. For example, the support department stores the latest research papers related to the consultation content in a database and uses them for support. The support department can also provide support by referring to past cases related to the consultation content. For example, the support department stores past cases related to the consultation content in a database and uses them for support. Furthermore, the support department can provide support by referring to industry best practices related to the consultation content. For example, the support department stores industry best practices related to the consultation content in a database and uses them for support. This improves the accuracy of support by referring to relevant literature related to the consultation content. Some or all of the above processes in the support department may be performed using AI, for example, or not using AI. For example, the support department can input relevant literature related to the consultation content into a generating AI and have the generating AI perform the improvement of support accuracy.

[0065] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0066] The reception department can analyze an employee's past consultation history to select the most appropriate method of handling their inquiry. For example, it can prioritize suggesting methods the employee has used in the past (chat, voice, etc.). It can also automatically suggest relevant topics based on the content of past consultations. Furthermore, it can prompt employees to seek consultation at appropriate times based on their past consultation frequency. In this way, the system can select the most suitable method of handling an employee's inquiry by analyzing their past consultation history.

[0067] The analysis unit can be equipped with an analysis function that statistically analyzes employees' health status and consultation content. For example, regression analysis can be used to analyze the relationship between employees' health status and consultation content. Cluster analysis can also be used to group employees' consultation content. Furthermore, time series analysis can be used to track changes in employees' health status. In this way, by statistically analyzing employees' health status and consultation content, the overall health status of the company can be understood.

[0068] The service provider can include a support unit that analyzes employee consultation trends and provides preventative support. For example, it can analyze the frequency of employee consultations and evaluate whether specific problems occur frequently. It can also use trend analysis to understand the trends in employee consultations. Furthermore, it can use pattern recognition to identify commonalities in employee consultations. This allows for the analysis of employee consultation trends and the provision of preventative support, thereby supporting employee health.

[0069] The reception desk can filter inquiries based on employees' current work situations and areas of interest. For example, it can prioritize inquiries related to an employee's current project status. It can also suggest appropriate consultation topics based on an employee's areas of interest. Furthermore, it can filter specific inquiries based on an employee's work environment. This allows for priority reception of relevant inquiries by filtering based on an employee's current work situation and areas of interest.

[0070] The reception desk can prioritize inquiries based on the employee's geographical location. For example, if an employee is in a specific office, inquiries related to that office will be prioritized. Similarly, if an employee is working remotely, inquiries related to remote work will be prioritized. Furthermore, if an employee is on a business trip, inquiries related to their destination will be prioritized. This allows for more appropriate inquiries to be received by prioritizing those that are relevant to the employee's geographical location.

[0071] The analysis unit can adjust the level of detail in the analysis based on the importance of the consultation content. For example, it can perform a detailed analysis for consultations of high importance, a concise analysis for consultations of low importance, and an analysis of appropriate detail for consultations of moderate importance. By adjusting the level of detail in the analysis based on the importance of the consultation content, it is possible to perform a detailed analysis for important consultations.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The reception desk receives inquiries from employees. These inquiries may include work-related questions, health-related questions, and personal issues. The reception desk provides an interface for employees to make anonymous inquiries, and includes features such as forms for entering inquiries, chatbots, voice input, and video calls. Step 2: The analysis unit analyzes the consultation content received by the reception unit. The analysis is performed using methods such as text analysis, sentiment analysis, and pattern recognition. For example, text analysis is used to extract keywords from the consultation content and identify the category of the consultation content. Sentiment analysis is used to identify the emotions contained in the consultation content, and pattern recognition is used to compare it with past consultation data and identify similar consultation content. Step 3: The scoring unit scores the mental and physical state based on the consultation content analyzed by the analysis unit. Scoring is performed based on the score range, evaluation criteria, and algorithm used. For example, the employee's mental and physical state is scored on a scale from 0 to 100, and an alert is generated if the score is low. Step 4: The alerting unit automatically generates an alert if the score is low, determined by the scoring unit. The alert is generated based on factors such as the score threshold, notification method, and alert type. For example, an alert is generated and the HR department is notified if the score is below 50. Step 5: The Service Department provides information to the Human Resources Department based on alerts generated by the Alert Department. This information includes the format of the report, the notification method, and the type of information to be provided. For example, when an alert occurs, the Human Resources Department is notified by email and a report containing the details of the alert is automatically generated.

[0074] (Example of form 2) An AI workplace consultation concierge according to an embodiment of the present invention is an AI-based consultation platform that allows employees to anonymously consult about the workplace environment, supervisors, colleagues, job content, health, future career, etc. The AI ​​workplace consultation concierge scores the mental and physical state of employees and automatically generates an alert if the score is low, enabling the human resources department to take appropriate follow-up action. Because an AI acts as the consultant, employees are more likely to express their true feelings, and the human resources department can more easily grasp the genuine voices of employees. For example, by providing an environment where employees can consult anonymously, employees can consult with peace of mind. In addition, by scoring the mental and physical health state and automatically generating an alert if the score is low, the human resources department can respond quickly. This supports the mental and physical health of employees and contributes to improving the workplace environment. As a result, the AI ​​workplace consultation concierge can efficiently receive and analyze employee consultations, score their mental and physical state, generate alerts, and provide information to the human resources department.

[0075] The AI ​​workplace consultation concierge according to this embodiment comprises a reception unit, an analysis unit, a scoring unit, an alert unit, and a provision unit. The reception unit receives consultation content from employees. Employee consultation content includes, but is not limited to, work-related consultations, health-related consultations, and personal problems. The reception unit provides, for example, an interface for employees to make anonymous consultations. The reception unit may also provide a form or chatbot for employees to input consultation content. Furthermore, the reception unit may include a function that allows employees to make consultations via voice input or video call. For example, the reception unit provides a web interface for employees to make anonymous consultations and displays a form for employees to input consultation content. A chatbot provides an interactive interface for employees to make consultations in real time. The function of making consultations via voice input or video call provides a means for employees to make consultations more directly. The analysis unit analyzes the consultation content received by the reception unit. Analysis is performed by, for example, text analysis, sentiment analysis, pattern recognition, etc., but is not limited to these methods. For example, the analysis unit extracts keywords from the consultation content using text analysis and identifies the category of the consultation content. The analysis unit can also identify the emotions contained in the consultation content using sentiment analysis. Furthermore, the analysis unit can identify similar consultation content by comparing it with past consultation data using pattern recognition. For example, the analysis unit extracts keywords from the consultation content using text analysis and identifies the category of the consultation content. Sentiment analysis identifies the emotions contained in the consultation content and provides information for evaluating the employee's mental and physical state. Pattern recognition performs a more accurate analysis by comparing it with past consultation data and identifying similar consultation content. The scoring unit scores the mental and physical state based on the consultation content analyzed by the analysis unit. Scoring is performed based on, for example, a range of scores, evaluation criteria, and the algorithm used, but is not limited to such examples. For example, the scoring unit scores the employee's mental and physical state on a scale from 0 to 100. The scoring unit can also score the employee's mental and physical state on a scale from A to F.Furthermore, the scoring unit can also score employees' mental and physical health using percentiles. For example, the scoring unit can score employees' mental and physical health on a scale from 0 to 100 and generate an alert if the score is low. The A to F rating is used as a means of concisely evaluating employees' mental and physical health. Percentiles are used as an indicator to evaluate employees' mental and physical health in comparison to other employees. The alert unit automatically generates an alert when the scoring unit generates a low score. Alerts are generated based on, but are not limited to, the score threshold, notification method, and alert type. For example, the alert unit generates an alert if the score is below 50. The alert unit can also generate an emergency alert if the score is below 30. Furthermore, the alert unit can also generate a caution alert if the score is below 70. For example, the alert unit generates an alert and notifies the HR department if the score is below 50. An emergency alert is generated when the score is below 30 and is used when immediate action is required. A caution alert is generated when the score is below 70 and is used when caution is required. The service provider provides information to the human resources department based on alerts generated by the alert provider. This information may include, but is not limited to, the format of reports, notification methods, and the types of information provided. For example, the service provider may notify the human resources department via email when an alert occurs. The service provider may also automatically generate and provide a report containing details of the alert. Furthermore, the service provider may display the alert status on a dashboard, allowing the human resources department to understand the situation in real time. For example, the service provider may notify the human resources department via email when an alert occurs and automatically generate a report containing details of the alert. The dashboard displays the alert status in real time and is used as a tool to enable the human resources department to respond quickly. This allows the AI ​​workplace consultation concierge according to the embodiment to efficiently receive and analyze employee consultations, score their mental and physical state, generate alerts, and provide information to the human resources department.

[0076] The reception desk receives inquiries from employees. These inquiries may include, but are not limited to, work-related questions, health-related questions, or personal issues. The reception desk may provide an interface for employees to make anonymous inquiries. It may also provide forms or chatbots for employees to input their inquiries. Furthermore, the reception desk may include features that allow employees to make inquiries via voice input or video calls. For example, the reception desk may provide a web interface for employees to make anonymous inquiries and display a form for employees to input their inquiries. A chatbot may provide an interactive interface for employees to make real-time inquiries. Features that allow employees to make inquiries via voice input or video calls provide a means for employees to make inquiries more directly. To ensure a safe environment for employees to make inquiries, the reception desk implements encryption technology for privacy protection. For example, inquiries are encrypted using the SSL / TLS protocol to prevent unauthorized access by third parties. The reception desk also provides a function for employees to record their inquiries for later reference. This allows employees to review past inquiries and make additional inquiries as needed. Furthermore, the reception area will provide a multilingual interface, enabling employees who speak different languages ​​to seek advice smoothly. For example, consultations will be available in multiple languages, such as English, Japanese, and Spanish, catering to the diverse needs of employees. This allows the reception area to provide an environment where employees can feel comfortable seeking advice and to efficiently process inquiries.

[0077] The analysis unit analyzes the consultation content received by the reception unit. Analysis is performed using methods such as text analysis, sentiment analysis, and pattern recognition, but is not limited to these examples. For instance, the analysis unit can use text analysis to extract keywords from the consultation content and identify its category. It can also use sentiment analysis to identify the emotions contained in the consultation content. Furthermore, it can use pattern recognition to compare the current consultation with past consultation data and identify similar consultations. For example, the analysis unit can use text analysis to extract keywords from the consultation content and identify its category. Sentiment analysis identifies the emotions contained in the consultation content and provides information for evaluating the employee's mental and physical state. Pattern recognition allows for more accurate analysis by comparing the current consultation with past consultation data and identifying similar consultations. The analysis unit utilizes natural language processing (NLP) technology to understand the context of the consultation content and perform more detailed analysis. For example, NLP technology is used to analyze the context of the consultation content and identify the root cause of the employee's problem. Furthermore, the analysis unit can use machine learning algorithms to learn patterns in consultation content and predict future consultation content. This allows the analysis unit to quickly and accurately analyze employee consultation content and provide information for evaluating employees' mental and physical health. In addition, the analysis unit can leverage high-performance computing resources for real-time analysis, enabling rapid response. For example, it can use a cloud-based analysis platform to quickly process large amounts of data and provide real-time analysis results. This allows the analysis unit to quickly and accurately analyze employee consultation content and provide information for evaluating employees' mental and physical health.

[0078] The scoring unit scores the mental and physical state of an employee based on the consultation content analyzed by the analysis unit. Scoring is performed based on, for example, a score range, evaluation criteria, and the algorithm used, but is not limited to these examples. For example, the scoring unit scores an employee's mental and physical state on a scale from 0 to 100. The scoring unit can also score an employee's mental and physical state using a rating system from A to F. Furthermore, the scoring unit can score an employee's mental and physical state using percentiles. For example, the scoring unit scores an employee's mental and physical state on a scale from 0 to 100 and generates an alert if the score is low. The A to F rating system is used as a means of concisely evaluating an employee's mental and physical state. Percentiles are used as an indicator to evaluate an employee's mental and physical state in comparison to other employees. The scoring unit uses machine learning algorithms to build a model for scoring employees' mental and physical states. For example, it trains a model to predict an employee's mental and physical state using past consultation data and then scores new consultation content. Furthermore, the scoring unit can calculate an overall score by combining multiple indicators to evaluate an employee's mental and physical state. For example, it can comprehensively evaluate an employee's mental and physical state by combining the results of emotion analysis, the category of the consultation content, and past consultation history. In addition, the scoring unit can visualize the scoring results, allowing for an intuitive understanding of changes in an employee's mental and physical state. For example, the scoring results can be displayed in graphs or charts, allowing for a visual confirmation of changes in an employee's mental and physical state. This enables the scoring unit to accurately evaluate an employee's mental and physical state and provide information for taking appropriate action.

[0079] The alerting unit automatically generates an alert when the scoring unit generates a low score. Alerts are generated based on, but are not limited to, a score threshold, notification method, and alert type. For example, the alerting unit might generate an alert if the score is below 50. It can also generate an emergency alert if the score is below 30. Furthermore, it can generate a cautionary alert if the score is below 70. For example, the alerting unit might generate an alert and notify the HR department if the score is below 50. An emergency alert is generated when the score is below 30 and is used when immediate action is required. A cautionary alert is generated when the score is below 70 and is used when attention is needed. The alerting unit uses multiple notification methods to ensure rapid and reliable alert generation. For example, it might combine email, SMS, and push notifications to ensure alerts are delivered reliably. The alerting unit can also provide detailed alert content, indicating specific actions that need to be taken. For example, alert content might include a detailed assessment of the employee's physical and mental condition and recommended actions. Furthermore, the alerting unit records the history of alerts for later reference. This allows for reviewing past alert occurrences and evaluating the effectiveness of responses. The alert unit can also analyze the frequency and content of alerts to help improve the system. For example, it can analyze alert patterns and predict alert occurrences under specific conditions. This enables the alert unit to quickly understand the physical and mental state of employees and provide information to take appropriate action.

[0080] The Service Provider provides information to the Human Resources Department based on alerts generated by the Alerts Department. This information may include, but is not limited to, the format of reports, notification methods, and the types of information provided. For example, the Service Provider may notify the Human Resources Department via email when an alert occurs. The Service Provider may also automatically generate and provide reports containing details of the alerts. Furthermore, the Service Provider may display alert status on a dashboard, allowing the Human Resources Department to stay informed in real time. For example, the Service Provider may notify the Human Resources Department via email when an alert occurs and automatically generate reports containing details of the alerts. The dashboard is used as a tool to display alert status in real time, enabling the Human Resources Department to respond quickly. The Service Provider can provide detailed information about the alerts, indicating specific actions required. For example, alert content may include detailed assessments of employees' physical and mental health and recommended actions. Additionally, the Service Provider records the history of alerts for later reference. This allows for reviewing past alert occurrences and evaluating the effectiveness of responses. The Service Provider can also analyze the frequency and content of alerts to help improve the system. For example, by analyzing alert patterns, it's possible to predict when alerts will occur under specific conditions. This allows the service provider to quickly understand the physical and mental state of employees and provide information to take appropriate action.

[0081] The analysis unit includes a learning unit that learns from past consultation data. The learning unit learns from past consultation data using, for example, a machine learning algorithm. For example, the learning unit learns patterns in consultation content using past consultation data to improve the accuracy of the analysis. The learning unit can also learn based on the type of dataset. For example, the learning unit learns using different types of datasets, such as consultation data related to work, consultation data related to health, and consultation data related to personal problems. Furthermore, the learning unit can adjust the frequency of learning. For example, the learning unit periodically learns from past consultation data and updates the analysis algorithm. This improves the accuracy of the analysis by learning from past consultation data. Some or all of the above processes in the learning unit may be performed using, for example, AI, or not using AI. For example, the learning unit can input past consultation data into a generating AI and have the generating AI perform learning of patterns in consultation content.

[0082] The analysis unit includes an analysis unit that statistically analyzes employees' health status and consultation content. The analysis unit analyzes employees' health status and consultation content using the statistical methods it employs. For example, the analysis unit uses regression analysis to analyze the relationship between employees' health status and consultation content. The analysis unit can also group employees' consultation content using cluster analysis. Furthermore, the analysis unit can track changes in employees' health status using time series analysis. For example, the analysis unit uses regression analysis to analyze the relationship between employees' health status and consultation content and evaluate the impact of health deterioration on consultation content. Cluster analysis is used to group employees' consultation content and identify common problems. Time series analysis is used to track changes in employees' health status and grasp long-term trends. This allows for an understanding of the overall health of the company by statistically analyzing employees' health status and consultation content. Some or all of the above processes in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input employee health status and consultation content data into a generating AI and have the generating AI perform the statistical analysis.

[0083] The service unit includes a support unit that analyzes employee consultation trends and provides preventative support. The support unit, for example, performs frequency analysis to analyze employee consultation trends. For example, the support unit analyzes the frequency of employee consultations and evaluates whether a particular problem occurs frequently. The support unit can also use trend analysis to grasp trends in employee consultations. Furthermore, the support unit can use pattern recognition to identify commonalities in employee consultations. For example, the support unit uses frequency analysis to analyze the frequency of employee consultations and evaluates whether a particular problem occurs frequently. Trend analysis is used to grasp trends in employee consultations and predict future problems. Pattern recognition is used to identify commonalities in employee consultations and provide preventative support. This allows for supporting employee health by analyzing employee consultation trends and providing preventative support. Some or all of the above processes in the support unit may be performed using AI, for example, or not using AI. For example, the support unit can input employee consultation data into a generating AI and have the generating AI perform a consultation trend analysis.

[0084] The reception desk estimates the employee's emotions and adjusts the timing of consultations based on the estimated emotions. For example, if an employee is feeling stressed, the reception desk will immediately accept consultations. For example, the reception desk may capture the employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it may calculate an emotion score based on changes in facial expressions. Also, if an employee is relaxed, the reception desk will accept consultations at an appropriate time. For example, the reception desk may record the employee's voice and estimate their emotions using voice analysis technology. For example, it may analyze the tone and speed of their voice and calculate an emotion score. Also, if an employee is busy, the reception desk may set a reminder so that they can consult later. For example, the reception desk may collect the employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it may calculate an emotion score based on fluctuations in heart rate. This allows for consultations to be accepted at a more appropriate time by adjusting the timing of consultations based on the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the above-described processes in the reception area may be performed using AI, or not using AI. For example, the reception area may input employee sentiment data into a generative AI and have the generative AI perform sentiment estimation.

[0085] The reception department analyzes the employee's past consultation history and selects the most suitable consultation method. For example, the reception department prioritizes suggesting consultation methods (chat, voice, etc.) that the employee has used in the past. For example, the reception department stores the employee's past consultation history in a database and analyzes past consultation methods. The reception department can also automatically suggest relevant topics based on the content of the employee's past consultations. For example, the reception department analyzes the content of the employee's past consultations and extracts relevant topics. Furthermore, the reception department can prompt the employee for consultation at the appropriate time based on the employee's past consultation frequency. For example, the reception department analyzes the employee's past consultation frequency and sends reminders at the appropriate time. This allows the reception department to select the most suitable consultation method by analyzing the employee's past consultation history. Some or all of the above processes in the reception department may be performed using AI, or not. For example, the reception department can input the employee's past consultation history into a generating AI and have the generating AI select the most suitable consultation method.

[0086] The reception desk filters incoming consultations based on the employee's current work situation and areas of interest. For example, the reception desk prioritizes receiving consultations based on the employee's current project status. For example, the reception desk stores the employee's current project status in a database and extracts relevant consultations. The reception desk can also suggest appropriate consultation topics based on the employee's areas of interest. For example, the reception desk analyzes the employee's areas of interest and extracts relevant consultation topics. Furthermore, the reception desk can filter specific consultations based on the employee's work environment. For example, the reception desk stores the employee's work environment in a database and extracts relevant consultations. This allows the reception desk to prioritize receiving relevant consultations by filtering based on the employee's current work situation and areas of interest. 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 data on the employee's current work situation and areas of interest into a generating AI and have the generating AI perform the filtering.

[0087] The reception desk estimates the emotions of employees and prioritizes the types of consultations it receives based on those estimates. For example, if an employee is stressed, the reception desk will prioritize urgent consultations. For example, the reception desk may capture the employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it may calculate an emotion score based on changes in facial expressions. Also, if an employee is relaxed, the reception desk will accept normal consultations. For example, the reception desk may record the employee's voice and estimate their emotions using voice analysis technology. For example, it may analyze the tone and speed of their voice and calculate an emotion score. Furthermore, if an employee is feeling anxious, the reception desk will prioritize consultations that provide reassurance. For example, the reception desk may collect the employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it may calculate an emotion score based on fluctuations in heart rate. This allows for prioritizing consultations based on the employee's emotions, enabling the reception desk to prioritize urgent consultations. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the above-described processes in the reception area may be performed using AI, or not using AI. For example, the reception area may input employee sentiment data into a generative AI and have the generative AI perform sentiment estimation.

[0088] The reception desk prioritizes receiving inquiries based on the employee's geographical location information. For example, if an employee is in a specific office, the reception desk will prioritize inquiries related to that office. For example, the reception desk may obtain the employee's geographical location information using GPS data and extract relevant inquiries. The reception desk can also prioritize inquiries related to remote work if the employee is working remotely. For example, the reception desk may obtain the employee's geographical location information using location services and extract relevant inquiries. Furthermore, if an employee is on a business trip, the reception desk may prioritize inquiries related to the business trip destination. For example, the reception desk may store the employee's geographical location information in a database and extract relevant inquiries. This allows for more appropriate inquiries to be received by prioritizing inquiries based on the employee's geographical location information. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input employees' geographical location information into a generating AI and have the AI ​​extract highly relevant inquiries.

[0089] The reception department analyzes employees' social media activity when receiving inquiries and accepts relevant inquiries. For example, the reception department suggests relevant inquiries based on the interests expressed by employees on social media. For example, the reception department stores employees' social media activity in a database and extracts their interests. The reception department can also prompt employees for inquiries at the appropriate time based on the amount of time they spend on social media. For example, the reception department analyzes the amount of time employees spend on social media and sends reminders at the appropriate time. Furthermore, the reception department can suggest appropriate inquiries based on the emotional expressions of employees on social media. For example, the reception department analyzes the emotional expressions of employees on social media and extracts relevant inquiries. In this way, relevant inquiries can be suggested by analyzing employees' social media activity. Some or all of the above processes in the reception department may be performed using AI, or not. For example, the reception department can input data on employees' social media activity into a generating AI and have the generating AI extract relevant inquiries.

[0090] The analysis unit estimates the employee's emotions and adjusts the presentation of the analysis based on the estimated emotions. For example, if an employee is stressed, the analysis unit provides simple and easy-to-understand analysis results. For example, the analysis unit captures the employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Also, if an employee is relaxed, the analysis unit provides detailed analysis results. For example, the analysis unit records the employee's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Furthermore, if an employee is anxious, the analysis unit provides reassuring analysis results. For example, the analysis unit collects the employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for the provision of more appropriate analysis results by adjusting the presentation of the analysis based on the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the processing described above in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit may input employee sentiment data into the generating AI and have the generating AI perform sentiment estimation.

[0091] The analysis unit adjusts the level of detail of the analysis based on the importance of the consultation content. For example, the analysis unit performs a detailed analysis for consultation content of high importance. For example, the analysis unit evaluates the importance of the consultation content and performs a detailed analysis for consultation content of high importance. The analysis unit can also perform a concise analysis for consultation content of low importance. For example, the analysis unit evaluates the importance of the consultation content and performs a concise analysis for consultation content of low importance. Furthermore, the analysis unit can perform an analysis with an appropriate level of detail for consultation content of moderate importance. For example, the analysis unit evaluates the importance of the consultation content and performs an analysis with an appropriate level of detail for consultation content of moderate importance. In this way, by adjusting the level of detail of the analysis based on the importance of the consultation content, a detailed analysis can be performed for important consultation content. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the importance of the consultation content into a generating AI and have the generating AI perform the adjustment of the level of detail of the analysis.

[0092] The analysis unit applies different analysis algorithms depending on the category of the consultation content during analysis. For example, the analysis unit applies a health-related analysis algorithm to consultations about health. For example, the analysis unit uses a health-related analysis algorithm to analyze consultations about health. The analysis unit can also apply a career-related analysis algorithm to consultations about careers. For example, the analysis unit uses a career-related analysis algorithm to analyze consultations about careers. Furthermore, the analysis unit can apply a workplace environment-related analysis algorithm to consultations about the workplace environment. For example, the analysis unit uses a workplace environment-related analysis algorithm to analyze consultations about the workplace environment. By applying different analysis algorithms depending on the category of the consultation content, more appropriate analysis results can be provided. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the category of the consultation content into a generating AI and have the generating AI execute the application of different analysis algorithms.

[0093] The analysis unit estimates the employee's emotions and adjusts the length of the analysis based on the estimated emotions. For example, if an employee is stressed, the analysis unit provides a short, concise analysis. For example, the analysis unit captures the employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Also, if an employee is relaxed, the analysis unit provides a detailed analysis. For example, the analysis unit records the employee's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice and calculates an emotion score. Furthermore, if an employee is anxious, the analysis unit provides a reassuring analysis. For example, the analysis unit collects the employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for more appropriate analysis results to be provided by adjusting the length of the analysis based on the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the processing described above in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit may input employee sentiment data into the generating AI and have the generating AI perform sentiment estimation.

[0094] The analysis unit determines the priority of analysis based on the submission date of the consultation content. For example, the analysis unit prioritizes the analysis of recently submitted consultation content. For example, the analysis unit stores the submission date and time of the consultation content in a database and prioritizes the analysis of recently submitted consultation content. The analysis unit can also postpone the analysis of older consultation content. For example, the analysis unit evaluates the submission date and time of the consultation content and postpones the analysis of older consultation content. Furthermore, the analysis unit can analyze consultation content of moderate age to a reasonable extent. For example, the analysis unit evaluates the submission date and time of the consultation content and analyzes consultation content of moderate age to a reasonable extent. In this way, by determining the priority of analysis based on the submission date of the consultation content, consultation content that requires a quicker response can be prioritized. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the submission date and time of the consultation content into a generating AI and have the generating AI perform the determination of the analysis priority.

[0095] The analysis unit adjusts the order of analysis based on the relevance of the consultation content during the analysis. For example, the analysis unit prioritizes the analysis of highly relevant consultation content. For example, the analysis unit evaluates the relevance of the consultation content and prioritizes the analysis of highly relevant consultation content. The analysis unit can also postpone the analysis of less relevant consultation content. For example, the analysis unit evaluates the relevance of the consultation content and postpones the analysis of less relevant consultation content. Furthermore, the analysis unit can appropriately analyze consultation content of moderate relevance. For example, the analysis unit evaluates the relevance of the consultation content and appropriately analyzes consultation content of moderate relevance. In this way, by adjusting the order of analysis based on the relevance of the consultation content, highly relevant consultation content can be prioritized. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the relevance of the consultation content into a generating AI and have the generating AI perform the adjustment of the analysis order.

[0096] The scoring unit estimates employees' emotions and adjusts the scoring criteria based on the estimated emotions. For example, if an employee is stressed, the scoring unit applies scoring criteria for stress reduction. For example, the scoring unit captures the employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Conversely, if an employee is relaxed, the scoring unit applies normal scoring criteria. For example, the scoring unit records the employee's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice and calculates an emotion score. Furthermore, if an employee is feeling anxious, the scoring unit applies scoring criteria that provide a sense of security. For example, the scoring unit collects the employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. By adjusting the scoring criteria based on employees' emotions, more appropriate scoring results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, with 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-described processes in the scoring unit may be performed using AI or not using AI. For example, the scoring unit can input employee emotion data into a generative AI and have the generative AI perform emotion estimation.

[0097] The scoring unit improves the accuracy of scoring by considering the interrelationships of the consultation content during the scoring process. For example, if the consultation content spans multiple categories, the scoring unit considers the interrelationships when scoring. For example, the scoring unit evaluates the interrelationships of the consultation content and scores the consultation content that spans multiple categories. The scoring unit can also consider the relevance of the consultation content when it is related. For example, the scoring unit evaluates the relevance of the consultation content and scores the related consultation content. Furthermore, if the consultation content is independent, the scoring unit can also consider its independence when scoring. For example, the scoring unit evaluates the independence of the consultation content and scores the independent consultation content. This improves the accuracy of scoring by considering the interrelationships of the consultation content. Some or all of the above processing in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input the interrelationships of the consultation content into a generating AI and have the generating AI perform the scoring accuracy improvement.

[0098] The scoring unit performs scoring while considering the client's attribute information. For example, the scoring unit may score based on the client's age. For example, the scoring unit may store the client's age in a database and perform scoring based on age. The scoring unit may also score based on the client's job title. For example, the scoring unit may store the client's job title in a database and perform scoring based on job title. Furthermore, the scoring unit may also score based on the client's years of service. For example, the scoring unit may store the client's years of service in a database and perform scoring based on years of service. This improves the accuracy of scoring by considering the client's attribute information. Some or all of the above processing in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit may input the client's attribute information into a generating AI and have the generating AI perform the scoring.

[0099] The scoring unit estimates the employee's emotions and adjusts the order in which the scoring results are displayed based on the estimated emotions. For example, if an employee is stressed, the scoring unit prioritizes displaying important results. For example, the scoring unit captures the employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Also, if an employee is relaxed, the scoring unit displays detailed results. For example, the scoring unit records the employee's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice and calculates an emotion score. Also, if an employee is anxious, the scoring unit prioritizes displaying results that provide a sense of security. For example, the scoring unit collects the employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for more appropriate results to be provided by adjusting the order in which the scoring results are displayed based on the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the scoring unit may be performed using AI, or not using AI. For example, the scoring unit may input employee sentiment data into the generative AI and have the generative AI perform sentiment estimation.

[0100] The scoring unit considers the geographical distribution of consultation content when scoring. For example, if the consultation content is concentrated in a particular region, the scoring unit applies scoring criteria related to that region. For example, the scoring unit stores the geographical distribution of consultation content in a database and applies scoring criteria related to that particular region. The scoring unit can also apply region-specific scoring criteria if the consultation content is widely distributed. For example, the scoring unit evaluates the geographical distribution of consultation content and applies region-specific scoring criteria. Furthermore, if the consultation content is not biased towards a particular region, the scoring unit can also apply normal scoring criteria. For example, the scoring unit evaluates the geographical distribution of consultation content and applies normal scoring criteria to consultation content that is not biased towards a particular region. This improves the accuracy of scoring by considering the geographical distribution of consultation content. Some or all of the above processing in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input the geographical distribution of consultation content into a generating AI and have the generating AI perform the scoring.

[0101] The scoring unit improves the accuracy of scoring by referring to relevant literature on the consultation content during the scoring process. For example, the scoring unit scores by referring to the latest research papers related to the consultation content. For example, the scoring unit stores the latest research papers related to the consultation content in a database and uses them for scoring. The scoring unit can also score by referring to past cases related to the consultation content. For example, the scoring unit stores past cases related to the consultation content in a database and uses them for scoring. Furthermore, the scoring unit can score by referring to industry best practices related to the consultation content. For example, the scoring unit stores industry best practices related to the consultation content in a database and uses them for scoring. This improves the accuracy of scoring by referring to relevant literature on the consultation content. Some or all of the above processes in the scoring unit may be performed using AI, for example, or not using AI. For example, the scoring unit can input relevant literature on the consultation content into a generating AI and have the generating AI perform the improvement of scoring accuracy.

[0102] The alert unit estimates the employee's emotions and adjusts the display method of alerts based on the estimated emotions. For example, if an employee is stressed, the alert unit displays a simple and highly visible alert. For example, the alert unit captures the employee's facial expression with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expression. Also, if an employee is relaxed, the alert unit displays a more detailed alert. For example, the alert unit records the employee's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice and calculates an emotion score. Also, if an employee is anxious, the alert unit displays a reassuring alert. For example, the alert unit collects the employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for the provision of more appropriate alerts by adjusting the display method of alerts based on the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generating AI may be, but is not limited to, text generating AI (e.g., LLM) or multimodal generating AI. Some or all of the processing described above in the alert unit may be performed using AI, or not using AI. For example, the alert unit may input employee sentiment data into the generating AI and have the generating AI perform sentiment estimation.

[0103] The alert unit predicts the current alert by referring to past alert data when an alert occurs. For example, the alert unit predicts the probability of the current alert occurring based on past alert data. For example, the alert unit saves past alert data to a database and predicts the probability of the current alert occurring. The alert unit can also predict the scope of impact of the current alert based on past alert data. For example, the alert unit evaluates past alert data and predicts the scope of impact of the current alert. Furthermore, the alert unit can propose a response method for the current alert based on past alert data. For example, the alert unit evaluates past alert data and proposes a response method for the current alert. In this way, by referring to past alert data, the probability of the current alert occurring and the scope of impact can be predicted. Some or all of the above processing in the alert unit may be performed using AI, for example, or without using AI. For example, the alert unit can input past alert data into a generating AI and have the generating AI perform the prediction of the current alert.

[0104] The alert unit applies different alert methods depending on the category of the consultation content when an alert occurs. For example, the alert unit applies health-related alert methods to consultations about health. For example, the alert unit stores the consultation content in a database and applies health-related alert methods. The alert unit can also apply career-related alert methods to consultations about careers. For example, the alert unit stores the consultation content in a database and applies career-related alert methods. Furthermore, the alert unit can apply workplace environment-related alert methods to consultations about the workplace environment. For example, the alert unit stores the consultation content in a database and applies workplace environment-related alert methods. By applying different alert methods depending on the category of the consultation content, more appropriate alerts can be provided. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input the category of the consultation content into a generating AI and have the generating AI execute the application of different alert methods.

[0105] The alert unit estimates the employee's emotions and adjusts the importance of alerts based on the estimated emotions. For example, if an employee is stressed, the alert unit prioritizes displaying high-priority alerts. For example, the alert unit captures the employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Also, if an employee is relaxed, the alert unit displays normal alerts. For example, the alert unit records the employee's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice and calculates an emotion score. Also, if an employee is anxious, the alert unit prioritizes displaying reassuring alerts. For example, the alert unit collects the employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for the provision of more appropriate alerts by adjusting the importance of alerts based on the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generating AI may be, but is not limited to, text generating AI (e.g., LLM) or multimodal generating AI. Some or all of the processing described above in the alert unit may be performed using AI, or not using AI. For example, the alert unit may input employee sentiment data into the generating AI and have the generating AI perform sentiment estimation.

[0106] The alert unit analyzes changes in alerts based on the submission date of the consultation content when an alert occurs. For example, the alert unit analyzes changes in alerts based on recently submitted consultation content. For example, the alert unit stores the submission date and time of the consultation content in a database and analyzes changes in alerts based on recently submitted consultation content. The alert unit can also analyze changes in alerts based on older consultation content. For example, the alert unit evaluates the submission date and time of the consultation content and analyzes changes in alerts based on older consultation content. Furthermore, the alert unit can also analyze changes in alerts based on consultation content of moderate age. For example, the alert unit evaluates the submission date and time of the consultation content and analyzes changes in alerts based on moderate age. This allows for more appropriate responses by analyzing changes in alerts based on the submission date of the consultation content. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input the submission date and time of the consultation content into a generating AI and have the generating AI perform the analysis of changes in alerts.

[0107] The alert unit analyzes the alert when it occurs by referring to relevant market data related to the consultation content. For example, the alert unit analyzes the impact of the alert based on market data related to the consultation content. For example, the alert unit stores market data related to the consultation content in a database and analyzes the impact of the alert. The alert unit can also analyze the probability of an alert occurring based on market data related to the consultation content. For example, the alert unit evaluates market data related to the consultation content and analyzes the probability of an alert occurring. Furthermore, the alert unit can propose a response method to the alert based on market data related to the consultation content. For example, the alert unit evaluates market data related to the consultation content and proposes a response method to the alert. This allows for the analysis of the impact and probability of an alert occurring by referring to relevant market data related to the consultation content. Some or all of the above processing in the alert unit may be performed using AI, for example, or without AI. For example, the alert unit can input market data related to the consultation content into a generating AI and have the generating AI perform the alert analysis.

[0108] The information provider estimates the employee's emotions and prioritizes the information to be provided based on the estimated emotions. For example, if an employee is stressed, the provider prioritizes providing information to reduce stress. For example, the provider may capture the employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it may calculate an emotion score based on changes in facial expressions. Also, if an employee is relaxed, the provider provides normal information. For example, the provider may record the employee's voice and estimate their emotions using voice analysis technology. For example, it may analyze the tone and speed of their voice and calculate an emotion score. Also, if an employee is anxious, the provider prioritizes providing information that provides a sense of security. For example, the provider may collect the employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it may calculate an emotion score based on fluctuations in heart rate. This allows for the provision of more appropriate information by prioritizing the information to be provided based on the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the delivery unit may be performed using AI, or not using AI. For example, the delivery unit may input employee sentiment data into the generative AI and have the generative AI perform sentiment estimation.

[0109] The information provider improves the accuracy of information provision by considering the interrelationships of the consultation content. For example, if the consultation content spans multiple categories, the information provider provides information while considering the interrelationships. For example, the information provider evaluates the interrelationships of the consultation content and provides information based on the consultation content that spans multiple categories. The information provider can also provide information while considering the relevance of the consultation content if it is related. For example, the information provider evaluates the relevance of the consultation content and provides information based on the related consultation content. Furthermore, if the consultation content is independent, the information provider can provide information while considering its independence. For example, the information provider evaluates the independence of the consultation content and provides information based on the independent consultation content. As a result, the accuracy of the information provided is improved by considering the interrelationships of the consultation content. Some or all of the above processing in the information provider may be performed using AI, for example, or without using AI. For example, the information provider can input the interrelationships of the consultation content into a generating AI and have the generating AI perform the improvement of the accuracy of information provision.

[0110] The information provider takes into account the client's attribute information when providing information. For example, the provider may provide information based on the client's age. For example, the provider may store the client's age in a database and provide information based on age. The provider may also provide information based on the client's job title. For example, the provider may store the client's job title in a database and provide information based on job title. Furthermore, the provider may also provide information based on the client's years of service. For example, the provider may store the client's years of service in a database and provide information based on years of service. This improves the accuracy of the information provided by taking the client's attribute information into consideration. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the provider may input the client's attribute information into a generating AI and have the generating AI perform the information provision.

[0111] The information provider estimates the employee's emotions and adjusts the display method of the information based on the estimated emotions. For example, if an employee is stressed, the provider provides a simple and highly visible display method. For example, the provider captures the employee's facial expression with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expression. Also, if an employee is relaxed, the provider provides a display method that includes detailed information. For example, the provider records the employee's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Also, if an employee is anxious, the provider provides a display method that provides a sense of security. For example, the provider collects the employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for the provision of more appropriate information by adjusting the display method of the information based on the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the delivery unit may be performed using AI, or not using AI. For example, the delivery unit may input employee sentiment data into the generative AI and have the generative AI perform sentiment estimation.

[0112] The information provider considers the geographical distribution of the consultation content when providing information. For example, if the consultation content is concentrated in a particular area, the provider will provide information related to that area. For example, the provider may store the geographical distribution of the consultation content in a database and provide information related to that specific area. The provider may also provide information for each region if the consultation content is widely distributed. For example, the provider may evaluate the geographical distribution of the consultation content and provide information for each region. Furthermore, if the consultation content is not biased towards a particular region, the provider may provide normal information. For example, the provider may evaluate the geographical distribution of the consultation content and provide normal information for consultation content that is not biased towards a particular region. This improves the accuracy of the information provided by considering the geographical distribution of the consultation content. Some or all of the above processing in the information provider may be performed using AI, for example, or not using AI. For example, the provider may input the geographical distribution of the consultation content into a generating AI and have the generating AI perform the information provision.

[0113] The information provider improves the accuracy of the information provided by referring to relevant literature on the consultation topic. For example, the information provider provides information by referring to the latest research papers related to the consultation topic. For example, the information provider stores the latest research papers related to the consultation topic in a database and uses them for information provision. The information provider can also provide information by referring to past cases related to the consultation topic. For example, the information provider stores past cases related to the consultation topic in a database and uses them for information provision. Furthermore, the information provider can also provide information by referring to industry best practices related to the consultation topic. For example, the information provider stores industry best practices related to the consultation topic in a database and uses them for information provision. This improves the accuracy of the information provided by referring to relevant literature on the consultation topic. Some or all of the above processing in the information provider may be performed using AI, for example, or not using AI. For example, the information provider can input relevant literature on the consultation topic into a generating AI and have the generating AI perform the improvement of the accuracy of information provision.

[0114] The learning unit estimates employees' emotions and selects training data based on the estimated emotions. For example, if an employee is stressed, the learning unit prioritizes learning data related to stress reduction. For example, the learning unit captures the employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Conversely, if an employee is relaxed, the learning unit learns normal data. For example, the learning unit records the employee's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice and calculates an emotion score. Furthermore, if an employee is anxious, the learning unit prioritizes learning data that provides a sense of security. For example, the learning unit collects the employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for more appropriate learning by selecting training data based on the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit may input employee sentiment data into the generative AI and have the generative AI perform sentiment estimation.

[0115] The learning unit optimizes the learning algorithm by referring to past learning data during the learning process. For example, the learning unit optimizes the current learning algorithm based on past learning data. For example, the learning unit saves past learning data to a database and optimizes the current learning algorithm. The learning unit can also improve the accuracy of the learning algorithm based on past learning data. For example, the learning unit evaluates past learning data and improves the accuracy of the learning algorithm. Furthermore, the learning unit can improve the efficiency of the learning algorithm based on past learning data. For example, the learning unit evaluates past learning data and improves the efficiency of the learning algorithm. As a result, the accuracy and efficiency of the learning algorithm are improved by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit can input past learning data into a generating AI and have the generating AI perform the optimization of the learning algorithm.

[0116] The learning unit estimates the employee's emotions and adjusts the learning frequency based on the estimated emotions. For example, if an employee is stressed, the learning unit increases the learning frequency. For example, the learning unit captures the employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Also, if an employee is relaxed, the learning unit performs learning at a normal frequency. For example, the learning unit records the employee's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of the voice and calculates an emotion score. Also, if an employee is anxious, the learning unit adjusts the learning frequency. For example, the learning unit collects the employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for more appropriate learning by adjusting the learning frequency based on the employee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit may input employee sentiment data into the generative AI and have the generative AI perform sentiment estimation.

[0117] The learning unit weights the training data based on the submission date of the consultations during training. For example, the learning unit may weight the training data by giving more weight to recently submitted consultations. For example, the learning unit may store the submission date and time of the consultations in a database and weight the training data by giving more weight to recently submitted consultations. The learning unit may also lighten the weight of older consultations. For example, the learning unit may evaluate the submission date and time of the consultations and lighten the weight of older consultations. Furthermore, the learning unit may also appropriately weight consultations that were submitted at a moderate time. For example, the learning unit may evaluate the submission date and time of the consultations and appropriately weight consultations that were submitted at a moderate time. This allows for more appropriate training by weighting the training data based on the submission date of the consultations. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI. For example, the learning unit may input the submission date and time of the consultations into a generating AI and have the generating AI perform the weighting of the training data.

[0118] The analysis department estimates employees' emotions and adjusts the analysis method based on the estimated emotions. For example, if an employee is stressed, the analysis department provides a simple and easy-to-understand analysis method. For example, the analysis department captures the employee's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on changes in facial expressions. Also, if an employee is relaxed, the analysis department provides a detailed analysis method. For example, the analysis department records the employee's voice and estimates their emotions using voice analysis technology. For example, it analyzes the tone and speed of their voice and calculates an emotion score. Furthermore, if an employee is anxious, the analysis department provides a reassuring analysis method. For example, the analysis department collects the employee's biometric data (heart rate and skin electrical activity) with sensors and estimates their emotions using an emotion estimation algorithm. For example, it calculates an emotion score based on fluctuations in heart rate. This allows for more appropriate analysis results by adjusting the analysis method based on the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit may input employee sentiment data into the generative AI and have the generative AI perform sentiment estimation.

[0119] The analysis unit optimizes the analysis algorithm by referring to past consultation data during analysis. For example, the analysis unit optimizes the current analysis algorithm based on past consultation data. For example, the analysis unit saves past consultation data to a database and optimizes the current analysis algorithm. The analysis unit can also improve the accuracy of the analysis algorithm based on past consultation data. For example, the analysis unit evaluates past consultation data and improves the accuracy of the analysis algorithm. Furthermore, the analysis unit can improve the efficiency of the analysis algorithm based on past consultation data. For example, the analysis unit evaluates past consultation data and improves the efficiency of the analysis algorithm. As a result, the accuracy and efficiency of the analysis algorithm are improved by referring to past consultation data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input past consultation data into a generating AI and have the generating AI perform the optimization of the analysis algorithm.

[0120] The analysis department estimates employees' emotions and adjusts the frequency of analysis based on the estimated emotions. For example, if an employee is stressed, the analysis department increases the frequency of analysis. For example, the analysis department may capture an employee's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. For example, it may calculate an emotion score based on changes in facial expression. Conversely, if an employee is relaxed, the analysis department performs analysis at the normal frequency. For example, the analysis department may record an employee's voice and estimate their emotions using voice analysis technology. For example, it may analyze the tone and speed of their voice and calculate an emotion score. Furthermore, if an employee is anxious, the analysis department adjusts the frequency of analysis. For example, the analysis department may collect an employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it may calculate an emotion score based on fluctuations in heart rate. This allows for more appropriate analysis by adjusting the frequency of analysis based on the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit may input employee sentiment data into the generative AI and have the generative AI perform sentiment estimation.

[0121] The analysis department weights the analysis data based on when the consultation content was submitted. For example, the analysis department may weight the analysis data by giving more weight to recently submitted consultation content. For example, the analysis department may store the submission date and time of the consultation content in a database and weight the analysis data by giving more weight to recently submitted consultation content. The analysis department may also lighten the weight of older consultation content. For example, the analysis department may evaluate the submission date and time of the consultation content and lighten the weight of older consultation content. Furthermore, the analysis department may also appropriately weight consultation content that was submitted at a moderate time. For example, the analysis department may evaluate the submission date and time of the consultation content and appropriately weight consultation content that was submitted at a moderate time. This allows for more appropriate analysis by weighting the analysis data based on when the consultation content was submitted. Some or all of the above processing in the analysis department may be performed using AI, for example, or not using AI. For example, the analysis department may input the submission date and time of the consultation content into a generating AI and have the generating AI perform the weighting of the analysis data.

[0122] The support department estimates employees' emotions and adjusts its support methods based on those estimates. For example, if an employee is stressed, the support department provides stress-reducing support. For instance, it might capture the employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it might calculate an emotion score based on changes in facial expressions. If an employee is relaxed, the support department provides its usual support methods. For example, it might record the employee's voice and estimate their emotions using voice analysis technology. For example, it might analyze the tone and speed of their voice to calculate an emotion score. If an employee is anxious, the support department provides reassuring support. For example, it might collect the employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it might calculate an emotion score based on fluctuations in heart rate. This allows for more appropriate support to be provided by adjusting support methods based on the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the support unit may be performed using AI, or not using AI. For example, the support unit may input employee sentiment data into the generative AI and have the generative AI perform sentiment estimation.

[0123] The support unit optimizes the support algorithm by referring to past consultation data during support. For example, the support unit optimizes the current support algorithm based on past consultation data. For example, the support unit saves past consultation data to a database and optimizes the current support algorithm. The support unit can also improve the accuracy of the support algorithm based on past consultation data. For example, the support unit evaluates past consultation data and improves the accuracy of the support algorithm. Furthermore, the support unit can improve the efficiency of the support algorithm based on past consultation data. For example, the support unit evaluates past consultation data and improves the efficiency of the support algorithm. As a result, the accuracy and efficiency of the support algorithm are improved by referring to past consultation data. Some or all of the above processes in the support unit may be performed using AI, for example, or without using AI. For example, the support unit can input past consultation data into a generating AI and have the generating AI perform the optimization of the support algorithm.

[0124] The support department estimates employees' emotions and adjusts the frequency of support based on the estimated emotions. For example, if an employee is stressed, the support department increases the frequency of support. For example, the support department may capture the employee's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. For example, it may calculate an emotion score based on changes in facial expressions. Also, if an employee is relaxed, the support department provides support at the normal frequency. For example, the support department may record the employee's voice and estimate their emotions using voice analysis technology. For example, it may analyze the tone and speed of the voice and calculate an emotion score. Also, if an employee is feeling anxious, the support department adjusts the frequency of support. For example, the support department may collect the employee's biometric data (heart rate and skin electrical activity) with sensors and estimate their emotions using an emotion estimation algorithm. For example, it may calculate an emotion score based on fluctuations in heart rate. This allows for more appropriate support to be provided by adjusting the frequency of support based on the employee's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the processing described above in the support unit may be performed using AI, or not using AI. For example, the support unit may input employee sentiment data into the generative AI and have the generative AI perform sentiment estimation.

[0125] The support department weights support data based on when the consultation content was submitted. For example, the support department may weight support data by giving more weight to recently submitted consultations. For example, the support department may store the submission date and time of the consultation content in a database and weight the support data by giving more weight to recently submitted consultations. The support department may also lighten the weight of older consultations. For example, the support department may evaluate the submission date and time of the consultation content and lighten the weight of older consultations. Furthermore, the support department may also appropriately weight consultations that were submitted at a moderate time. For example, the support department may evaluate the submission date and time of the consultation content and appropriately weight consultations that were submitted at a moderate time. In this way, by weighting support data based on when the consultation content was submitted, more appropriate support can be provided. Some or all of the above processing in the support department may be performed using AI, for example, or not using AI. For example, the support department may input the submission date and time of the consultation content into a generating AI and have the generating AI perform the weighting of the support data.

[0126] The support department improves the accuracy of its support by referring to relevant literature related to the consultation content. For example, the support department provides support by referring to the latest research papers related to the consultation content. For example, the support department stores the latest research papers related to the consultation content in a database and uses them for support. The support department can also provide support by referring to past cases related to the consultation content. For example, the support department stores past cases related to the consultation content in a database and uses them for support. Furthermore, the support department can provide support by referring to industry best practices related to the consultation content. For example, the support department stores industry best practices related to the consultation content in a database and uses them for support. This improves the accuracy of support by referring to relevant literature related to the consultation content. Some or all of the above processes in the support department may be performed using AI, for example, or not using AI. For example, the support department can input relevant literature related to the consultation content into a generating AI and have the generating AI perform the improvement of support accuracy.

[0127] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0128] The reception department can analyze an employee's past consultation history to select the most appropriate method of handling their inquiry. For example, it can prioritize suggesting methods the employee has used in the past (chat, voice, etc.). It can also automatically suggest relevant topics based on the content of past consultations. Furthermore, it can prompt employees to seek consultation at appropriate times based on their past consultation frequency. In this way, the system can select the most suitable method of handling an employee's inquiry by analyzing their past consultation history.

[0129] The analysis unit can be equipped with an analysis function that statistically analyzes employees' health status and consultation content. For example, regression analysis can be used to analyze the relationship between employees' health status and consultation content. Cluster analysis can also be used to group employees' consultation content. Furthermore, time series analysis can be used to track changes in employees' health status. In this way, by statistically analyzing employees' health status and consultation content, the overall health status of the company can be understood.

[0130] The service provider can include a support unit that analyzes employee consultation trends and provides preventative support. For example, it can analyze the frequency of employee consultations and evaluate whether specific problems occur frequently. It can also use trend analysis to understand the trends in employee consultations. Furthermore, it can use pattern recognition to identify commonalities in employee consultations. This allows for the analysis of employee consultation trends and the provision of preventative support, thereby supporting employee health.

[0131] The reception desk can estimate an employee's emotions and adjust the timing of consultations based on that estimation. For example, if an employee is feeling stressed, they can be contacted immediately. If an employee is relaxed, they can be contacted at an appropriate time. Furthermore, if an employee is busy, a reminder can be set so they can contact the office later. By adjusting the timing of consultations based on an employee's emotions, consultations can be received at a more appropriate time.

[0132] The reception desk can filter inquiries based on employees' current work situations and areas of interest. For example, it can prioritize inquiries related to an employee's current project status. It can also suggest appropriate consultation topics based on an employee's areas of interest. Furthermore, it can filter specific inquiries based on an employee's work environment. This allows for priority reception of relevant inquiries by filtering based on an employee's current work situation and areas of interest.

[0133] The reception desk can estimate the emotions of employees and prioritize the types of consultations it receives based on those estimates. For example, if an employee is feeling stressed, it will prioritize urgent consultations. If an employee is relaxed, it will prioritize regular consultations. Furthermore, if an employee is feeling anxious, it can prioritize consultations that provide reassurance. By prioritizing consultations based on employees' emotions, it is possible to prioritize urgent consultations.

[0134] The reception desk can prioritize inquiries based on the employee's geographical location. For example, if an employee is in a specific office, inquiries related to that office will be prioritized. Similarly, if an employee is working remotely, inquiries related to remote work will be prioritized. Furthermore, if an employee is on a business trip, inquiries related to their destination will be prioritized. This allows for more appropriate inquiries to be received by prioritizing those that are relevant to the employee's geographical location.

[0135] The analysis unit can estimate employees' emotions and adjust the presentation of the analysis based on those estimated emotions. For example, if an employee is stressed, it provides simple and easy-to-understand analysis results. If an employee is relaxed, it provides detailed analysis results. Furthermore, if an employee is anxious, it can provide reassuring analysis results. By adjusting the presentation of the analysis based on employees' emotions, it can provide more appropriate analysis results.

[0136] The analysis unit can adjust the level of detail in the analysis based on the importance of the consultation content. For example, it can perform a detailed analysis for consultations of high importance, a concise analysis for consultations of low importance, and an analysis of appropriate detail for consultations of moderate importance. By adjusting the level of detail in the analysis based on the importance of the consultation content, it is possible to perform a detailed analysis for important consultations.

[0137] The scoring unit can estimate employees' emotions and adjust the scoring criteria based on those estimates. For example, if an employee is stressed, stress reduction scoring criteria can be applied. If an employee is relaxed, the normal scoring criteria can be applied. Furthermore, if an employee is anxious, reassuring scoring criteria can be applied. By adjusting the scoring criteria based on employees' emotions, more appropriate scoring results can be provided.

[0138] The following briefly describes the processing flow for example form 2.

[0139] Step 1: The reception desk receives inquiries from employees. These inquiries may include work-related questions, health-related questions, and personal issues. The reception desk provides an interface for employees to make anonymous inquiries, and includes features such as forms for entering inquiries, chatbots, voice input, and video calls. Step 2: The analysis unit analyzes the consultation content received by the reception unit. The analysis is performed using methods such as text analysis, sentiment analysis, and pattern recognition. For example, text analysis is used to extract keywords from the consultation content and identify the category of the consultation content. Sentiment analysis is used to identify the emotions contained in the consultation content, and pattern recognition is used to compare it with past consultation data and identify similar consultation content. Step 3: The scoring unit scores the mental and physical state based on the consultation content analyzed by the analysis unit. Scoring is performed based on the score range, evaluation criteria, and algorithm used. For example, the employee's mental and physical state is scored on a scale from 0 to 100, and an alert is generated if the score is low. Step 4: The alerting unit automatically generates an alert if the score is low, determined by the scoring unit. The alert is generated based on factors such as the score threshold, notification method, and alert type. For example, an alert is generated and the HR department is notified if the score is below 50. Step 5: The Service Department provides information to the Human Resources Department based on alerts generated by the Alert Department. This information includes the format of the report, the notification method, and the type of information to be provided. For example, when an alert occurs, the Human Resources Department is notified by email and a report containing the details of the alert is automatically generated.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] For example, each of the multiple elements, including the reception unit, analysis unit, scoring unit, alert unit, and provision unit, is implemented by at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and provides an interface for receiving employee consultations. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the received consultations. The scoring unit is implemented by the specific processing unit 290 of the data processing unit 12 and scores the mental and physical state based on the analysis results. The alert unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates an alert when the score is low. The provision unit is implemented by the control unit 46A of the smart device 14 and provides information to the human resources department based on the alerts. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0144] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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).

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] For example, each of the multiple elements, including the reception unit, analysis unit, scoring unit, alert unit, and provision unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and provides an interface for receiving employee consultations. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the received consultations. The scoring unit is implemented by the specific processing unit 290 of the data processing unit 12 and scores the mental and physical state based on the analysis results. The alert unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates an alert when the score is low. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides information to the human resources department based on the alerts. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0160] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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).

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.).

[0172] 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.

[0173] 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.

[0174] 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.

[0175] For example, each of the multiple elements, including the reception unit, analysis unit, scoring unit, alert unit, and provision unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and provides an interface for receiving employee consultations. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the received consultations. The scoring unit is implemented by the specific processing unit 290 of the data processing unit 12 and scores the mental and physical state based on the analysis results. The alert unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates an alert when the score is low. The provision unit is implemented by the control unit 46A of the headset terminal 314 and provides information to the human resources department based on the alerts. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0176] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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).

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.).

[0189] 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.

[0190] 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.

[0191] 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.

[0192] For example, each of the multiple elements, including the reception unit, analysis unit, scoring unit, alert unit, and provision unit, is implemented by at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and provides an interface for receiving employee consultations. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the received consultations. The scoring unit is implemented by the specific processing unit 290 of the data processing unit 12 and scores the mental and physical state based on the analysis results. The alert unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates an alert when the score is low. The provision unit is implemented by the control unit 46A of the robot 414 and provides information to the human resources department based on the alerts. The correspondence between each unit and the devices and control units is not limited to the example described above and can be changed in various ways.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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."

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] (Note 1) The reception department handles inquiries from employees, An analysis unit analyzes the content of consultations received by the reception unit, A scoring unit that scores the mental and physical state based on the consultation content analyzed by the aforementioned analysis unit, The scoring unit automatically generates an alert when the score is low, The system includes a provisioning unit that provides information to the Human Resources Department based on alerts generated by the alerting unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, It has a learning unit that learns from past consultation data. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, The company has an analysis department that statistically analyzes the health status and consultation content of its employees. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, We have a support department that analyzes employee consultation trends and provides preventative support. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is We estimate the emotions of our employees and adjust the timing of consultations based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is Analyze employees' past consultation history to select the most suitable method of handling inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is When receiving inquiries, we filter them based on the employee's current work situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is The system estimates the emotions of employees and prioritizes the types of inquiries to be received based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is When receiving inquiries, the system prioritizes inquiries with high relevance based on the employee's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When receiving inquiries, the system analyzes employees' social media activity and identifies relevant inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, We estimate the emotions of employees and adjust the representation of the analysis based on the estimated emotions of the employees. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During analysis, the level of detail is adjusted based on the importance of the consultation content. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the consultation content. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, The system estimates employee sentiment and adjusts the length of the analysis based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, During the analysis, the priority of the analysis will be determined based on when the consultation content was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the consultation content. The system described in Appendix 1, characterized by the features described herein. (Note 17) The scoring unit is, The system estimates employee sentiment and adjusts scoring criteria based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 18) The scoring unit is, When scoring, consider the interrelationships between the consultation content to improve the accuracy of the scoring. The system described in Appendix 1, characterized by the features described herein. (Note 19) The scoring unit is, When scoring, the client's attribute information is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 20) The scoring unit is, The system estimates employee sentiment and adjusts the order in which scoring results are displayed based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The scoring unit is, When scoring, the geographical distribution of the consultation topics will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 22) The scoring unit is, When scoring, we improve the accuracy of the scoring by referring to relevant literature related to the consultation content. The system described in Appendix 1, characterized by the features described herein. (Note 23) The alert unit is, It estimates employee sentiment and adjusts how alerts are displayed based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The alert unit is, When an alert occurs, past alert data is referenced to predict the current alert. The system described in Appendix 1, characterized by the features described herein. (Note 25) The alert unit is, When an alert is triggered, different alert methods are applied depending on the category of the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 26) The alert unit is, It estimates employee sentiment and adjusts the importance of alerts based on the estimated employee sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The alert unit is, When an alert is triggered, we analyze how the alert changes based on when the consultation details were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 28) The alert unit is, When an alert is triggered, the system analyzes the alert by referring to relevant market data related to the inquiry. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, The system estimates employee sentiment and prioritizes the information provided based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned supply unit is, When providing information, we will improve the accuracy of the information provided by considering the interrelationships between the consultation topics. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned supply unit is, When providing information, we will take into consideration the attributes of the person seeking advice. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned supply unit is, We estimate employee sentiment and adjust how information is displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned supply unit is, When providing information, we will take into account the geographical distribution of the consultation topics. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned supply unit is, When providing information, we will refer to relevant literature related to the consultation content to improve the accuracy of the information provided. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned learning unit, The system estimates the emotions of employees and selects training data based on the estimated emotions of the employees. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned learning unit, It estimates employee emotions and adjusts the frequency of learning based on the estimated employee emotions. The system described in Appendix 2, characterized by the features described herein. (Note 38) The aforementioned learning unit, During the learning process, the learning data is weighted based on when the consultation content was submitted. The system described in Appendix 2, characterized by the features described herein. (Note 39) The aforementioned analysis unit is We estimate employee sentiment and adjust the analysis method based on the estimated employee sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned analysis unit is During analysis, the analysis algorithm is optimized by referring to past consultation data. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned analysis unit is We estimate employee sentiment and adjust the frequency of analysis based on the estimated employee sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 42) The aforementioned analysis unit is During the analysis, the analysis data will be weighted based on when the consultation content was submitted. The system described in Appendix 3, characterized by the features described herein. (Note 43) The aforementioned support unit is Estimate employees' emotions and adjust support methods based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 44) The aforementioned support unit is During support, the support algorithm is optimized by referring to past consultation data. The system described in Appendix 4, characterized by the features described herein. (Note 45) The aforementioned support unit is Estimate employee emotions and adjust the frequency of support based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 46) The aforementioned support unit is During support, support data is weighted based on when the consultation details were submitted. The system described in Appendix 4, characterized by the features described herein. (Note 47) The aforementioned support unit is When providing support, we refer to relevant literature related to the consultation topic to improve the accuracy of the support. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0212] 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 reception department handles inquiries from employees, An analysis unit analyzes the content of consultations received by the reception unit, A scoring unit that scores the mental and physical state based on the consultation content analyzed by the aforementioned analysis unit, The scoring unit automatically generates an alert when the score is low, The system includes a provisioning unit that provides information to the Human Resources Department based on alerts generated by the alerting unit. A system characterized by the following features.

2. The aforementioned analysis unit, It has a learning unit that learns from past consultation data. The system according to feature 1.

3. The aforementioned analysis unit, The company has an analysis department that statistically analyzes the health status and consultation content of its employees. The system according to feature 1.

4. The aforementioned supply unit is, We have a support department that analyzes employee consultation trends and provides preventative support. The system according to feature 1.

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

6. The aforementioned reception unit is Analyze employees' past consultation history to select the most suitable method of handling inquiries. The system according to feature 1.

7. The aforementioned reception unit is When receiving inquiries, we filter them based on the employee's current work situation and areas of interest. The system according to feature 1.

8. The aforementioned reception unit is The system estimates the emotions of employees and prioritizes the types of inquiries to be received based on those estimated emotions. The system according to feature 1.

9. The aforementioned reception unit is When receiving inquiries, the system prioritizes inquiries with high relevance based on the employee's geographical location. The system according to feature 1.

10. The aforementioned reception unit is When receiving inquiries, the system analyzes employees' social media activity and identifies relevant inquiries. The system according to feature 1.

Images