System

Abstract

To provide a system according to an embodiment, capable of gripping a mental condition of an employee in real time, and quickly performing an appropriate measurement.SOLUTION: A system according to an embodiment comprises an analysis unit, a scoring unit, an integration unit and an escalation unit. The analysis unit analyzes a chat log or email of an employee. The scoring unit scores a negative word extracted by the analysis unit. The integration unit integrates data of a pulse survey. The escalation unit determines an escalation destination on the basis of the data obtained by the integration unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to grasp the mental state of employees in real time and take appropriate measures quickly.

[0005] The system according to the embodiment aims to grasp the mental state of employees in real time and take appropriate measures quickly. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a scoring unit, an integration unit, and an escalation unit. The analysis unit analyzes chat logs or emails of employees. The scoring unit scores negative words extracted by the analysis unit. The integration unit integrates pulse survey data. The escalation unit determines the escalation destination based on the data obtained by the integration unit. Effect of the Invention

[0007] The system according to the embodiment can grasp the mental state of employees in real time and take appropriate measures quickly. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The system for detecting the health and mental state of employees in real time according to an embodiment of the present invention is a mechanism that utilizes generation AI to detect the health and mental state of employees in real time, and to prevent the outflow of human resources and improve mental health at an early stage. This system analyzes employees' chat logs and emails using generation AI, extracts negative words, and scores them. For example, if an employee uses negative words such as "tired" or "stressed," a score is calculated based on the frequency and context of the words. Next, the system combines this with other data such as pulse surveys to comprehensively grasp the employee's mental state. A pulse survey is a simple questionnaire that is periodically administered to employees to measure the employee's satisfaction and stress level. The generation AI integrates these data and evaluates the employee's mental state in real time. In addition, the system determines the most appropriate escalation destination for each score and content. For example, if the score is high, the system notifies the superior or human resources department and takes action early. In addition, if certain negative words appear frequently, the system escalates to a professional counselor. In this way, mental problems of employees can be discovered early and appropriate action can be taken. This system allows employees' health and mental states to be grasped in real time, preventing the loss of talent and improving their mental health. For example, if an employee feels stressed, mental health problems can be prevented by receiving counseling early on. It is also expected that employee satisfaction will increase and the productivity of the entire company will improve. As a result, a system that detects employees' health and mental states in real time can grasp the health and mental states of employees in real time, preventing the loss of talent and improving their mental health.

[0029] A system for detecting an employee's health and mental state in real time according to an embodiment includes an analysis unit, a scoring unit, an integration unit, and an escalation unit. The analysis unit analyzes the employee's chat log and email. The employee's chat log and email include, for example, business interactions and personal messages, but are not limited to such examples. The analysis unit extracts negative words from the chat log and email using, for example, a generation AI. The generation AI can analyze the contents of the chat log and email using a text generation AI (for example, LLM) and extract negative words. The analysis unit can also analyze the context of the chat log and email using the generation AI and calculate the frequency of negative words. For example, the generation AI extracts negative words such as "tired" and "stressed" in the chat log and email and calculates their frequency. The scoring unit scores the negative words extracted by the analysis unit using the generation AI. Scoring is performed based on, for example, the frequency and context of the negative words, but is not limited to such examples. For example, the scoring unit uses the generation AI to calculate a score based on the frequency of negative words. The scoring unit can also use the generation AI to calculate a score based on the context of negative words. For example, the generation AI analyzes the context of chat logs and emails, evaluates the importance of negative words, and calculates the score. The integration unit uses the generation AI to integrate data such as pulse surveys. The integration is performed, for example, by integrating the results of the pulse survey, chat logs, and email data, but is not limited to such an example. For example, the integration unit uses the generation AI to collect the results of the pulse survey and comprehensively grasp the mental state of the employee. The integration unit can also use the generation AI to integrate the chat log and email data and evaluate the mental state of the employee. For example, the generation AI integrates the results of the pulse survey with the chat log and email data to evaluate the mental state of the employee in real time. The escalation unit uses the generation AI to determine the escalation destination based on the data obtained by the integration unit. The escalation is performed, for example, based on the score and content, but is not limited to such an example.For example, the escalation unit uses the generation AI to notify superiors or the human resources department if the score is high, and escalate to a professional counselor if certain negative words appear frequently. In this way, the system for detecting the health and mental state of employees in real time according to the embodiment can grasp the health and mental state of employees in real time, prevent the loss of human resources, and improve their mental health.

[0030] The analysis unit analyzes the chat logs and emails of employees. The chat logs and emails of employees include, for example, business interactions and personal messages, but are not limited to such examples. The analysis unit extracts negative words from the chat logs and emails using, for example, a generation AI. The generation AI can analyze the contents of the chat logs and emails and extract negative words using a text generation AI (for example, LLM). The analysis unit can also analyze the context of the chat logs and emails using the generation AI and calculate the frequency of negative words. For example, the generation AI extracts negative words such as "tired" and "stressed" in the chat logs and emails and calculates their frequency. Furthermore, the analysis unit utilizes natural language processing technology to analyze the contents of the employee's chat logs and emails in detail. Specifically, morphological analysis and grammatical analysis are performed to deepen understanding of the context. For example, morphological analysis is used to identify the part of speech of each word, and grammatical analysis is used to grasp the structure of the sentence. This makes it possible to understand the meaning based on the context, rather than simply extracting words. Furthermore, the analysis unit introduces emotion analysis technology to grasp employees' emotions more accurately. Using emotion analysis technology, emotions expressed in chat logs and emails can be classified into three categories: positive, negative, and neutral, and their intensity can be evaluated. For example, the emotion evaluation will be different if a sentence containing the word "tired" is used in a positive context overall than if it is used in a negative context. In this way, the analysis unit can analyze employees' chat logs and emails from multiple angles and grasp employees' health and mental states more accurately.

[0031] The scoring unit uses the generation AI to score the negative words extracted by the analysis unit. Scoring is performed, for example, based on the frequency and context of the negative words, but is not limited to such examples. For example, the scoring unit uses the generation AI to calculate a score based on the frequency of the negative words. The scoring unit can also use the generation AI to calculate a score based on the context of the negative words. For example, the generation AI analyzes the context of chat logs and emails, evaluates the importance of negative words, and calculates the score. Furthermore, the scoring unit takes into account multiple factors to comprehensively evaluate the health and mental state of employees. For example, the evaluation can include not only the frequency of negative words, but also the frequency of positive words and the balance of positive and negative in the context. This makes it possible to grasp the overall trend of emotions rather than simply counting negative words. In addition, the scoring unit can detect abnormal fluctuations by referring to the employee's past data and comparing it with the current state. For example, if the frequency of negative words has increased sharply compared to data from the past few months, it can be determined that the employee is likely to be feeling stressed. In this way, the scoring unit can evaluate an employee's health and mental state from multiple angles and calculate a score in real time.

[0032] The integration unit integrates data such as pulse surveys using the generation AI. The integration is performed, for example, by integrating the results of the pulse survey, chat logs, and email data, but is not limited to such examples. For example, the integration unit uses the generation AI to collect the results of the pulse survey and comprehensively grasp the mental state of the employee. The integration unit can also use the generation AI to integrate chat log and email data to evaluate the mental state of the employee. For example, the generation AI integrates the results of the pulse survey with the chat log and email data to evaluate the mental state of the employee in real time. Furthermore, the integration unit can utilize other data sources to more accurately evaluate the health and mental state of the employee. For example, by integrating the employee's attendance status, work performance data, and even the results of health checkups, a more comprehensive evaluation is possible. This allows the employee's health and mental state to be understood from multiple angles, and abnormal fluctuations and risks can be detected early. In addition, the integration unit performs filtering and cleaning to ensure the quality and reliability of the data in the data integration process. For example, the accuracy of the evaluation can be improved by removing noise and missing data and using only reliable data. In this way, the Integration Department integrates multiple data sources and comprehensively evaluates employees' health and mental state, enabling real-time situation assessment and early response.

[0033] The escalation unit uses the generation AI to determine the escalation destination based on the data obtained by the integration unit. Escalation is performed, for example, based on the score and the content, but is not limited to such examples. For example, the escalation unit uses the generation AI to notify the superior or the human resources department when the score is high, and escalate to a professional counselor when specific negative words appear frequently. As a result, the system for detecting the health and mental state of employees in real time according to the embodiment can grasp the health and mental state of employees in real time, prevent the outflow of human resources, and improve mental aspects. Furthermore, the escalation unit realizes a quick and efficient response by automating the escalation process. For example, the generation AI can determine the priority of escalation based on the score and the content, and automatically select the optimal escalation destination. In addition, the escalation unit can record the history of escalation and use it for later analysis and improvement. For example, the results of past escalations and the effects of responses can be analyzed, and the standards and processes of escalation can be continuously improved. In this way, the escalation department can support employees' mental health and maintain the health of the entire organization by understanding employees' health and mental state in real time and taking appropriate escalation measures.

[0034] The scoring unit can calculate the score based on the frequency or context of negative words. The scoring unit, for example, calculates the score based on the frequency of negative words. For example, the scoring unit uses the generation AI to calculate the frequency of appearance of negative words such as "tired" and "stressed" in chat logs and emails, and calculates the score based on the frequency. The scoring unit can also calculate the score based on the context of negative words. For example, the scoring unit uses the generation AI to analyze the context of chat logs and emails, evaluate the importance of negative words, and calculate the score. In this way, the mental state of employees can be more accurately evaluated by calculating the score based on the frequency and context of negative words. Part or all of the above-mentioned processing in the scoring unit may be performed, for example, using AI, or may be performed without using AI. For example, the scoring unit can use the generation AI to calculate the frequency of appearance of negative words such as "tired" and "stressed" in chat logs and emails, and calculate the score based on the frequency.

[0035] The integration unit collects the results of the pulse survey and can comprehensively grasp the mental state of the employee. The integration unit, for example, collects the results of the pulse survey and comprehensively grasps the mental state of the employee. The pulse survey is a simple questionnaire that is periodically administered to employees, and measures the satisfaction and stress level of the employee. For example, the integration unit uses a generation AI to collect the results of the pulse survey and comprehensively grasp the mental state of the employee. The integration unit can also use a generation AI to integrate the results of the pulse survey with other data and evaluate the mental state of the employee in real time. For example, the integration unit uses a generation AI to integrate the results of the pulse survey with chat log and email data and evaluate the mental state of the employee in real time. This allows for more accurate evaluation by collecting the results of the pulse survey and comprehensively grasping the mental state of the employee. Part or all of the above-mentioned processing in the integration unit may be performed, for example, using AI, or may be performed without using AI. For example, the integration unit uses a generation AI to collect the results of the pulse survey and comprehensively grasp the mental state of the employee.

[0036] The escalation unit can determine the escalation destination based on the score or the content. The escalation unit determines the escalation destination based on the score, for example. For example, the escalation unit uses the generation AI to notify a superior or a human resources department when the score is high, and responds promptly. The escalation unit can also determine the escalation destination based on the content. For example, the escalation unit uses the generation AI to escalate to a professional counselor when a specific negative word appears frequently. This allows for a quick and appropriate response by determining the most appropriate escalation destination based on the score or the content. Some or all of the above-mentioned processing in the escalation unit may be performed, for example, using AI, or may be performed without using AI. For example, the escalation unit uses the generation AI to notify a superior or a human resources department when the score is high, and responds promptly.

[0037] The escalation unit can notify a superior or the human resources department when the score is high, and escalate to a professional counselor when a specific negative word appears frequently. The escalation unit, for example, notifies a superior or the human resources department when the score is high. For example, the escalation unit uses a generation AI to notify a superior or the human resources department when the score is high, and responds early. The escalation unit can also escalate to a professional counselor when a specific negative word appears frequently. For example, the escalation unit uses a generation AI to escalate to a professional counselor when a specific negative word appears frequently. This makes it possible to detect and respond to mental problems of employees early by performing appropriate escalation when the score is high or when a specific negative word appears frequently. Some or all of the above-mentioned processing in the escalation unit may be performed, for example, using AI, or may be performed without using AI. For example, the escalation unit can use a generation AI to notify a superior or the human resources department when the score is high, and respond early.

[0038] The analysis unit can analyze the employee's past chat logs and email history and select an analysis method. The analysis unit determines the focus of the analysis, for example, based on negative words frequently used by the employee in the past. For example, the analysis unit uses a generation AI to analyze the employee's past chat logs and email history and extracts frequently used negative words. Based on the result, the analysis unit can determine the focus of the analysis. In addition, if negative words appear frequently in a specific time period from the employee's past chat logs, the analysis unit can also focus on that time period for analysis. For example, the analysis unit uses a generation AI to analyze the employee's past chat logs and check whether negative words appear frequently in a specific time period. Based on the result, the analysis unit can focus on that time period for analysis. In addition, the analysis unit can analyze the employee's email history and prioritize analysis of negative words related to a specific project or work. For example, the analysis unit uses a generation AI to analyze the employee's email history and extracts negative words related to a specific project or work. Based on the result, the analysis unit can prioritize analysis. This allows the optimal analysis method to be selected by analyzing the employee's past chat logs and email history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use a generation AI to analyze the employee's past chat logs and email history and select the optimal analysis method.

[0039] The analysis unit can perform filtering based on the employee's current project and work content during analysis. The analysis unit, for example, prioritizes analysis of chat logs and emails related to the employee's current project. For example, the analysis unit uses the generation AI to extract chat logs and emails related to the employee's current project and prioritizes analysis of them. The analysis unit can also filter logs and emails containing specific keywords based on the employee's work content. For example, the analysis unit uses the generation AI to extract chat logs and emails containing keywords related to the employee's work content and filters them. Furthermore, the analysis unit can adjust the focus of the analysis according to the progress of the employee's project. For example, the analysis unit uses the generation AI to grasp the progress of the employee's project and adjust the focus of the analysis according to the progress. This allows more relevant data to be analyzed by filtering based on the employee's current project and work content. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform filtering based on the employee's current project and work content using the generation AI.

[0040] During the analysis, the analysis unit can prioritize the analysis of highly relevant logs and emails by taking into account the geographical location information of the employee. For example, when an employee is in a specific area, the analysis unit prioritizes the analysis of logs and emails related to that area. For example, the analysis unit uses a generation AI to acquire the geographical location information of the employee, extracts logs and emails related to that area, and analyzes them preferentially. In addition, when an employee is on a business trip, the analysis unit can also prioritize the analysis of logs and emails related to the business trip destination. For example, the analysis unit uses a generation AI to acquire the geographical location information of the employee, extracts logs and emails related to the business trip destination, and analyzes them preferentially. In addition, when an employee is working remotely, the analysis unit can also prioritize the analysis of logs and emails related to the home or remote work destination. For example, the analysis unit uses a generation AI to acquire the geographical location information of the employee, extracts logs and emails related to the home or remote work destination, and analyzes them preferentially. As a result, more relevant data can be analyzed by taking into account the geographical location information of the employee. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can use generative AI to prioritize analysis of highly relevant logs and emails taking into account employees' geographic location information.

[0041] During the analysis, the analysis unit can analyze the employee's social media activity and analyze related logs and emails. For example, if the employee posts negatively on social media, the analysis unit preferentially analyzes logs and emails related to the content. For example, the analysis unit uses the generation AI to analyze the employee's social media activity, extracts negative posts, and preferentially analyzes logs and emails related to the content. The analysis unit can also analyze logs and emails related to a specific topic from the employee's social media activity. For example, the analysis unit uses the generation AI to analyze the employee's social media activity, extracts logs and emails related to a specific topic, and analyzes them. Furthermore, the analysis unit can adjust the timing of the analysis based on the time period during which the employee is active on social media. For example, the analysis unit uses the generation AI to analyze the time period during which the employee is active on social media, and adjusts the timing of the analysis based on the time period. This allows more relevant data to be analyzed by analyzing the employee's social media activity. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analytics department can use generative AI to analyze employees' social media activity and analyze related logs and emails.

[0042] The scoring unit can adjust the detail level of the score based on the importance of the negative words at the time of scoring. For example, when many negative words with high importance are included, the scoring unit displays a detailed scoring result. For example, the scoring unit uses the generation AI to analyze the contents of the chat log or email, and when many negative words with high importance are included, the scoring unit displays the detailed scoring result. In addition, the scoring unit can also display a simplified scoring result when many negative words with low importance are included. For example, the scoring unit uses the generation AI to analyze the contents of the chat log or email, and when many negative words with low importance are included, the scoring unit displays the simplified scoring result. In addition, the scoring unit can dynamically adjust the detail level of the scoring according to the importance of the negative words. For example, the scoring unit uses the generation AI to analyze the contents of the chat log or email, and dynamically adjust the detail level of the scoring according to the importance of the negative words. This allows for a more accurate scoring result to be provided by adjusting the detail level of the score based on the importance of the negative words. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can use a generating AI to analyze the contents of chat logs and emails and adjust the detail level of the score based on the importance of negative words.

[0043] The scoring unit can apply different scoring algorithms depending on the category of the negative word at the time of scoring. For example, the scoring unit applies a stress-specific scoring algorithm to negative words related to stress. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, extracts negative words related to stress, and applies a stress-specific scoring algorithm to the words. The scoring unit can also apply a fatigue-specific scoring algorithm to negative words related to fatigue. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, extracts negative words related to fatigue, and applies a fatigue-specific scoring algorithm to the words. Furthermore, the scoring unit can also apply a dissatisfaction-specific scoring algorithm to negative words related to dissatisfaction. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, extracts negative words related to dissatisfaction, and applies a dissatisfaction-specific scoring algorithm to the words. This makes it possible to provide more accurate scoring results by applying different scoring algorithms depending on the category of the negative word. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit may use a generating AI to analyze the contents of chat logs and emails, and apply different scoring algorithms depending on the category of negative words.

[0044] The scoring unit can determine the priority of the score based on the appearance time of the negative word at the time of scoring. For example, the scoring unit assigns a high priority to a negative word that has appeared recently and reflects it in the scoring result. For example, the scoring unit uses a generation AI to analyze the contents of a chat log or an email, extracts a negative word that has appeared recently, assigns a high priority to the word, and reflects it in the scoring result. The scoring unit can also assign a high priority to a negative word that has appeared frequently in the past and reflects it in the scoring result. For example, the scoring unit uses a generation AI to analyze the contents of a chat log or an email, extracts a negative word that has appeared frequently in the past, assigns a high priority to the word, and reflects it in the scoring result. Furthermore, the scoring unit can dynamically adjust the priority of the score based on the appearance time of the negative word. For example, the scoring unit uses a generation AI to analyze the contents of a chat log or an email, and dynamically adjusts the priority of the score based on the appearance time of the negative word. This allows more important data to be scored preferentially by determining the priority of the score based on the time when the negative words appeared. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can use a generating AI to analyze the contents of chat logs and emails and determine the priority of the score based on the time when the negative words appeared.

[0045] The scoring unit can adjust the order of scores based on the relevance of negative words during scoring. For example, the scoring unit assigns a high score to negative words with high relevance and reflects it in the scoring result. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, extracts negative words with high relevance, assigns a high score to the words, and reflects it in the scoring result. The scoring unit can also assign a low score to negative words with low relevance and reflect it in the scoring result. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, extracts negative words with low relevance, assigns a low score to the words, and reflects it in the scoring result. Furthermore, the scoring unit can dynamically adjust the order of scores based on the relevance of negative words. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, and dynamically adjusts the order of scores based on the relevance of negative words. This makes it possible to provide a more accurate scoring result by adjusting the order of scores based on the relevance of negative words. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit may use a generating AI to analyze the contents of chat logs and emails and adjust the order of scores based on the relevance of negative words.

[0046] The integration unit can adjust the level of detail of the integration based on the importance of the pulse survey results at the time of integration. For example, the integration unit integrates pulse survey results with high importance in detail to provide a deep analysis. For example, the integration unit uses a generation AI to analyze the pulse survey results and integrate the results with high importance in detail. The integration unit can also simplify and integrate the results of pulse surveys with low importance so that they can be understood quickly. For example, the integration unit uses a generation AI to analyze the pulse survey results and simplify and integrate the results with low importance. Furthermore, the integration unit can dynamically adjust the level of detail of the integration according to the importance of the pulse survey results. For example, the integration unit uses a generation AI to analyze the pulse survey results and dynamically adjust the level of detail of the integration according to the importance. As a result, by adjusting the level of detail of the integration based on the importance of the pulse survey results, a more accurate integration result can be provided. A part or all of the above-mentioned processing in the integration unit may be performed, for example, using AI, or may be performed without using AI. For example, the integrator can use generative AI to adjust the granularity of the integration based on the importance of the pulse survey results.

[0047] The integration unit can apply different integration algorithms depending on the category of the pulse survey at the time of integration. For example, the integration unit applies an integration algorithm dedicated to stress to the result of the pulse survey related to stress. For example, the integration unit uses a generation AI to analyze the result of the pulse survey and applies an integration algorithm dedicated to stress to the result related to stress. The integration unit can also apply an integration algorithm dedicated to fatigue to the result of the pulse survey related to fatigue. For example, the integration unit uses a generation AI to analyze the result of the pulse survey and applies an integration algorithm dedicated to fatigue to the result related to fatigue. Furthermore, the integration unit can also apply an integration algorithm dedicated to dissatisfaction to the result of the pulse survey related to dissatisfaction. For example, the integration unit uses a generation AI to analyze the result of the pulse survey and applies an integration algorithm dedicated to dissatisfaction to the result related to dissatisfaction. In this way, by applying different integration algorithms depending on the category of the pulse survey, more accurate integration results can be provided. Part or all of the above-mentioned processing in the integration unit may be performed using, for example, AI, or may be performed without using AI. For example, the integration unit can use a generation AI to apply different integration algorithms depending on the category of the pulse survey.

[0048] The integration unit can determine the priority of integration based on the implementation time of the pulse survey at the time of integration. The integration unit, for example, prioritizes integration of the results of the most recently implemented pulse survey. For example, the integration unit uses the generation AI to analyze the results of the pulse survey and prioritizes integration of the most recently implemented results. The integration unit can also prioritize integration of the latest results while referring to the results of the pulse surveys implemented in the past. For example, the integration unit uses the generation AI to analyze the results of the pulse survey and prioritizes integration of the latest results while referring to the past results. Furthermore, the integration unit can dynamically adjust the priority of integration based on the implementation time of the pulse survey. For example, the integration unit uses the generation AI to analyze the results of the pulse survey and dynamically adjust the priority of integration based on the implementation time. As a result, by determining the priority of integration based on the implementation time of the pulse survey, more recent data can be prioritized for integration. Part or all of the above-mentioned processing in the integration unit may be performed, for example, using AI, or may be performed without using AI. For example, the integration unit can use the generation AI to determine the priority of integration based on the implementation time of the pulse survey.

[0049] The integration unit can adjust the order of integration based on the relevance of the pulse surveys at the time of integration. The integration unit, for example, prioritizes integration of pulse survey results with high relevance. For example, the integration unit uses a generation AI to analyze the results of the pulse survey and prioritizes integration of results with high relevance. The integration unit can also postpone integration of pulse survey results with low relevance. For example, the integration unit uses a generation AI to analyze the results of the pulse survey and prioritizes integration of results with low relevance. Furthermore, the integration unit can dynamically adjust the order of integration based on the relevance of the pulse survey. For example, the integration unit uses a generation AI to analyze the results of the pulse survey and dynamically adjust the order of integration based on the relevance. As a result, by adjusting the order of integration based on the relevance of the pulse survey, more relevant data can be preferentially integrated. A part or all of the above-mentioned processing in the integration unit may be performed, for example, using AI, or may be performed without using AI. For example, the integration unit can adjust the order of integration based on the relevance of the pulse survey using a generation AI.

[0050] The escalation unit can adjust the level of detail of the escalation based on the importance of the score at the time of escalation. For example, the escalation unit applies a detailed escalation procedure in the case of a score with high importance. For example, the escalation unit uses a generation AI to evaluate the importance of the score and applies a detailed escalation procedure to the score with high importance. In addition, the escalation unit can also apply a simplified escalation procedure in the case of a score with low importance. For example, the escalation unit uses a generation AI to evaluate the importance of the score and applies a simplified escalation procedure to the score with low importance. Furthermore, the escalation unit can dynamically adjust the level of detail of the escalation according to the importance of the score. For example, the escalation unit uses a generation AI to evaluate the importance of the score and dynamically adjusts the level of detail of the escalation according to the importance. As a result, by adjusting the level of detail of the escalation based on the importance of the score, more appropriate escalation is possible. A part or all of the above-mentioned processing in the escalation unit may be performed using an AI, for example, or may be performed without using an AI. For example, the escalation unit can use generative AI to adjust the detail of the escalation based on the importance of the score.

[0051] The escalation unit can apply different escalation algorithms depending on the category of the score at the time of escalation. For example, the escalation unit applies an escalation algorithm dedicated to stress to the score related to stress. For example, the escalation unit uses a generation AI to evaluate the category of the score and applies an escalation algorithm dedicated to stress to the score related to stress. The escalation unit can also apply an escalation algorithm dedicated to fatigue to the score related to fatigue. For example, the escalation unit uses a generation AI to evaluate the category of the score and applies an escalation algorithm dedicated to fatigue to the score related to fatigue. Furthermore, the escalation unit can also apply an escalation algorithm dedicated to dissatisfaction to the score related to dissatisfaction. For example, the escalation unit uses a generation AI to evaluate the category of the score and applies an escalation algorithm dedicated to dissatisfaction to the score related to dissatisfaction. This allows for more appropriate escalation by applying different escalation algorithms depending on the category of the score. A part or all of the above-mentioned processing in the escalation unit may be performed using an AI, for example, or may be performed without using an AI. For example, the escalation unit can use a generative AI to apply different escalation algorithms depending on the category of the score.

[0052] The escalation unit can determine the priority of the escalation based on the appearance time of the score at the time of escalation. The escalation unit, for example, assigns a high priority to a score that has appeared recently and performs escalation. For example, the escalation unit uses a generation AI to evaluate the appearance time of the score and assigns a high priority to a score that has appeared recently and performs escalation. The escalation unit can also assign a high priority to a score that has appeared frequently in the past and perform escalation. For example, the escalation unit uses a generation AI to evaluate the appearance time of the score and assigns a high priority to a score that has appeared frequently in the past and performs escalation. Furthermore, the escalation unit can dynamically adjust the priority of the escalation based on the appearance time of the score. For example, the escalation unit uses a generation AI to evaluate the appearance time of the score and dynamically adjusts the priority of the escalation based on the appearance time. As a result, by determining the priority of the escalation based on the appearance time of the score, escalation based on more recent data is possible. A part or all of the above-mentioned processing in the escalation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the escalation unit can use the generation AI to determine escalation priorities based on when the scores appear.

[0053] The escalation unit can adjust the order of escalation based on the relevance of the scores at the time of escalation. The escalation unit, for example, assigns a high priority to a score having a high relevance and performs escalation. For example, the escalation unit uses a generation AI to evaluate the relevance of the scores and assigns a high priority to a score having a high relevance and performs escalation. The escalation unit can also assign a low priority to a score having a low relevance and perform escalation. For example, the escalation unit uses a generation AI to evaluate the relevance of the scores and assigns a low priority to a score having a low relevance and performs escalation. Furthermore, the escalation unit can dynamically adjust the order of escalation based on the relevance of the scores. For example, the escalation unit uses a generation AI to evaluate the relevance of the scores and dynamically adjusts the order of escalation based on the relevance. As a result, by adjusting the order of escalation based on the relevance of the scores, escalation based on more highly relevant data is possible. A part or all of the above-mentioned processing in the escalation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the escalation unit can use generative AI to adjust the order of escalation based on score relevance.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The analysis unit can collect employees' health data and use it for analysis. For example, it can obtain heart rate and sleep data from employees' fitness trackers and smart watches, and combine this data with chat logs and email content for analysis. The analysis unit can also collect employees' diet and exercise records and use them to evaluate their health conditions. Furthermore, the analysis unit can import the results of employees' regular health checkups and track changes in their long-term health conditions. This makes it possible to comprehensively analyze employees' health data and more accurately evaluate their health conditions.

[0056] The integration department can collect employees' work performance data and use it for integration. For example, it can collect employees' project progress and task completion rates, and combine and integrate these data with chat logs and email contents. The integration department can also collect employees' work evaluations and feedback, and use them for evaluating their mental state. In addition, the integration department can capture employees' attendance status and working hours, and track changes in long-term work performance. This makes it possible to comprehensively integrate employees' work performance data and more accurately evaluate their mental state.

[0057] The escalation department can collect data on employees' work performance and use it to make escalation decisions. For example, it can collect employees' project progress and task completion rates and use this data to make decisions about whether to escalate. The escalation department can also collect employees' work evaluations and feedback and use this data to make escalation decisions. Furthermore, the escalation department can record employees' attendance status and working hours to track changes in long-term work performance. This allows for a comprehensive evaluation of employees' work performance data, enabling more appropriate escalation.

[0058] The analysis unit can analyze the employee's past work performance data and determine the focus of the analysis. For example, the analysis can be performed with an emphasis on projects in which the employee showed poor performance in the past. The analysis unit can also analyze the employee's past work evaluations and feedback and perform analysis with an emphasis on specific problem areas. Furthermore, the analysis unit can analyze the employee's past attendance status and working hours to track long-term changes in performance. In this way, the optimal analysis method can be selected by analyzing the employee's past work performance data.

[0059] During analysis, the analysis unit can perform filtering based on the employee's current health condition. For example, if an employee currently has a health problem, chat logs and emails related to that problem can be analyzed with priority. The analysis unit can also filter logs and emails containing specific keywords based on the employee's health data. Furthermore, the analysis unit can adjust the focus of the analysis according to changes in the employee's health condition. This allows more relevant data to be analyzed by filtering based on the employee's current health condition.

[0060] During analysis, the analysis unit can prioritize analysis of highly relevant logs and emails by taking into account the geographic location information of employees. For example, if an employee is in a specific area, the analysis unit can prioritize analysis of logs and emails related to that area. In addition, if an employee is on a business trip, the analysis unit can prioritize analysis of logs and emails related to the business trip destination. Furthermore, if an employee is working remotely, the analysis unit can prioritize analysis of logs and emails related to the employee's home or remote work destination. In this way, more relevant data can be analyzed by taking into account the geographic location information of employees.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The analysis unit analyzes employees' chat logs and emails. For example, using a generative AI, it extracts negative words from chat logs and emails and calculates their frequency. Specifically, it extracts negative words such as "tired" and "stressed" from chat logs and emails and calculates their frequency. Step 2: The scoring section uses the generation AI to score the negative words extracted by the analysis section. Scoring is performed based on the frequency and context of the negative words. For example, the score is calculated based on the frequency of the negative words, and the importance of the negative words is evaluated based on the context, and the score is calculated. Step 3: The integration unit uses generative AI to integrate data such as pulse surveys. For example, pulse survey results, chat logs, and email data can be integrated to comprehensively grasp the employee's mental state. This allows the employee's mental state to be evaluated in real time. Step 4: The Escalation Department uses generative AI to determine who to escalate to based on the data obtained by the Integration Department. For example, if the score is high, the department will be notified, and if certain negative words are frequently used, the case will be escalated to a professional counselor.

[0063] (Example 2) The system for detecting the health and mental state of employees in real time according to an embodiment of the present invention is a mechanism that utilizes generation AI to detect the health and mental state of employees in real time, and to prevent the outflow of human resources and improve mental health at an early stage. This system analyzes employees' chat logs and emails using generation AI, extracts negative words, and scores them. For example, if an employee uses negative words such as "tired" or "stressed," a score is calculated based on the frequency and context of the words. Next, the system combines this with other data such as pulse surveys to comprehensively grasp the employee's mental state. A pulse survey is a simple questionnaire that is periodically administered to employees to measure the employee's satisfaction and stress level. The generation AI integrates these data and evaluates the employee's mental state in real time. In addition, the system determines the most appropriate escalation destination for each score and content. For example, if the score is high, the system notifies the superior or human resources department and takes action early. In addition, if certain negative words appear frequently, the system escalates to a professional counselor. In this way, mental problems of employees can be discovered early and appropriate action can be taken. This system allows employees' health and mental states to be grasped in real time, preventing the loss of talent and improving their mental health. For example, if an employee feels stressed, mental health problems can be prevented by receiving counseling early on. It is also expected that employee satisfaction will increase and the productivity of the entire company will improve. As a result, a system that detects employees' health and mental states in real time can grasp the health and mental states of employees in real time, preventing the loss of talent and improving their mental health.

[0064] A system for detecting an employee's health and mental state in real time according to an embodiment includes an analysis unit, a scoring unit, an integration unit, and an escalation unit. The analysis unit analyzes the employee's chat log and email. The employee's chat log and email include, for example, business interactions and personal messages, but are not limited to such examples. The analysis unit extracts negative words from the chat log and email using, for example, a generation AI. The generation AI can analyze the contents of the chat log and email using a text generation AI (for example, LLM) and extract negative words. The analysis unit can also analyze the context of the chat log and email using the generation AI and calculate the frequency of negative words. For example, the generation AI extracts negative words such as "tired" and "stressed" in the chat log and email and calculates their frequency. The scoring unit scores the negative words extracted by the analysis unit using the generation AI. Scoring is performed based on, for example, the frequency and context of the negative words, but is not limited to such examples. For example, the scoring unit uses the generation AI to calculate a score based on the frequency of negative words. The scoring unit can also use the generation AI to calculate a score based on the context of negative words. For example, the generation AI analyzes the context of chat logs and emails, evaluates the importance of negative words, and calculates the score. The integration unit uses the generation AI to integrate data such as pulse surveys. The integration is performed, for example, by integrating the results of the pulse survey, chat logs, and email data, but is not limited to such an example. For example, the integration unit uses the generation AI to collect the results of the pulse survey and comprehensively grasp the mental state of the employee. The integration unit can also use the generation AI to integrate the chat log and email data and evaluate the mental state of the employee. For example, the generation AI integrates the results of the pulse survey with the chat log and email data to evaluate the mental state of the employee in real time. The escalation unit uses the generation AI to determine the escalation destination based on the data obtained by the integration unit. The escalation is performed, for example, based on the score and content, but is not limited to such an example.For example, the escalation unit uses the generation AI to notify superiors or the human resources department if the score is high, and escalate to a professional counselor if certain negative words appear frequently. In this way, the system for detecting the health and mental state of employees in real time according to the embodiment can grasp the health and mental state of employees in real time, prevent the loss of human resources, and improve their mental health.

[0065] The analysis unit analyzes the chat logs and emails of employees. The chat logs and emails of employees include, for example, business interactions and personal messages, but are not limited to such examples. The analysis unit extracts negative words from the chat logs and emails using, for example, a generation AI. The generation AI can analyze the contents of the chat logs and emails and extract negative words using a text generation AI (for example, LLM). The analysis unit can also analyze the context of the chat logs and emails using the generation AI and calculate the frequency of negative words. For example, the generation AI extracts negative words such as "tired" and "stressed" in the chat logs and emails and calculates their frequency. Furthermore, the analysis unit utilizes natural language processing technology to analyze the contents of the employee's chat logs and emails in detail. Specifically, morphological analysis and grammatical analysis are performed to deepen understanding of the context. For example, morphological analysis is used to identify the part of speech of each word, and grammatical analysis is used to grasp the structure of the sentence. This makes it possible to understand the meaning based on the context, rather than simply extracting words. Furthermore, the analysis unit introduces emotion analysis technology to grasp employees' emotions more accurately. Using emotion analysis technology, emotions expressed in chat logs and emails can be classified into three categories: positive, negative, and neutral, and their intensity can be evaluated. For example, the emotion evaluation will be different if a sentence containing the word "tired" is used in a positive context overall than if it is used in a negative context. In this way, the analysis unit can analyze employees' chat logs and emails from multiple angles and grasp employees' health and mental states more accurately.

[0066] The scoring unit uses the generation AI to score the negative words extracted by the analysis unit. Scoring is performed, for example, based on the frequency and context of the negative words, but is not limited to such examples. For example, the scoring unit uses the generation AI to calculate a score based on the frequency of the negative words. The scoring unit can also use the generation AI to calculate a score based on the context of the negative words. For example, the generation AI analyzes the context of chat logs and emails, evaluates the importance of negative words, and calculates the score. Furthermore, the scoring unit takes into account multiple factors to comprehensively evaluate the health and mental state of employees. For example, the evaluation can include not only the frequency of negative words, but also the frequency of positive words and the balance of positive and negative in the context. This makes it possible to grasp the overall trend of emotions rather than simply counting negative words. In addition, the scoring unit can detect abnormal fluctuations by referring to the employee's past data and comparing it with the current state. For example, if the frequency of negative words has increased sharply compared to data from the past few months, it can be determined that the employee is likely to be feeling stressed. In this way, the scoring unit can evaluate an employee's health and mental state from multiple angles and calculate a score in real time.

[0067] The integration unit integrates data such as pulse surveys using the generation AI. The integration is performed, for example, by integrating the results of the pulse survey, chat logs, and email data, but is not limited to such examples. For example, the integration unit uses the generation AI to collect the results of the pulse survey and comprehensively grasp the mental state of the employee. The integration unit can also use the generation AI to integrate chat log and email data to evaluate the mental state of the employee. For example, the generation AI integrates the results of the pulse survey with the chat log and email data to evaluate the mental state of the employee in real time. Furthermore, the integration unit can utilize other data sources to more accurately evaluate the health and mental state of the employee. For example, by integrating the employee's attendance status, work performance data, and even the results of health checkups, a more comprehensive evaluation is possible. This allows the employee's health and mental state to be understood from multiple angles, and abnormal fluctuations and risks can be detected early. In addition, the integration unit performs filtering and cleaning to ensure the quality and reliability of the data in the data integration process. For example, the accuracy of the evaluation can be improved by removing noise and missing data and using only reliable data. In this way, the Integration Department integrates multiple data sources and comprehensively evaluates employees' health and mental state, enabling real-time situation assessment and early response.

[0068] The escalation unit uses the generation AI to determine the escalation destination based on the data obtained by the integration unit. Escalation is performed, for example, based on the score and the content, but is not limited to such examples. For example, the escalation unit uses the generation AI to notify the superior or the human resources department when the score is high, and escalate to a professional counselor when specific negative words appear frequently. As a result, the system for detecting the health and mental state of employees in real time according to the embodiment can grasp the health and mental state of employees in real time, prevent the outflow of human resources, and improve mental aspects. Furthermore, the escalation unit realizes a quick and efficient response by automating the escalation process. For example, the generation AI can determine the priority of escalation based on the score and the content, and automatically select the optimal escalation destination. In addition, the escalation unit can record the history of escalation and use it for later analysis and improvement. For example, the results of past escalations and the effects of responses can be analyzed, and the standards and processes of escalation can be continuously improved. In this way, the escalation department can support employees' mental health and maintain the health of the entire organization by understanding employees' health and mental state in real time and taking appropriate escalation measures.

[0069] The scoring unit can calculate the score based on the frequency or context of negative words. The scoring unit, for example, calculates the score based on the frequency of negative words. For example, the scoring unit uses the generation AI to calculate the frequency of appearance of negative words such as "tired" and "stressed" in chat logs and emails, and calculates the score based on the frequency. The scoring unit can also calculate the score based on the context of negative words. For example, the scoring unit uses the generation AI to analyze the context of chat logs and emails, evaluate the importance of negative words, and calculate the score. In this way, the mental state of employees can be more accurately evaluated by calculating the score based on the frequency and context of negative words. Part or all of the above-mentioned processing in the scoring unit may be performed, for example, using AI, or may be performed without using AI. For example, the scoring unit can use the generation AI to calculate the frequency of appearance of negative words such as "tired" and "stressed" in chat logs and emails, and calculate the score based on the frequency.

[0070] The integration unit collects the results of the pulse survey and can comprehensively grasp the mental state of the employee. The integration unit, for example, collects the results of the pulse survey and comprehensively grasps the mental state of the employee. The pulse survey is a simple questionnaire that is periodically administered to employees, and measures the satisfaction and stress level of the employee. For example, the integration unit uses a generation AI to collect the results of the pulse survey and comprehensively grasp the mental state of the employee. The integration unit can also use a generation AI to integrate the results of the pulse survey with other data and evaluate the mental state of the employee in real time. For example, the integration unit uses a generation AI to integrate the results of the pulse survey with chat log and email data and evaluate the mental state of the employee in real time. This allows for more accurate evaluation by collecting the results of the pulse survey and comprehensively grasping the mental state of the employee. Part or all of the above-mentioned processing in the integration unit may be performed, for example, using AI, or may be performed without using AI. For example, the integration unit uses a generation AI to collect the results of the pulse survey and comprehensively grasp the mental state of the employee.

[0071] The escalation unit can determine the escalation destination based on the score or the content. The escalation unit determines the escalation destination based on the score, for example. For example, the escalation unit uses the generation AI to notify a superior or a human resources department when the score is high, and responds promptly. The escalation unit can also determine the escalation destination based on the content. For example, the escalation unit uses the generation AI to escalate to a professional counselor when a specific negative word appears frequently. This allows for a quick and appropriate response by determining the most appropriate escalation destination based on the score or the content. Some or all of the above-mentioned processing in the escalation unit may be performed, for example, using AI, or may be performed without using AI. For example, the escalation unit uses the generation AI to notify a superior or a human resources department when the score is high, and responds promptly.

[0072] The escalation unit can notify a superior or the human resources department when the score is high, and escalate to a professional counselor when a specific negative word appears frequently. The escalation unit, for example, notifies a superior or the human resources department when the score is high. For example, the escalation unit uses a generation AI to notify a superior or the human resources department when the score is high, and responds early. The escalation unit can also escalate to a professional counselor when a specific negative word appears frequently. For example, the escalation unit uses a generation AI to escalate to a professional counselor when a specific negative word appears frequently. This makes it possible to detect and respond to mental problems of employees early by performing appropriate escalation when the score is high or when a specific negative word appears frequently. Some or all of the above-mentioned processing in the escalation unit may be performed, for example, using AI, or may be performed without using AI. For example, the escalation unit can use a generation AI to notify a superior or the human resources department when the score is high, and respond early.

[0073] The analysis unit can estimate the employee's emotions and adjust the timing of the analysis based on the estimated employee's emotions. For example, if the employee is feeling stressed, the analysis unit can increase the frequency of analysis and detect problems early. For example, the analysis unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is feeling stressed. If the employee is feeling stressed, the analysis unit can increase the frequency of analysis and detect problems early. In addition, the analysis unit can reduce the frequency of analysis and avoid excessive monitoring if the employee is relaxed. For example, the analysis unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is feeling stressed. If the employee is feeling stressed, the analysis unit can reduce the frequency of analysis and avoid excessive monitoring. In addition, the analysis unit can temporarily stop the analysis if the employee is in a hurry, allowing the employee to concentrate on work. For example, the analysis unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is in a hurry. When an employee is in a hurry, the analysis unit can temporarily stop the analysis to allow the employee to concentrate on work. This allows the analysis to be performed at a more appropriate time by adjusting the timing of the analysis based on the employee's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use a generation AI to analyze the contents of the employee's chat log or email, estimate the employee's emotions, and adjust the timing of the analysis based on the emotions.

[0074] The analysis unit can analyze the employee's past chat logs and email history and select an analysis method. The analysis unit determines the focus of the analysis, for example, based on negative words frequently used by the employee in the past. For example, the analysis unit uses a generation AI to analyze the employee's past chat logs and email history and extracts frequently used negative words. Based on the result, the analysis unit can determine the focus of the analysis. In addition, if negative words appear frequently in a specific time period from the employee's past chat logs, the analysis unit can also focus on that time period for analysis. For example, the analysis unit uses a generation AI to analyze the employee's past chat logs and check whether negative words appear frequently in a specific time period. Based on the result, the analysis unit can focus on that time period for analysis. In addition, the analysis unit can analyze the employee's email history and prioritize analysis of negative words related to a specific project or work. For example, the analysis unit uses a generation AI to analyze the employee's email history and extracts negative words related to a specific project or work. Based on the result, the analysis unit can prioritize analysis. This allows the optimal analysis method to be selected by analyzing the employee's past chat logs and email history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can use a generation AI to analyze the employee's past chat logs and email history and select the optimal analysis method.

[0075] The analysis unit can perform filtering based on the employee's current project and work content during analysis. The analysis unit, for example, prioritizes analysis of chat logs and emails related to the employee's current project. For example, the analysis unit uses the generation AI to extract chat logs and emails related to the employee's current project and prioritizes analysis of them. The analysis unit can also filter logs and emails containing specific keywords based on the employee's work content. For example, the analysis unit uses the generation AI to extract chat logs and emails containing keywords related to the employee's work content and filters them. Furthermore, the analysis unit can adjust the focus of the analysis according to the progress of the employee's project. For example, the analysis unit uses the generation AI to grasp the progress of the employee's project and adjust the focus of the analysis according to the progress. This allows more relevant data to be analyzed by filtering based on the employee's current project and work content. Part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform filtering based on the employee's current project and work content using the generation AI.

[0076] The analysis unit can estimate the employee's emotions and determine the priority of logs and emails to be analyzed based on the estimated employee's emotions. For example, when an employee is feeling stressed, the analysis unit prioritizes analyzing logs and emails related to stress. For example, the analysis unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is feeling stressed. When an employee is feeling stressed, the analysis unit can prioritize analyzing logs and emails related to stress. In addition, when an employee is relaxed, the analysis unit can also prioritize analyzing logs and emails related to normal work. For example, the analysis unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is relaxed. When an employee is relaxed, the analysis unit can prioritize analyzing logs and emails related to normal work. In addition, when an employee is in a hurry, the analysis unit can also prioritize analyzing logs and emails with high importance. For example, the analysis unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is in a hurry. When an employee is in a hurry, the analysis unit can prioritize analysis of logs and emails with high importance. This allows more important data to be analyzed with priority by determining the priority of logs and emails to be analyzed based on the employee's emotions. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can use a generation AI to analyze the contents of the employee's chat logs and emails, estimate the employee's emotions, and determine the priority of logs and emails to be analyzed based on the emotions.

[0077] During the analysis, the analysis unit can prioritize the analysis of highly relevant logs and emails by taking into account the geographical location information of the employee. For example, when an employee is in a specific area, the analysis unit prioritizes the analysis of logs and emails related to that area. For example, the analysis unit uses a generation AI to acquire the geographical location information of the employee, extracts logs and emails related to that area, and analyzes them preferentially. In addition, when an employee is on a business trip, the analysis unit can also prioritize the analysis of logs and emails related to the business trip destination. For example, the analysis unit uses a generation AI to acquire the geographical location information of the employee, extracts logs and emails related to the business trip destination, and analyzes them preferentially. In addition, when an employee is working remotely, the analysis unit can also prioritize the analysis of logs and emails related to the home or remote work destination. For example, the analysis unit uses a generation AI to acquire the geographical location information of the employee, extracts logs and emails related to the home or remote work destination, and analyzes them preferentially. As a result, more relevant data can be analyzed by taking into account the geographical location information of the employee. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can use generative AI to prioritize analysis of highly relevant logs and emails taking into account employees' geographic location information.

[0078] During the analysis, the analysis unit can analyze the employee's social media activity and analyze related logs and emails. For example, if the employee posts negatively on social media, the analysis unit preferentially analyzes logs and emails related to the content. For example, the analysis unit uses the generation AI to analyze the employee's social media activity, extracts negative posts, and preferentially analyzes logs and emails related to the content. The analysis unit can also analyze logs and emails related to a specific topic from the employee's social media activity. For example, the analysis unit uses the generation AI to analyze the employee's social media activity, extracts logs and emails related to a specific topic, and analyzes them. Furthermore, the analysis unit can adjust the timing of the analysis based on the time period during which the employee is active on social media. For example, the analysis unit uses the generation AI to analyze the time period during which the employee is active on social media, and adjusts the timing of the analysis based on the time period. This allows more relevant data to be analyzed by analyzing the employee's social media activity. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analytics department can use generative AI to analyze employees' social media activity and analyze related logs and emails.

[0079] The scoring unit can estimate the employee's emotions and adjust the way the scoring is expressed based on the estimated employee's emotions. For example, if the employee is feeling stressed, the scoring unit can display the scoring result simply to make it easier to understand. For example, the scoring unit can use the generation AI to analyze the contents of the employee's chat log or email to estimate whether the employee is feeling stressed. If the employee is feeling stressed, the scoring unit can display the scoring result simply to make it easier to understand. In addition, the scoring unit can also display detailed scoring results and provide in-depth analysis if the employee is relaxed. For example, the scoring unit can use the generation AI to analyze the contents of the employee's chat log or email to estimate whether the employee is feeling relaxed. If the employee is feeling relaxed, the scoring unit can display detailed scoring results and provide in-depth analysis. In addition, the scoring unit can display only the main points of the scoring result if the employee is in a hurry to make it easier to understand. For example, the scoring unit uses the generation AI to analyze the contents of the employee's chat log or email to estimate whether the employee is in a hurry. If the employee is in a hurry, the scoring unit can display only the main points of the scoring result to enable quick understanding. This allows the scoring result to be more easily understood by adjusting the scoring expression method based on the employee's emotions. Some or all of the above-mentioned processing in the scoring unit may be performed, for example, using AI or may be performed without using AI. For example, the scoring unit can use the generation AI to analyze the contents of the employee's chat log or email to estimate the employee's emotions and adjust the scoring expression method based on the emotions.

[0080] The scoring unit can adjust the detail level of the score based on the importance of the negative words at the time of scoring. For example, when many negative words with high importance are included, the scoring unit displays a detailed scoring result. For example, the scoring unit uses the generation AI to analyze the contents of the chat log or email, and when many negative words with high importance are included, the scoring unit displays the detailed scoring result. In addition, the scoring unit can also display a simplified scoring result when many negative words with low importance are included. For example, the scoring unit uses the generation AI to analyze the contents of the chat log or email, and when many negative words with low importance are included, the scoring unit displays the simplified scoring result. In addition, the scoring unit can dynamically adjust the detail level of the scoring according to the importance of the negative words. For example, the scoring unit uses the generation AI to analyze the contents of the chat log or email, and dynamically adjust the detail level of the scoring according to the importance of the negative words. This allows for a more accurate scoring result to be provided by adjusting the detail level of the score based on the importance of the negative words. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can use a generating AI to analyze the contents of chat logs and emails and adjust the detail level of the score based on the importance of negative words.

[0081] The scoring unit can apply different scoring algorithms depending on the category of the negative word at the time of scoring. For example, the scoring unit applies a stress-specific scoring algorithm to negative words related to stress. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, extracts negative words related to stress, and applies a stress-specific scoring algorithm to the words. The scoring unit can also apply a fatigue-specific scoring algorithm to negative words related to fatigue. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, extracts negative words related to fatigue, and applies a fatigue-specific scoring algorithm to the words. Furthermore, the scoring unit can also apply a dissatisfaction-specific scoring algorithm to negative words related to dissatisfaction. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, extracts negative words related to dissatisfaction, and applies a dissatisfaction-specific scoring algorithm to the words. This makes it possible to provide more accurate scoring results by applying different scoring algorithms depending on the category of the negative word. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit may use a generating AI to analyze the contents of chat logs and emails, and apply different scoring algorithms depending on the category of negative words.

[0082] The scoring unit can estimate the employee's emotions and adjust the length of the scoring based on the estimated employee's emotions. For example, if the employee is stressed, the scoring unit shortens the scoring result so that it can be understood quickly. For example, the scoring unit uses the generation AI to analyze the contents of the employee's chat log and email to estimate whether the employee is stressed. If the employee is stressed, the scoring unit can shorten the scoring result so that it can be understood quickly. In addition, the scoring unit can display detailed scoring results and provide deep analysis if the employee is relaxed. For example, the scoring unit uses the generation AI to analyze the contents of the employee's chat log and email to estimate whether the employee is relaxed. If the employee is relaxed, the scoring unit can display detailed scoring results and provide deep analysis. In addition, the scoring unit can display only the main points of the scoring result so that it can be understood quickly if the employee is in a hurry. For example, the scoring unit uses the generation AI to analyze the contents of the employee's chat log and email to estimate whether the employee is in a hurry. When an employee is in a hurry, the scoring unit can display only the main points of the scoring result so that the employee can quickly understand it. This allows the length of the scoring to be adjusted based on the employee's emotions, thereby providing a scoring result that is easier to understand. Some or all of the above-mentioned processing in the scoring unit may be performed, for example, using AI, or may be performed without using AI. For example, the scoring unit can use a generating AI to analyze the contents of the employee's chat log or email, estimate the employee's emotions, and adjust the length of the scoring based on the emotions.

[0083] The scoring unit can determine the priority of the score based on the appearance time of the negative word at the time of scoring. For example, the scoring unit assigns a high priority to a negative word that has appeared recently and reflects it in the scoring result. For example, the scoring unit uses a generation AI to analyze the contents of a chat log or an email, extracts a negative word that has appeared recently, assigns a high priority to the word, and reflects it in the scoring result. The scoring unit can also assign a high priority to a negative word that has appeared frequently in the past and reflects it in the scoring result. For example, the scoring unit uses a generation AI to analyze the contents of a chat log or an email, extracts a negative word that has appeared frequently in the past, assigns a high priority to the word, and reflects it in the scoring result. Furthermore, the scoring unit can dynamically adjust the priority of the score based on the appearance time of the negative word. For example, the scoring unit uses a generation AI to analyze the contents of a chat log or an email, and dynamically adjusts the priority of the score based on the appearance time of the negative word. This allows more important data to be scored preferentially by determining the priority of the score based on the time when the negative words appeared. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit can use a generating AI to analyze the contents of chat logs and emails and determine the priority of the score based on the time when the negative words appeared.

[0084] The scoring unit can adjust the order of scores based on the relevance of negative words during scoring. For example, the scoring unit assigns a high score to negative words with high relevance and reflects it in the scoring result. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, extracts negative words with high relevance, assigns a high score to the words, and reflects it in the scoring result. The scoring unit can also assign a low score to negative words with low relevance and reflect it in the scoring result. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, extracts negative words with low relevance, assigns a low score to the words, and reflects it in the scoring result. Furthermore, the scoring unit can dynamically adjust the order of scores based on the relevance of negative words. For example, the scoring unit uses a generation AI to analyze the contents of chat logs and emails, and dynamically adjusts the order of scores based on the relevance of negative words. This makes it possible to provide a more accurate scoring result by adjusting the order of scores based on the relevance of negative words. Some or all of the above-mentioned processing in the scoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the scoring unit may use a generating AI to analyze the contents of chat logs and emails and adjust the order of scores based on the relevance of negative words.

[0085] The integration unit can estimate the employee's emotions and adjust the integration method based on the estimated employee's emotions. For example, if the employee is stressed, the integration unit uses a simple integration method to make it easier to understand. For example, the integration unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is stressed. If the employee is stressed, the integration unit can use a simple integration method to make it easier to understand. In addition, the integration unit can use a detailed integration method to provide a deep analysis if the employee is relaxed. For example, the integration unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is relaxed. If the employee is relaxed, the integration unit can use a detailed integration method to provide a deep analysis. In addition, if the employee is in a hurry, the integration unit can integrate only the main points to make it easier to understand. For example, the integration unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is in a hurry. If the employee is in a hurry, the integration unit can integrate only the main points to make it easier to understand. This allows the integration method to be adjusted based on the employee's emotions, providing an integration result that is easier to understand. Some or all of the above-mentioned processing in the integration unit may be performed using, for example, AI, or may be performed without using AI. For example, the integration unit can use a generating AI to analyze the contents of the employee's chat log or email, estimate the employee's emotions, and adjust the integration method based on the emotions.

[0086] The integration unit can estimate the employee's emotions and adjust the integration method based on the estimated employee's emotions. For example, if the employee is stressed, the integration unit uses a simple integration method to make it easier to understand. For example, the integration unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is stressed. If the employee is stressed, the integration unit can use a simple integration method to make it easier to understand. In addition, the integration unit can use a detailed integration method to provide a deep analysis if the employee is relaxed. For example, the integration unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is relaxed. If the employee is relaxed, the integration unit can use a detailed integration method to provide a deep analysis. In addition, if the employee is in a hurry, the integration unit can integrate only the main points to make it easier to understand. For example, the integration unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is in a hurry. If the employee is in a hurry, the integration unit can integrate only the main points to make it easier to understand. This allows the integration method to be adjusted based on the employee's emotions, providing an integration result that is easier to understand. Some or all of the above-mentioned processing in the integration unit may be performed using, for example, AI, or may be performed without using AI. For example, the integration unit can use a generating AI to analyze the contents of the employee's chat log or email, estimate the employee's emotions, and adjust the integration method based on the emotions.

[0087] The integration unit can adjust the level of detail of the integration based on the importance of the pulse survey results at the time of integration. For example, the integration unit integrates pulse survey results with high importance in detail to provide a deep analysis. For example, the integration unit uses a generation AI to analyze the pulse survey results and integrate the results with high importance in detail. The integration unit can also simplify and integrate the results of pulse surveys with low importance so that they can be understood quickly. For example, the integration unit uses a generation AI to analyze the pulse survey results and simplify and integrate the results with low importance. Furthermore, the integration unit can dynamically adjust the level of detail of the integration according to the importance of the pulse survey results. For example, the integration unit uses a generation AI to analyze the pulse survey results and dynamically adjust the level of detail of the integration according to the importance. As a result, by adjusting the level of detail of the integration based on the importance of the pulse survey results, a more accurate integration result can be provided. A part or all of the above-mentioned processing in the integration unit may be performed, for example, using AI, or may be performed without using AI. For example, the integrator can use generative AI to adjust the granularity of the integration based on the importance of the pulse survey results.

[0088] The integration unit can apply different integration algorithms depending on the category of the pulse survey at the time of integration. For example, the integration unit applies an integration algorithm dedicated to stress to the result of the pulse survey related to stress. For example, the integration unit uses a generation AI to analyze the result of the pulse survey and applies an integration algorithm dedicated to stress to the result related to stress. The integration unit can also apply an integration algorithm dedicated to fatigue to the result of the pulse survey related to fatigue. For example, the integration unit uses a generation AI to analyze the result of the pulse survey and applies an integration algorithm dedicated to fatigue to the result related to fatigue. Furthermore, the integration unit can also apply an integration algorithm dedicated to dissatisfaction to the result of the pulse survey related to dissatisfaction. For example, the integration unit uses a generation AI to analyze the result of the pulse survey and applies an integration algorithm dedicated to dissatisfaction to the result related to dissatisfaction. In this way, by applying different integration algorithms depending on the category of the pulse survey, more accurate integration results can be provided. Part or all of the above-mentioned processing in the integration unit may be performed using, for example, AI, or may be performed without using AI. For example, the integration unit can use a generation AI to apply different integration algorithms depending on the category of the pulse survey.

[0089] The integration unit can estimate the employee's emotions and determine the priority of integration based on the estimated employee's emotions. For example, when an employee is feeling stressed, the integration unit prioritizes integration of data related to stress. For example, the integration unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is feeling stressed. When an employee is feeling stressed, the integration unit can prioritize integration of data related to stress. In addition, when an employee is relaxed, the integration unit can also prioritize integration of data related to normal work. For example, the integration unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is relaxed. When an employee is relaxed, the integration unit can prioritize integration of data related to normal work. In addition, when an employee is in a hurry, the integration unit can also prioritize integration of data with high importance. For example, the integration unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is in a hurry. When an employee is in a hurry, the integration unit can prioritize integration of data with high importance. This allows the integration priority to be determined based on the employee's emotions, so that more important data can be integrated preferentially. Some or all of the above-mentioned processing in the integration unit may be performed using, for example, AI, or may be performed without using AI. For example, the integration unit can use a generation AI to analyze the contents of the employee's chat logs and emails, estimate the employee's emotions, and determine the integration priority based on the emotions.

[0090] The integration unit can determine the priority of integration based on the implementation time of the pulse survey at the time of integration. The integration unit, for example, prioritizes integration of the results of the most recently implemented pulse survey. For example, the integration unit uses the generation AI to analyze the results of the pulse survey and prioritizes integration of the most recently implemented results. The integration unit can also prioritize integration of the latest results while referring to the results of the pulse surveys implemented in the past. For example, the integration unit uses the generation AI to analyze the results of the pulse survey and prioritizes integration of the latest results while referring to the past results. Furthermore, the integration unit can dynamically adjust the priority of integration based on the implementation time of the pulse survey. For example, the integration unit uses the generation AI to analyze the results of the pulse survey and dynamically adjust the priority of integration based on the implementation time. As a result, by determining the priority of integration based on the implementation time of the pulse survey, more recent data can be prioritized for integration. Part or all of the above-mentioned processing in the integration unit may be performed, for example, using AI, or may be performed without using AI. For example, the integration unit can use the generation AI to determine the priority of integration based on the implementation time of the pulse survey.

[0091] The integration unit can adjust the order of integration based on the relevance of the pulse surveys at the time of integration. The integration unit, for example, prioritizes integration of pulse survey results with high relevance. For example, the integration unit uses a generation AI to analyze the results of the pulse survey and prioritizes integration of results with high relevance. The integration unit can also postpone integration of pulse survey results with low relevance. For example, the integration unit uses a generation AI to analyze the results of the pulse survey and prioritizes integration of results with low relevance. Furthermore, the integration unit can dynamically adjust the order of integration based on the relevance of the pulse survey. For example, the integration unit uses a generation AI to analyze the results of the pulse survey and dynamically adjust the order of integration based on the relevance. As a result, by adjusting the order of integration based on the relevance of the pulse survey, more relevant data can be preferentially integrated. A part or all of the above-mentioned processing in the integration unit may be performed, for example, using AI, or may be performed without using AI. For example, the integration unit can adjust the order of integration based on the relevance of the pulse survey using a generation AI.

[0092] The escalation unit can estimate the employee's emotions and adjust the escalation method based on the estimated employee's emotions. For example, if the employee is feeling stressed, the escalation unit quickly escalates to a superior. For example, the escalation unit uses the generation AI to analyze the contents of the employee's chat log and email to estimate whether the employee is feeling stressed. If the employee is feeling stressed, the escalation unit can quickly escalate to a superior. In addition, the escalation unit can apply a normal escalation procedure if the employee is relaxed. For example, the escalation unit uses the generation AI to analyze the contents of the employee's chat log and email to estimate whether the employee is feeling relaxed. If the employee is relaxed, the escalation unit can apply a normal escalation procedure. In addition, the escalation unit can apply a simplified escalation procedure if the employee is in a hurry. For example, the escalation unit uses the generation AI to analyze the contents of the employee's chat log and email to estimate whether the employee is in a hurry. When an employee is in a hurry, the escalation unit can apply a simplified escalation procedure. This allows for more appropriate escalation by adjusting the escalation method based on the employee's emotions. Some or all of the above-mentioned processing in the escalation unit may be performed using, for example, AI, or may be performed without using AI. For example, the escalation unit can use a generation AI to analyze the contents of the employee's chat log or email, estimate the employee's emotions, and adjust the escalation method based on the emotions.

[0093] The escalation unit can adjust the level of detail of the escalation based on the importance of the score at the time of escalation. For example, the escalation unit applies a detailed escalation procedure in the case of a score with high importance. For example, the escalation unit uses a generation AI to evaluate the importance of the score and applies a detailed escalation procedure to the score with high importance. In addition, the escalation unit can also apply a simplified escalation procedure in the case of a score with low importance. For example, the escalation unit uses a generation AI to evaluate the importance of the score and applies a simplified escalation procedure to the score with low importance. Furthermore, the escalation unit can dynamically adjust the level of detail of the escalation according to the importance of the score. For example, the escalation unit uses a generation AI to evaluate the importance of the score and dynamically adjusts the level of detail of the escalation according to the importance. As a result, by adjusting the level of detail of the escalation based on the importance of the score, more appropriate escalation is possible. A part or all of the above-mentioned processing in the escalation unit may be performed using an AI, for example, or may be performed without using an AI. For example, the escalation unit can use generative AI to adjust the detail of the escalation based on the importance of the score.

[0094] The escalation unit can apply different escalation algorithms depending on the category of the score at the time of escalation. For example, the escalation unit applies an escalation algorithm dedicated to stress to the score related to stress. For example, the escalation unit uses a generation AI to evaluate the category of the score and applies an escalation algorithm dedicated to stress to the score related to stress. The escalation unit can also apply an escalation algorithm dedicated to fatigue to the score related to fatigue. For example, the escalation unit uses a generation AI to evaluate the category of the score and applies an escalation algorithm dedicated to fatigue to the score related to fatigue. Furthermore, the escalation unit can also apply an escalation algorithm dedicated to dissatisfaction to the score related to dissatisfaction. For example, the escalation unit uses a generation AI to evaluate the category of the score and applies an escalation algorithm dedicated to dissatisfaction to the score related to dissatisfaction. This allows for more appropriate escalation by applying different escalation algorithms depending on the category of the score. A part or all of the above-mentioned processing in the escalation unit may be performed using an AI, for example, or may be performed without using an AI. For example, the escalation unit can use a generative AI to apply different escalation algorithms depending on the category of the score.

[0095] The escalation unit can estimate the employee's emotions and determine the priority of escalation based on the estimated employee's emotions. For example, if the employee is feeling stressed, the escalation unit prioritizes stress-related escalations. For example, the escalation unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is feeling stressed. If the employee is feeling stressed, the escalation unit can prioritize stress-related escalations. In addition, the escalation unit can apply a normal escalation procedure if the employee is relaxed. For example, the escalation unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is relaxed. If the employee is relaxed, the escalation unit can apply a normal escalation procedure. In addition, the escalation unit can prioritize escalations with high importance if the employee is in a hurry. For example, the escalation unit uses the generation AI to analyze the contents of the employee's chat logs and emails to estimate whether the employee is in a hurry. When an employee is in a hurry, the escalation unit can prioritize escalations with a high level of importance. This allows the escalation priority to be determined based on the employee's emotions, so that more important escalations can be prioritized. Some or all of the above-mentioned processing in the escalation unit may be performed using, for example, AI, or may be performed without using AI. For example, the escalation unit can use a generation AI to analyze the contents of the employee's chat log or email, estimate the employee's emotions, and determine the priority of escalations based on the emotions.

[0096] The escalation unit can determine the priority of the escalation based on the appearance time of the score at the time of escalation. The escalation unit, for example, assigns a high priority to a score that has appeared recently and performs escalation. For example, the escalation unit uses a generation AI to evaluate the appearance time of the score and assigns a high priority to a score that has appeared recently and performs escalation. The escalation unit can also assign a high priority to a score that has appeared frequently in the past and perform escalation. For example, the escalation unit uses a generation AI to evaluate the appearance time of the score and assigns a high priority to a score that has appeared frequently in the past and performs escalation. Furthermore, the escalation unit can dynamically adjust the priority of the escalation based on the appearance time of the score. For example, the escalation unit uses a generation AI to evaluate the appearance time of the score and dynamically adjusts the priority of the escalation based on the appearance time. As a result, by determining the priority of the escalation based on the appearance time of the score, escalation based on more recent data is possible. A part or all of the above-mentioned processing in the escalation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the escalation unit can use the generation AI to determine escalation priorities based on when the scores appear.

[0097] The escalation unit can adjust the order of escalation based on the relevance of the scores at the time of escalation. The escalation unit, for example, assigns a high priority to a score having a high relevance and performs escalation. For example, the escalation unit uses a generation AI to evaluate the relevance of the scores and assigns a high priority to a score having a high relevance and performs escalation. The escalation unit can also assign a low priority to a score having a low relevance and perform escalation. For example, the escalation unit uses a generation AI to evaluate the relevance of the scores and assigns a low priority to a score having a low relevance and performs escalation. Furthermore, the escalation unit can dynamically adjust the order of escalation based on the relevance of the scores. For example, the escalation unit uses a generation AI to evaluate the relevance of the scores and dynamically adjusts the order of escalation based on the relevance. As a result, by adjusting the order of escalation based on the relevance of the scores, escalation based on more highly relevant data is possible. A part or all of the above-mentioned processing in the escalation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the escalation unit can use generative AI to adjust the order of escalation based on score relevance.

[0098] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0099] The analysis unit can collect employees' health data and use it for analysis. For example, it can obtain heart rate and sleep data from employees' fitness trackers and smart watches, and combine this data with chat logs and email content for analysis. The analysis unit can also collect employees' diet and exercise records and use them to evaluate their health conditions. Furthermore, the analysis unit can import the results of employees' regular health checkups and track changes in their long-term health conditions. This makes it possible to comprehensively analyze employees' health data and more accurately evaluate their health conditions.

[0100] The scoring unit can estimate the emotion of the employee and adjust the scoring criteria based on the estimated emotion of the employee. For example, if the employee is feeling stressed, the scoring criteria can be tightened to perform a more detailed evaluation. Also, if the employee is relaxed, the scoring criteria can be relaxed to perform a simplified evaluation. Furthermore, if the employee is in a hurry, the scoring criteria can be adjusted to perform a quick evaluation. In this way, by adjusting the scoring criteria based on the emotion of the employee, a more appropriate evaluation can be performed.

[0101] The integration department can collect employees' work performance data and use it for integration. For example, it can collect employees' project progress and task completion rates, and combine and integrate these data with chat logs and email contents. The integration department can also collect employees' work evaluations and feedback, and use them for evaluating their mental state. In addition, the integration department can capture employees' attendance status and working hours, and track changes in long-term work performance. This makes it possible to comprehensively integrate employees' work performance data and more accurately evaluate their mental state.

[0102] The escalation unit can estimate the employee's emotions and adjust the timing of escalation based on the estimated employee's emotions. For example, if an employee is feeling stressed, escalation can be performed quickly to respond early. Also, if an employee is relaxed, the timing of escalation can be delayed to avoid excessive intervention. Furthermore, if an employee is in a hurry, escalation can be temporarily suspended to allow the employee to concentrate on work. This allows for more appropriate responses by adjusting the timing of escalation based on the employee's emotions.

[0103] The escalation department can collect data on employees' work performance and use it to make escalation decisions. For example, it can collect employees' project progress and task completion rates and use this data to make decisions about whether to escalate. The escalation department can also collect employees' work evaluations and feedback and use this data to make escalation decisions. Furthermore, the escalation department can record employees' attendance status and working hours to track changes in long-term work performance. This allows for a comprehensive evaluation of employees' work performance data, enabling more appropriate escalation.

[0104] The analysis unit can estimate the employee's emotions and adjust the analysis method based on the estimated employee's emotions. For example, if the employee is feeling stressed, the analysis method can be made more detailed to perform a deeper analysis. Also, if the employee is relaxed, the analysis method can be simplified to obtain results quickly. Furthermore, if the employee is in a hurry, the analysis can be temporarily stopped to allow the employee to concentrate on work. In this way, more appropriate analysis can be performed by adjusting the analysis method based on the employee's emotions.

[0105] The analysis unit can analyze the employee's past work performance data and determine the focus of the analysis. For example, the analysis can be performed with an emphasis on projects in which the employee showed poor performance in the past. The analysis unit can also analyze the employee's past work evaluations and feedback and perform analysis with an emphasis on specific problem areas. Furthermore, the analysis unit can analyze the employee's past attendance status and working hours to track long-term changes in performance. In this way, the optimal analysis method can be selected by analyzing the employee's past work performance data.

[0106] During analysis, the analysis unit can perform filtering based on the employee's current health condition. For example, if an employee currently has a health problem, chat logs and emails related to that problem can be analyzed with priority. The analysis unit can also filter logs and emails containing specific keywords based on the employee's health data. Furthermore, the analysis unit can adjust the focus of the analysis according to changes in the employee's health condition. This allows more relevant data to be analyzed by filtering based on the employee's current health condition.

[0107] The analysis unit can estimate the employee's emotions and determine the analysis priority based on the estimated employee's emotions. For example, if an employee is feeling stressed, logs and emails related to stress can be prioritized for analysis. Also, if an employee is relaxed, logs and emails related to normal work can be prioritized for analysis. Furthermore, if an employee is in a hurry, logs and emails with high importance can be prioritized for analysis. In this way, by determining the analysis priority based on the employee's emotions, more important data can be analyzed preferentially.

[0108] During analysis, the analysis unit can prioritize analysis of highly relevant logs and emails by taking into account the geographic location information of employees. For example, if an employee is in a specific area, the analysis unit can prioritize analysis of logs and emails related to that area. In addition, if an employee is on a business trip, the analysis unit can prioritize analysis of logs and emails related to the business trip destination. Furthermore, if an employee is working remotely, the analysis unit can prioritize analysis of logs and emails related to the employee's home or remote work destination. In this way, more relevant data can be analyzed by taking into account the geographic location information of employees.

[0109] The process flow of the second embodiment will be briefly described below.

[0110] Step 1: The analysis unit analyzes employees' chat logs and emails. For example, using a generative AI, it extracts negative words from chat logs and emails and calculates their frequency. Specifically, it extracts negative words such as "tired" and "stressed" from chat logs and emails and calculates their frequency. Step 2: The scoring section uses the generation AI to score the negative words extracted by the analysis section. Scoring is performed based on the frequency and context of the negative words. For example, the score is calculated based on the frequency of the negative words, and the importance of the negative words is evaluated based on the context, and the score is calculated. Step 3: The integration unit uses generative AI to integrate data such as pulse surveys. For example, pulse survey results, chat logs, and email data can be integrated to comprehensively grasp the employee's mental state. This allows the employee's mental state to be evaluated in real time. Step 4: The Escalation Department uses generative AI to determine who to escalate to based on the data obtained by the Integration Department. For example, if the score is high, the department will be notified, and if certain negative words are frequently used, the case will be escalated to a professional counselor.

[0111] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0112] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0113] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0114] Each of the multiple elements including the above-mentioned analysis unit, scoring unit, integration unit, and escalation unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart device 14, and analyzes chat logs and emails of employees. The scoring unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and scores negative words. The integration unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and integrates data such as pulse surveys. The escalation unit is realized, for example, by the control unit 46A of the smart device 14, and determines the escalation destination. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0121] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0122] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0123] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0124] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0125] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0126] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0127] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0128] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] Each of the multiple elements including the above-mentioned analysis unit, scoring unit, integration unit, and escalation unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart glasses 214, and analyzes chat logs and emails of employees. The scoring unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and scores negative words. The integration unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and integrates data such as pulse surveys. The escalation unit is realized, for example, by the control unit 46A of the smart glasses 214, and determines the escalation destination. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0138] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0141] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] Each of the multiple elements including the above-mentioned analysis unit, scoring unit, integration unit, and escalation unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the headset type terminal 314, and analyzes chat logs and emails of employees. The scoring unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and scores negative words. The integration unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and integrates data such as pulse surveys. The escalation unit is realized, for example, by the control unit 46A of the headset type terminal 314, and determines the escalation destination. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

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

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

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

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

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

[0154] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0155] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0156] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0157] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0158] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0159] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0161] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] Each of the multiple elements including the above-mentioned analysis unit, scoring unit, integration unit, and escalation unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the robot 414, and analyzes chat logs and emails of employees. The scoring unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and scores negative words. The integration unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and integrates data such as pulse surveys. The escalation unit is realized, for example, by the control unit 46A of the robot 414, and determines the escalation destination. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0164] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0165] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0166] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0167] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0168] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0169] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0172] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0173] In addition, 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 upon request from the data processing device 12.

[0174] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0175] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0176] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0177] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0178] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0179] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0180] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0181] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0182] (Appendix 1) an analysis unit that analyzes chat logs or emails of employees; A scoring unit that scores the negative words extracted by the analysis unit; an integration unit that integrates pulse survey data; an escalation unit that determines an escalation destination based on the data obtained by the integration unit; A system characterized by: (Appendix 2) The scoring unit includes: Calculate score based on frequency or context of negative words 2. The system of claim 1, (Appendix 3) The integration unit includes: Collect pulse survey results to get a comprehensive picture of employees' mental health 2. The system of claim 1, (Appendix 4) The escalation unit: Escalation decisions based on score or content 2. The system of claim 1, (Appendix 5) The escalation unit: If your score is high, notify your manager or HR department, and if certain negative words are appearing frequently, escalate to a professional counselor. 2. The system of claim 1, (Appendix 6) The analysis unit is Infer employee sentiment and adjust analysis timing based on the inferred employee sentiment 2. The system of claim 1, (Appendix 7) The analysis unit is Analyze employees' past chat logs or email history and select an analysis method 2. The system of claim 1, (Appendix 8) The analysis unit is During analysis, filter based on employees' current projects and work activities 2. The system of claim 1, (Appendix 9) The analysis unit is Infer employee sentiment and prioritize logs and emails for analysis based on the inferred employee sentiment 2. The system of claim 1, (Appendix 10) The analysis unit is During analysis, the geographic location of employees is taken into account to prioritize the analysis of relevant logs and emails. 2. The system of claim 1, (Appendix 11) The analysis unit is During analysis, analyze employees' social media activities and analyze related logs and emails 2. The system of claim 1, (Appendix 12) The scoring unit includes: Infer employee sentiment and adjust scoring based on the inferred employee sentiment 2. The system of claim 1, (Appendix 13) The scoring unit includes: When scoring, adjust the granularity of the score based on the importance of negative words 2. The system of claim 1, (Appendix 14) The scoring unit includes: During scoring, apply different scoring algorithms depending on the category of negative words. 2. The system of claim 1, (Appendix 15) The scoring unit includes: Estimate employee sentiment and adjust the length of scoring based on the estimated employee sentiment 2. The system of claim 1, (Appendix 16) The scoring unit includes: When scoring, prioritize scores based on when negative words appear 2. The system of claim 1, (Appendix 17) The scoring unit includes: When scoring, adjust the order of scores based on negative word relevance 2. The system of claim 1, (Appendix 18) The integration unit includes: Estimate employee sentiment and adjust integration methods based on estimated employee sentiment 2. The system of claim 1, (Appendix 19) The integration unit includes: Estimate employee sentiment and adjust integration methods based on estimated employee sentiment 2. The system of claim 1, (Appendix 20) The integration unit includes: During consolidation, adjust the granularity of the consolidation based on the importance of the pulse survey results 2. The system of claim 1, (Appendix 21) The integration unit includes: During merging, different merging algorithms are applied depending on the category of the pulse survey. 2. The system of claim 1, (Appendix 22) The integration unit includes: Estimate employee sentiment and prioritize consolidation based on estimated employee sentiment 2. The system of claim 1, (Appendix 23) The integration unit includes: When consolidating, prioritize consolidation based on when pulse surveys are conducted 2. The system of claim 1, (Appendix 24) The integration unit includes: When merging, adjust the order of merging based on the relevance of the pulse survey 2. The system of claim 1, (Appendix 25) The escalation unit: Estimate employee sentiment and adjust escalation strategies based on estimated employee sentiment 2. The system of claim 1, (Appendix 26) The escalation unit: During escalation, adjust the granularity of the escalation based on the severity of the score 2. The system of claim 1, (Appendix 27) The escalation unit: During escalation, apply different escalation algorithms depending on the score category 2. The system of claim 1, (Appendix 28) The escalation unit: Estimate employee sentiment and prioritize escalations based on estimated employee sentiment 2. The system of claim 1, (Appendix 29) The escalation unit: During escalation, prioritize the escalation based on when the score appears 2. The system of claim 1, (Appendix 30) The escalation unit: During escalation, adjust the escalation order based on score relevance 2. The system of claim 1, [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes chat logs or emails of employees; A scoring unit that scores the negative words extracted by the analysis unit; an integration unit that integrates pulse survey data; an escalation unit that determines an escalation destination based on the data obtained by the integration unit; A system characterized by:

2. The scoring unit includes: Calculate score based on frequency or context of negative words 2. The system of claim 1 .

3. The integration unit includes: Collect pulse survey results to get a comprehensive picture of employees' mental health 2. The system of claim 1 .

4. The escalation unit: Escalation decisions based on score or content 2. The system of claim 1 .

5. The escalation unit: If your score is high, notify your manager or HR department, and if certain negative words are appearing frequently, escalate to a professional counselor.

2. The system of claim 1 .

6. The analysis unit is Infer employee sentiment and adjust analysis timing based on the inferred employee sentiment 2. The system of claim 1 .

7. The analysis unit is Analyze employees' past chat logs or email history and select an analysis method 2. The system of claim 1 .

8. The analysis unit is During analysis, filter based on employees' current projects and work activities 2. The system of claim 1 .

Images