system

Abstract

We provide the system. [Solution] Means for collecting and analyzing employee communication information, A means for determining the emotions and stress levels of employees based on the analysis thereof, A means of notifying the administrator based on the judgment result, Methods for collecting opinions from employees anonymously, A means of collecting and reporting such opinions while maintaining anonymity, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] An increase in the employee turnover rate is a problem that seriously affects a company's talent cultivation and organizational efficiency. It is difficult to detect employees' stress and dissatisfaction early and take appropriate measures, which leads to a decline in employees' motivation and enthusiasm. In addition, it often happens that employees' opinions and feedback cannot be effectively incorporated, and the improvement of the workplace environment is delayed. The current system has problems such as insufficient provision of career plans to support employees and improvement proposals for the workplace.

Means for Solving the Problems

[0005] This invention provides a means to determine employees' emotions and stress levels by collecting and analyzing their communication information. By notifying managers based on the results of the assessment, it becomes possible to take countermeasures early. Furthermore, by providing a means to collect anonymous opinions from employees, aggregate them, and report them, the effective use of feedback is promoted. In addition, by analyzing employees' work history and skill data and generating and presenting personalized skill development and career plans, it supports employee growth. By providing a means to analyze communication information within a group to identify areas for improvement in business processes and create and notify optimal improvement proposals, the workplace environment is improved. In this way, it provides a means to achieve employee retention and improved engagement throughout the company.

[0006] An "employee" is an individual who is employed by a company or organization and performs duties on behalf of that company or organization.

[0007] "Communication information" includes electronic messaging data such as emails, chats, and documents sent and received by employees in the workplace.

[0008] "Analysis" refers to the process of processing and interpreting data in order to find specific patterns or trends from the collected data.

[0009] "Emotions" refers to the psychological state or feelings that employees exhibit in their daily work and communication.

[0010] "Stress level" is a measure that indicates the intensity and degree of mental or emotional burden experienced by employees.

[0011] "Judgment" refers to the process of drawing a specific conclusion or evaluation based on the results of an analysis.

[0012] A "manager" refers to an individual within an organization who oversees the work and projects of other employees and supports the achievement of the company's goals.

[0013] "Notification" refers to the act or means of informing relevant parties of specific information.

[0014] "Anonymous" refers to a state where an individual's identifying information is hidden, making it impossible to identify the person.

[0015] "Opinion" refers to an expression indicating what an individual or group thinks or feels about a specific matter.

[0016] "Feedback" refers to the evaluation or opinion returned by the recipient regarding a specific action or situation.

[0017] "Work history" refers to a record that chronologically describes the job content and work experience an individual has been involved in in the past.

[0018] "Skill data" refers to data that systematically summarizes information about an individual's knowledge, skills, and abilities.

[0019] "Career plan" refers to what an individual has systematically shown regarding the career goals and paths they want to achieve in the future.

[0020] "Within the group" refers to among the members within a specific organization or group.

[0021] "Business process" refers to a series of business procedures and activities carried out within an organization, which should be optimized to achieve goals.

[0022] "Improvement proposal" refers to a proposal that aims for a better state than the current situation and shows specific methods and means.

Brief Explanation of Drawings

Embodiments for Carrying Out the Invention

[0024] 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.

[0025] First, the language used in the following description will be explained.

[0026] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0027] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0028] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0029] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0030] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0031] [First Embodiment]

[0032] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0033] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0034] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0036] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0037] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0038] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0039] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0041] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0042] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0043] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0044] The system according to the present invention provides a comprehensive solution for preventing employee turnover and improving employee engagement within a company.

[0045] First, the server collects employee communication information, such as emails and chat messages, in real time. Based on this information, the server uses natural language processing technology to analyze the data and evaluate the employee's emotions and stress level. If the resulting stress score exceeds a certain threshold, the server notifies the administrator with an alert. Upon receiving this notification, the administrator can quickly take the necessary actions.

[0046] Next, users can input their career-related questions into the system. The server then conducts a detailed analysis of the employee's work history and skills data. Based on this, it generates skill development and career plans for the employee and provides appropriate advice to the user via the terminal.

[0047] Furthermore, to propose improvements to the work environment, the server collects and analyzes communication information and business data within the group. Based on this information, it identifies bottlenecks and specific problems in business processes and creates appropriate improvement plans. The terminals have the functionality to notify administrators of these proposals and collect feedback.

[0048] Furthermore, users can anonymously provide opinions and feedback to the system. The server collects these opinions anonymously and periodically generates summarized reports. Terminals can then present these reports to administrators and management to help further improve the work environment.

[0049] As a concrete example, suppose an employee is experiencing stress. The server analyzes the frequency of negative keywords in the employee's emails and determines a high stress score. Based on this, the server automatically notifies the administrator. When a user seeks career advice through the system, the server analyzes the history and suggests specific methods for skill development and online learning resources. The terminal then immediately presents the results to the user, encouraging their self-improvement.

[0050] To implement the present invention, it is necessary to apply the above system architecture and set up data collection and analysis algorithms that are appropriate for the corporate environment. This makes it possible to understand the feelings of employees and provide appropriate care and support.

[0051] The following describes the processing flow.

[0052] Step 1:

[0053] The server collects employee communication information, such as emails and chat messages, in real time. To collect this information, it connects to various communication platforms and retrieves data via the necessary APIs.

[0054] Step 2:

[0055] The server analyzes the collected communication information using natural language processing technology. This analysis identifies keywords and sentence structures that indicate emotion, tone, and stress within the text data, and applies an algorithm to evaluate each employee's emotional state and stress level.

[0056] Step 3:

[0057] The server calculates a stress score based on the analysis results. If the calculated stress score exceeds a pre-set threshold, it determines that the employee is experiencing excessive stress.

[0058] Step 4:

[0059] The server automatically sends notifications to administrators regarding employees with high stress levels. These notifications include the employee's stress score and a summary of the suspected causes.

[0060] Step 5:

[0061] Users log in to the career counseling interface and enter their questions and requests. The career counseling content should include specific details about future goals, desired skill development, etc.

[0062] Step 6:

[0063] The server retrieves the user's work history and current skills data from the database and analyzes it. The analysis considers past achievements, skill growth rates, industry trends, and other factors to develop an optimal career plan.

[0064] Step 7:

[0065] The server generates a career plan and a concrete action plan for skill development based on the user's plan. This includes recommended educational courses, training programs, and next steps to take.

[0066] Step 8:

[0067] The device displays the generated career plan and action plan on the user's screen, prompting them to review and make selections, thereby supporting the user in proactively improving their skills.

[0068] Step 9:

[0069] Users submit anonymous feedback about their workplace through a dedicated form, writing down their opinions and suggestions for improvement. The feedback provided covers topics such as the work environment, management policies, and the quality of communication.

[0070] Step 10:

[0071] The server automatically aggregates and analyzes the collected anonymous feedback. Based on the analysis results, it creates a report that includes improvement suggestions while maintaining anonymity.

[0072] Step 11:

[0073] The terminal presents the generated reports to administrators and management, proposing specific actions for improving the workplace environment. This information is displayed in the form of a dashboard or periodic reports.

[0074] (Example 1)

[0075] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0076] When employee stress and engagement decline significantly within a company, it often negatively impacts organizational performance and employee turnover. However, directly observing employees' accurate emotional states and job satisfaction is difficult, and insufficient timely care and support remain challenges. Furthermore, a lack of support for individual employee skill development and career development also contributes to the difficulty in improving the workplace environment.

[0077] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0078] In this invention, the server includes means for collecting and statistically analyzing information, means for inferring emotions or psychological states based on the analysis, and means for providing information to administrators based on the inference results. This makes it possible to grasp the emotional state of employees in real time and provide intervention and support at the appropriate time. Furthermore, by providing means for anonymous opinion collection and analysis of work history and skills information, it becomes possible to create career plans tailored to individual employees and promote improvements in the workplace environment throughout the organization.

[0079] "Information" refers to data transmitted by organizations and individuals, encompassing all communications related to emotions and business operations.

[0080] "Statistical analysis" is the process of analyzing collected data using statistical methods to extract meaningful information.

[0081] "Emotion" refers to an element that indicates an individual's psychological state, and is a numerical evaluation of positive or negative mental processes.

[0082] "Psychological state" refers to an individual's overall mental condition, including their emotions, mood, and level of stress.

[0083] "Inference" is the process of predicting a state that has not yet been clearly observed, based on collected data.

[0084] A "manager" is someone within an organization who is responsible for supervising the work of other members and helping them achieve their best performance.

[0085] "Providing information" means presenting insights and warnings obtained from analysis in an appropriate manner, and giving the target audience the material they need to make decisions.

[0086] "Opinion gathering" refers to obtaining diverse feedback through a process in which users can anonymously submit their thoughts and opinions.

[0087] "Work history" refers to a record of the duties and responsibilities an employee has held in the past, and is information that indicates their professional experience.

[0088] "Skills information" refers to data on the knowledge and abilities possessed by individual employees and is used to evaluate their skill levels and expertise.

[0089] A "career plan" is a proposal or blueprint that outlines the career goals and career path that an employee wishes to achieve in the future.

[0090] The system for realizing this invention is configured as follows: The server is primarily responsible for automatically collecting information through communication methods (email, chat, etc.) used by employees within the company. In this process, an API is used to efficiently acquire communication information. Specifically, it is common to use the email protocol for email systems and the messaging API for chat systems.

[0091] The server uses natural language processing techniques to perform sentiment analysis on the collected information. Libraries such as Python's NLTK and spaCy can be used to extract key phrases and quantify employees' emotions and stress levels.

[0092] Users can input questions and concerns about their careers through the system's interface. The entered data is sent to the server, which performs a detailed analysis based on past work experience and skills information. Analysis tools such as Pandas and Scikit-learn can be used for data processing. Based on the results of this analysis, the system generates skill improvement suggestions and career plans for the user.

[0093] The generated career plan and advice are displayed to the user via their device. The device interface is designed to be intuitive and easy for users to understand, and is provided as a web application. This allows users to quickly access recommended actions and learning resources.

[0094] Furthermore, the server analyzes communication information and business data within the group to identify potential problems occurring within business processes. This analysis utilizes data streaming using Apache® Kafka and Hadoop for big data analysis. For identified areas for improvement, appropriate improvement suggestions are formulated and provided to the administrator. This information is notified to the administrator via the terminal, and feedback is also collected.

[0095] Furthermore, users can submit feedback anonymously to the system, and the server compiles this feedback to create a summary report. This report is presented to administrators and management via terminals and used to improve the work environment.

[0096] As a concrete example, by inputting a prompt such as "What workplace improvements would be effective in reducing employee stress levels?" into the AI ​​model, the AI ​​can generate improvement measures and present them to managers as actionable suggestions. Through this entire process, companies can understand their employees' feelings and respond quickly and appropriately, thereby revitalizing the workplace and improving employee satisfaction.

[0097] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0098] Step 1:

[0099] The server collects communication information from the company's email and chat systems. Input includes each employee's email data and chat logs. This data is retrieved in real time using an API, organized, and stored in a database. Specifically, it calls the communication platform's API and receives the data in JSON format. Then, it parses the JSON data to extract the necessary information and prepares it for analysis.

[0100] Step 2:

[0101] The server applies natural language processing to the collected communication information to perform sentiment analysis. The input is the message text obtained in step 1. The server uses Python's NLTK and spaCy libraries to tokenize the text data and calculate sentiment scores. The output of this process is the sentiment score and stress level associated with each message, which is used to evaluate the psychological state of employees.

[0102] Step 3:

[0103] The server notifies the administrator of the results of the sentiment analysis. The inputs are the sentiment score and stress level generated in step 2. If these exceed a certain threshold, the server sends an alert to the administrator using Twilio or the SMTP protocol. Specifically, it generates the body of the alert email and sends the notification to the specified recipient address.

[0104] Step 4:

[0105] Users input career consultations through the system interface. This input includes questions and consultation details from individual employees. This information is entered into a web form or chatbot and sent to the server. Specific operations include validating the input data on the user interface and sending that data to the server.

[0106] Step 5:

[0107] The server analyzes employee work history and skill data based on career consultations from users. The input consists of employee work history data and the consultation content from step 4. This data is analyzed using Pandas and Scikit-learn to generate skill development methods and career plans. The output of this process is a career plan tailored to each employee, supporting users in their independent growth.

[0108] Step 6:

[0109] The terminal presents the user with the career plan received from the server. The input is the career plan generated in step 5. This is displayed on the user interface and summarized in a way that the user can easily understand. Specifically, the key points of the career plan are displayed on the web dashboard, and links to related resources are provided.

[0110] Step 7:

[0111] The server analyzes communication information and business data within a group to generate suggestions for improving business processes. Input includes communication information and business performance data from the entire organization. This data is analyzed using big data technologies such as Hadoop to identify bottlenecks. The improvement suggestions based on this analysis are crucial for streamlining business workflows. The output consists of specific improvement suggestions, which are provided to administrators.

[0112] Step 8:

[0113] The terminal notifies the administrator of improvement suggestions from the server and collects feedback. The input is the improvement suggestion generated in step 7. This is notified to the administrator's console and provides a function to record feedback on the improvement suggestion. Specifically, the system communicates business improvement suggestions to the administrator through the notification system and collects opinions through a feedback form.

[0114] Step 9:

[0115] Users provide feedback to the system anonymously. The input consists of anonymous feedback and suggestions from employees. Users fill out a pre-prepared form and submit it to the server. This process includes anonymization techniques to prevent the identification of individuals.

[0116] Step 10:

[0117] The server aggregates anonymously collected opinions and compiles them into regular reports. The input is the anonymous feedback obtained in step 9. This is stored in a database and aggregated at regular intervals to generate a summary report. This report is provided to managers and management to help with the continuous improvement of the work environment.

[0118] (Application Example 1)

[0119] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0120] Within a company, it is difficult to grasp employee stress and emotions in real time and take appropriate action quickly based on that information. Furthermore, providing employees with concrete career advancement opportunities and mechanisms to encourage self-growth are also crucial challenges. In addition, there is a need to collect feedback while maintaining anonymity, identify bottlenecks in operations, and implement countermeasures, all with the aim of continuously improving the workplace environment. The need for a system that can comprehensively manage employee mental health and career programs is increasing.

[0121] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0122] In this invention, the server includes means for collecting and analyzing employee communication information, means for determining the employee's emotions and stress level, and means for notifying the administrator based on the determination results. This enables appropriate monitoring of employees' mental health status within the company and allows for quick and effective responses. Furthermore, it supports employee self-growth by analyzing work history and skill data and generating and presenting career plans. At the same time, it contributes to improving the work environment by collecting anonymous feedback, identifying areas for improvement in the workplace, and notifying administrators of optimal improvement suggestions.

[0123] "Communication information" refers to data that includes the content of emails, chats, and other communications used by employees for work purposes.

[0124] "Emotional and stress levels" are indicators that show the psychological state of employees and are used to evaluate the mental health status in that workplace environment.

[0125] A "manager" refers to a person within a company who is responsible for managing employees' duties and mental health, and taking appropriate action as needed.

[0126] "Anonymity" refers to a state in which care is taken to ensure that the individual providing the information is not identified, thereby providing an environment where people can express their opinions with peace of mind.

[0127] "Work history" refers to information that includes records of the work performed, positions held, and achievements of an employee to date.

[0128] "Skill data" refers to data that includes information about the knowledge, skills, and abilities that employees possess.

[0129] A "career plan" outlines the job goals and necessary skill development plans that employees should achieve in the future.

[0130] A "bottleneck" refers to an obstacle or point in a business process that reduces efficiency and is an area that needs improvement.

[0131] To realize this invention, a server, a terminal, and a user must work together to form a system. The server collects communication information from employees within the company in real time and analyzes the data using natural language processing technology to determine emotions and stress levels. Google's Cloud Natural Language API is suitable as the software to use. If the determined stress score exceeds a certain threshold, the server immediately notifies the administrator.

[0132] Users access the system using their smartphones or computers and input their career-related questions. The server generates a career plan based on the employee's work history and skills data, and presents advice to the user via their device. PostgreSQL is used as the database, and Node.js and Express are used for the backend.

[0133] Anonymous feedback is collected using an app built with React Native, and the opinions are aggregated and compiled into a report by a server. This report is presented to administrators and management via the user's device, contributing to improvements in the work environment.

[0134] For example, if an employee sends an email containing keywords indicating work-related stress, the server analyzes the content and calculates a high stress score. Based on these results, it automatically suggests online resources for leadership training and stress management to the administrator. Furthermore, users can receive specific advice from the generating AI model by entering prompts such as, "Please tell me my current stress level and suggestions for career improvement."

[0135] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0136] Step 1:

[0137] The server collects employee email and chat data from the company's internal communication platform as input. This data is converted into a format that can be analyzed in real time, preparing it for natural language processing. As output, it generates parseable text data.

[0138] Step 2:

[0139] The server uses the Google Cloud Natural Language API to analyze text data. Specifically, it performs sentiment analysis to detect sentiment scores and stress levels based on individual messages. The output of this process is each employee's stress score.

[0140] Step 3:

[0141] The server checks if the stress score, which is the result of the analysis, exceeds a certain threshold. This threshold is pre-configured, and when the score exceeds it, an alert is sent to the administrator. The alert includes a brief explanation of the employee's stress level.

[0142] Step 4:

[0143] Users input their career consultation requests into the system using their smartphones or computers. The server then uses this input to read the employee's work history and skills data from a database and applies it to a career plan generation algorithm. The output of this algorithm is a proposal for skill development and a career plan.

[0144] Step 5:

[0145] The device presents the generated career plan to the user through the user interface. The user can refer to this plan and obtain a concrete action plan for self-improvement. At this point, the user can also provide the generating AI model with the prompt "Please give me suggestions for improving my skills" to obtain further advice.

[0146] Step 6:

[0147] The terminal collects user feedback through an anonymous feedback input function and sends it to the server. The server aggregates and analyzes the received feedback and generates a report for improving the workplace environment. This report is provided to administrators, contributing to the improvement process.

[0148] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0149] This invention provides a system that combines an emotion engine to more accurately determine employees' emotions and stress levels. This system is designed to effectively prevent employee turnover and improve employee engagement.

[0150] The server not only collects and analyzes communication information, but also utilizes an emotion engine to recognize emotions from text. This emotion engine uses natural language processing techniques and machine learning algorithms to identify emotions in text data and evaluate their degree. The server integrates this emotion data with previous analysis results to determine more detailed emotions and stress levels. These detailed results are used to more accurately understand employees' health and mental burden.

[0151] Furthermore, the server generates personalized notifications and suggestions based on this emotion recognition. For example, if an employee has negative emotions indicating a high stress level, the server creates suggestions that provide resources and support to help alleviate that stress. The terminal then presents these suggestions to the employee, making them readily available.

[0152] As a concrete example, consider a case where a user experiences anxiety about communication in their daily work. The server collects the user's chat records and analyzes them using an emotion engine. From this analysis, it determines whether the user is experiencing anxiety or stress. The server then suggests mental health support resources to the user and guides them to use these resources via their device. This allows for early intervention before the problem escalates.

[0153] The server also aggregates anonymous feedback data and uses a sentiment engine to analyze the sentiment of the posts. Based on this analysis, it categorizes the feedback, understands the overall sentiment trends of the company, and reports areas for improvement to administrators.

[0154] To implement this invention, it is necessary to integrate the emotion engine with existing employee management systems and build a framework for follow-up based on individual emotion data. This will enable companies to rapidly and accurately support the mental health of their employees.

[0155] The following describes the processing flow.

[0156] Step 1:

[0157] The server collects employee email and chat communication information in real time. APIs and data pipelines are used for collection, creating a system that efficiently gathers data from various platforms.

[0158] Step 2:

[0159] The server supplies the collected communication information to the emotion engine. The emotion engine uses natural language processing (NLP) to analyze the text data and identify each employee's emotional tone and subjective emotional state. Specifically, it evaluates keywords and context within the text to generate an emotion score.

[0160] Step 3:

[0161] The server integrates emotional scores with employee profile data to determine detailed emotional states and stress levels. This allows for an assessment of how much attention is needed based on the stress score.

[0162] Step 4:

[0163] The server automatically generates personalized notifications and suggestions based on the determined emotional state and stress level. For example, if the user is experiencing high stress levels, it will suggest resources and support contacts that can help reduce stress.

[0164] Step 5:

[0165] The device displays generated notifications and suggestions to the user. These notifications are sent to the user's mobile device or PC, designed for immediate review.

[0166] Step 6:

[0167] Users review notifications and suggestions received through their devices and utilize the provided resources and support as needed. This usage data is also reflected in subsequent analyses and stored as learning material for the system.

[0168] Step 7:

[0169] Users submit their opinions about the work environment through an anonymous feedback form. The submitted feedback is used as an opportunity for them to express their dissatisfaction and suggestions for improvement.

[0170] Step 8:

[0171] The server analyzes anonymously collected feedback using an emotion engine. It analyzes the emotional tone of the feedback and assesses the overall emotional trends within the organization. This classifies the feedback as positive, negative, or neutral.

[0172] Step 9:

[0173] Based on the sentiment analysis results, the server generates a report identifying areas for improvement. This report includes specific improvement suggestions based on the feedback, which can be used to support decision-making across the organization.

[0174] Step 10:

[0175] The terminals facilitate quick action by displaying generated reports on a dashboard accessible to administrators and management. This visualization aims to continuously improve the overall organizational environment.

[0176] (Example 2)

[0177] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0178] There is a growing need to accurately monitor employees' emotions and stress levels and provide appropriate support early on. However, traditional systems struggle to grasp the emotional state of individual employees in real time and to provide rapid, individualized follow-up. Furthermore, they lack sufficient functionality to effectively utilize employee feedback to improve the organization as a whole.

[0179] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0180] In this invention, the server includes means for collecting and preprocessing employee information, means for identifying and evaluating emotions using natural language processing techniques and machine learning algorithms, and means for generating personalized suggestions based on emotions and stress levels. This makes it possible to understand employees' emotions and stress levels in more detail and quickly, and to provide appropriate support.

[0181] "Information" refers to all data collected from employee emails, chat history, internal social media posts, and other sources.

[0182] "Preprocessing" refers to the process of cleaning and tokenizing data in order to convert collected information into an analyzable format.

[0183] "Natural language processing technology" refers to the technology used by computers to understand human language and interpret emotions and intentions.

[0184] A "machine learning algorithm" refers to a method that automatically learns rules and knowledge from data to perform classification and prediction.

[0185] "Sentiment identification and evaluation" refers to the process of extracting emotions from text and analyzing the type and intensity of those emotions.

[0186] "Proposal generation" refers to creating specific action plans and resources to provide to employees based on the analysis results.

[0187] This invention provides a system for accurately identifying and responding quickly to employee emotions and stress levels. This enables companies to improve employee well-being and support efficient business operations. The system is implemented with a configuration including servers, terminals, and users.

[0188] The server collects various employee information and is equipped with an emotion engine that uses natural language processing technology and machine learning algorithms. The server first collects information, cleans up unnecessary data, and performs preprocessing by tokenizing it. Then, it identifies emotions from the text using natural language processing technology and evaluates the degree of those emotions using machine learning algorithms. This process makes it possible to specifically understand which employees are experiencing stress.

[0189] The terminal receives notifications from the server and provides personalized suggestions to individual employees. For example, if a particular employee shows signs of stress, the terminal will present them with resources and support information to alleviate that stress. This information is provided in the form of links or other means for instant access.

[0190] Users can use the system while maintaining their privacy and can also provide feedback anonymously. This allows for more feedback to be gathered, which helps to understand the sentiment trends across the organization.

[0191] As a concrete example, consider the case of a user who experiences anxiety in their daily work. The server uses a generative AI model to execute a prompt message, "Analyze the emotion of this text," and analyzes the user's chat history. If the emotion engine identifies anxiety, the server generates a notification that includes relaxation techniques and counseling services. The terminal presents this to the user, and continuous monitoring is performed to determine if support is needed.

[0192] By implementing this system, companies can provide prompt and appropriate support to their employees, significantly contributing to the improvement of the workplace environment.

[0193] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0194] Step 1:

[0195] The server collects information such as employee emails, chat history, and internal social media posts. The input consists of unprocessed data from each information source. The server uses APIs to collect this data and performs real-time data ingestion. The output is a raw dataset awaiting preprocessing.

[0196] Step 2:

[0197] The server preprocesses the collected raw data. The input is the raw data collected in Step 1. In this step, data cleaning is performed to remove meaningless strings and special characters. Furthermore, the data is tokenized and converted into a format that is easy to analyze using natural language processing. The output is a clean, tokenized dataset.

[0198] Step 3:

[0199] The server identifies and evaluates emotions using natural language processing techniques and machine learning algorithms. The input is tokenized data processed in step 2. The emotion engine utilizes a generative AI model and executes the prompt "Analyze the emotion of this text" to detect the emotional state of each message. The output is a dataset with emotion labels.

[0200] Step 4:

[0201] The server calculates each employee's stress level based on the results of the sentiment analysis. The input is the sentiment-labeled data obtained in step 3. The stress level is quantified by comparing it to a pre-set baseline value. The output is a dataset containing each employee's stress level.

[0202] Step 5:

[0203] The server generates personalized suggestions for employees based on their emotions and stress levels. The input is the stress level data obtained in step 4. Using the generation AI model, it creates a specific action plan based on the prompt message, "Create suggestions for employees showing signs of high stress." The output is a dataset of personalized suggestions as notification content.

[0204] Step 6:

[0205] The terminal receives the suggestion notification sent from the server and presents it to the employee. The input is the individual suggestion data generated in step 5. Specifically, the notification is displayed on the terminal and includes links and action buttons to allow the employee to easily access resources. The output is the notification display information as provided to the employee.

[0206] Step 7:

[0207] The server collects and analyzes anonymous feedback from employees. Input data is gathered through feedback forms and surveys. An emotion engine is used to classify the feedback content and analyze the organization's emotional trends. The output is an organizational emotional analysis report.

[0208] (Application Example 2)

[0209] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0210] The current lack of detailed assessments of employees' emotions and stress levels presents a challenge in implementing appropriate measures to prevent turnover and improve engagement. Furthermore, the absence of a system for emotionally evaluating employee feedback and understanding the overall emotional trends within the organization makes it difficult to implement swift and effective corrective measures.

[0211] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0212] In this invention, the server includes means for collecting and analyzing employee communication information, means for determining emotions and stress levels based on the analysis and proposing stress reduction measures as necessary, means for notifying employees and managers, and means for anonymously collecting opinions and evaluating emotions. This enables detailed information about employees' mental states and early intervention for appropriate improvements.

[0213] "Communication information" refers to text data such as emails and chat messages exchanged by employees in the course of their work.

[0214] An "emotion engine" is a system that uses natural language processing technology and machine learning algorithms to identify emotions from text data and evaluate their intensity.

[0215] "Stress level" refers to the degree of mental burden on an employee, as determined by an emotional engine.

[0216] "Methods for collecting opinions anonymously" refer to ways in which employees can provide their opinions without them being known to third parties.

[0217] "Follow-up" refers to activities that provide ongoing support and suggestions to employees based on emotional data.

[0218] "Emotional trends" refer to the overall patterns and tendencies of individual employees' emotions within an organization.

[0219] An "improvement proposal" is a plan that outlines specific measures to address business processes and organizational sentiment based on the analysis results.

[0220] The system that realizes this invention implements a program that collects and analyzes employee communication information. The server collects text data from messaging apps and email systems that employees use on a daily basis and analyzes it using natural language processing technology and machine learning algorithms. For the analysis, generative AI models suitable for sentiment analysis, such as Google's BERT model or OpenAI's GPT-3, are used.

[0221] The emotion engine identifies emotions from text data and determines stress levels. Based on this information, the server suggests stress relief measures and mental health support resources, and sends notifications to administrators and the employee via their devices. The notifications include links to specific resources and methods for mental health care.

[0222] Furthermore, anonymous feedback is collected from employees, and emotional evaluations are performed using an emotion engine to understand the emotional trends of the entire organization. The server aggregates this data, reports the company's overall emotional trends to managers, and proposes necessary business improvements and support systems.

[0223] As a concrete example, when a user experiences communication difficulties during delivery work, the server analyzes the message content and sends a follow-up notification to the user guiding them to a counseling service to reduce stress. Links to the necessary resources are provided in a format that can be immediately accessed on a smartphone. This process supports employees' mental health early on and improves job satisfaction.

[0224] Examples of prompt statements are as follows:

[0225] "Explain how to create a program that assesses employees' emotions and stress levels and suggests appropriate support resources."

[0226] "Please provide specific steps for analyzing an organization's emotional trends based on emotional data and proposing improvement plans."

[0227] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0228] Step 1:

[0229] The server collects text data from messaging apps and email systems used by employees. In this step, the collected text data is sent to the server as input, preparing foundational data for a comprehensive understanding of employee intent and context. The output is a set of verified text data.

[0230] Step 2:

[0231] The server uses an emotion engine to analyze the collected text data and identify the emotion (positive, negative, or neutral) of each message. The input is the text data obtained in step 1, and natural language processing techniques and machine learning algorithms (e.g., BERT, GPT-3) are used. The output is the emotion determination result for each message.

[0232] Step 3:

[0233] The server quantifies the stress level of employees based on the sentiment analysis results. To calculate the stress score, an algorithm for quantifying the degree of stress is applied using the output of the sentiment engine as input. The output is the stress score for each employee, and appropriate resource proposals are made based on this score.

[0234] Step 4:

[0235] The user receives a notification of the stress level sent from the server on the terminal. The inputs are the stress score and the proposed content based on it, and the output is a notification message that the user can confirm. As an operation, the user is enabled to access the proposed mental health support resources.

[0236] Step 5:

[0237] The server receives the feedback provided by employees from the anonymous opinion collection form and analyzes it with the sentiment engine. The input is the text data of the anonymous feedback, and sentiment evaluation and opinion classification are performed. The output is the sentiment evaluation result and the categorized feedback.

[0238] Step 6:

[0239] The server creates a report for reporting the overall sentiment trend of the organization to the administrator based on the aggregated feedback data and the sentiment analysis results. The input is the output of Step 5, and the output is a report for the administrator that includes visualized data. This enables the formulation of business improvements and support systems as needed.

[0240] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0241] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0242] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0243] [Second Embodiment]

[0244] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0245] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0246] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0247] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0248] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0249] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0250] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0251] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0252] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0253] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0254] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0255] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0256] The system according to the present invention provides a comprehensive solution for preventing employee turnover and improving employee engagement within a company.

[0257] First, the server collects employee communication information, such as emails and chat messages, in real time. Based on this information, the server uses natural language processing technology to analyze the data and evaluate the employee's emotions and stress level. If the resulting stress score exceeds a certain threshold, the server notifies the administrator with an alert. Upon receiving this notification, the administrator can quickly take the necessary actions.

[0258] Next, users can input their career-related questions into the system. The server then conducts a detailed analysis of the employee's work history and skills data. Based on this, it generates skill development and career plans for the employee and provides appropriate advice to the user via the terminal.

[0259] Furthermore, to propose improvements to the work environment, the server collects and analyzes communication information and business data within the group. Based on this information, it identifies bottlenecks and specific problems in business processes and creates appropriate improvement plans. The terminals have the functionality to notify administrators of these proposals and collect feedback.

[0260] Furthermore, users can anonymously provide opinions and feedback to the system. The server collects these opinions anonymously and periodically generates summarized reports. Terminals can then present these reports to administrators and management to help further improve the work environment.

[0261] As a concrete example, suppose an employee is experiencing stress. The server analyzes the frequency of negative keywords in the employee's emails and determines a high stress score. Based on this, the server automatically notifies the administrator. When a user seeks career advice through the system, the server analyzes the history and suggests specific methods for skill development and online learning resources. The terminal then immediately presents the results to the user, encouraging their self-improvement.

[0262] To implement the present invention, it is necessary to apply the above system architecture and set up data collection and analysis algorithms that are appropriate for the corporate environment. This makes it possible to understand the feelings of employees and provide appropriate care and support.

[0263] The following describes the processing flow.

[0264] Step 1:

[0265] The server collects employee communication information, such as emails and chat messages, in real time. To collect this information, it connects to various communication platforms and retrieves data via the necessary APIs.

[0266] Step 2:

[0267] The server analyzes the collected communication information using natural language processing technology. This analysis identifies keywords and sentence structures that indicate emotion, tone, and stress within the text data, and applies an algorithm to evaluate each employee's emotional state and stress level.

[0268] Step 3:

[0269] The server calculates a stress score based on the analysis results. If the calculated stress score exceeds a pre-set threshold, it determines that the employee is experiencing excessive stress.

[0270] Step 4:

[0271] The server automatically sends notifications to administrators regarding employees with high stress levels. These notifications include the employee's stress score and a summary of the suspected causes.

[0272] Step 5:

[0273] Users log in to the career counseling interface and enter their questions and requests. The career counseling content should include specific details about future goals, desired skill development, etc.

[0274] Step 6:

[0275] The server retrieves the user's work history and current skills data from the database and analyzes it. The analysis considers past achievements, skill growth rates, industry trends, and other factors to develop an optimal career plan.

[0276] Step 7:

[0277] The server generates a formulated career plan and a specific action plan for skill improvement. The generated content includes recommended educational courses, training programs, the next steps to be taken, and so on.

[0278] Step 8:

[0279] The terminal displays the generated career plan and action plan on the user's screen and encourages confirmation and selection, thereby assisting the user to proactively improve their skills.

[0280] Step 9:

[0281] The user posts anonymous feedback regarding the workplace from a dedicated form and writes down opinions and improvement wishes. The provided feedback content relates to the business environment, management policies, quality of communication, and so on.

[0282] Step 10:

[0283] The server automatically aggregates and analyzes the collected anonymous feedback. Based on the analysis results, a report including improvement proposals is created while maintaining anonymity. <​​​​​​​​​​​​​​​​​​When employee stress and engagement decline significantly within a company, it often negatively impacts organizational performance and employee turnover. However, directly observing employees' accurate emotional states and job satisfaction is difficult, and insufficient timely care and support remain challenges. Furthermore, a lack of support for individual employee skill development and career development also contributes to the difficulty in improving the workplace environment.

[0289] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0290] In this invention, the server includes means for collecting and statistically analyzing information, means for inferring emotions or psychological states based on the analysis, and means for providing information to administrators based on the inference results. This makes it possible to grasp the emotional state of employees in real time and provide intervention and support at the appropriate time. Furthermore, by providing means for anonymous opinion collection and analysis of work history and skills information, it becomes possible to create career plans tailored to individual employees and promote improvements in the workplace environment throughout the organization.

[0291] "Information" refers to data transmitted by organizations and individuals, encompassing all communications related to emotions and business operations.

[0292] "Statistical analysis" is the process of analyzing collected data using statistical methods to extract meaningful information.

[0293] "Emotion" refers to an element that indicates an individual's psychological state, and is a numerical evaluation of positive or negative mental processes.

[0294] "Psychological state" refers to an individual's overall mental condition, including their emotions, mood, and level of stress.

[0295] "Inference" is the process of predicting a state that has not yet been clearly observed, based on collected data.

[0296] A "manager" is someone within an organization who is responsible for supervising the work of other members and helping them achieve their best performance.

[0297] "Providing information" means presenting insights and warnings obtained from analysis in an appropriate manner, and giving the target audience the material they need to make decisions.

[0298] "Opinion gathering" refers to obtaining diverse feedback through a process in which users can anonymously submit their thoughts and opinions.

[0299] "Work history" refers to a record of the duties and responsibilities an employee has held in the past, and is information that indicates their professional experience.

[0300] "Skills information" refers to data on the knowledge and abilities possessed by individual employees and is used to evaluate their skill levels and expertise.

[0301] A "career plan" is a proposal or blueprint that outlines the career goals and career path that an employee wishes to achieve in the future.

[0302] The system for realizing this invention is configured as follows: The server is primarily responsible for automatically collecting information through communication methods (email, chat, etc.) used by employees within the company. In this process, an API is used to efficiently acquire communication information. Specifically, it is common to use the email protocol for email systems and the messaging API for chat systems.

[0303] The server uses natural language processing techniques to perform sentiment analysis on the collected information. Libraries such as Python's NLTK and spaCy can be used to extract key phrases and quantify employees' emotions and stress levels.

[0304] Users can input consultations and questions regarding their careers through the system interface. The input data is sent to the server, which conducts a detailed analysis based on past work experience and skill information. Analytical tools such as Pandas and Scikit-learn can be used for data processing. Based on the analysis results, career improvement plans and career plans for users are generated.

[0305] The generated career plans and advice are displayed to the user through the terminal. The terminal-side interface is designed to be intuitively understandable for the user and is provided as a web application. This enables the user to immediately access the recommended actions and learning resources.

[0306] Furthermore, the server analyzes the communication information and business data within the group to identify potential problems occurring in the business process. For this analysis, data streaming using Apache Kafka and Hadoop for big data analysis are utilized. Regarding the identified areas for improvement, appropriate improvement proposals are formulated and provided to the administrator. This information is notified to the administrator through the terminal, and feedback is also collected.

[0307] In addition, users can submit opinions to the system anonymously, and the server aggregates this and creates a summary report. This report is presented to the administrator and management through the terminal and is utilized for improving the workplace environment.

[0308] As a specific example, by inputting a prompt sentence such as "What workplace improvements are effective in reducing the stress levels of employees?" to the generative AI model, the AI can generate improvement measures and present them to the administrator as executable proposals. Through this series of processes, the company can understand the feelings of employees and take prompt and appropriate actions to activate the workplace and improve employee satisfaction.

[0309] The flow of the specific process in Example 1 will be described using FIG. 11.

[0310] Step 1:

[0311] The server collects communication information from the company's email and chat systems. Input includes each employee's email data and chat logs. This data is retrieved in real time using an API, organized, and stored in a database. Specifically, it calls the communication platform's API and receives the data in JSON format. Then, it parses the JSON data to extract the necessary information and prepares it for analysis.

[0312] Step 2:

[0313] The server applies natural language processing to the collected communication information to perform sentiment analysis. The input is the message text obtained in step 1. The server uses Python's NLTK and spaCy libraries to tokenize the text data and calculate sentiment scores. The output of this process is the sentiment score and stress level associated with each message, which is used to evaluate the psychological state of employees.

[0314] Step 3:

[0315] The server notifies the administrator of the results of the sentiment analysis. The inputs are the sentiment score and stress level generated in step 2. If these exceed a certain threshold, the server sends an alert to the administrator using Twilio or the SMTP protocol. Specifically, it generates the body of the alert email and sends the notification to the specified recipient address.

[0316] Step 4:

[0317] Users input career consultations through the system interface. This input includes questions and consultation details from individual employees. This information is entered into a web form or chatbot and sent to the server. Specific operations include validating the input data on the user interface and sending that data to the server.

[0318] Step 5:

[0319] The server analyzes employee work history and skill data based on career consultations from users. The input consists of employee work history data and the consultation content from step 4. This data is analyzed using Pandas and Scikit-learn to generate skill development methods and career plans. The output of this process is a career plan tailored to each employee, supporting users in their independent growth.

[0320] Step 6:

[0321] The terminal presents the user with the career plan received from the server. The input is the career plan generated in step 5. This is displayed on the user interface and summarized in a way that the user can easily understand. Specifically, the key points of the career plan are displayed on the web dashboard, and links to related resources are provided.

[0322] Step 7:

[0323] The server analyzes communication information and business data within a group to generate suggestions for improving business processes. Input includes communication information and business performance data from the entire organization. This data is analyzed using big data technologies such as Hadoop to identify bottlenecks. The improvement suggestions based on this analysis are crucial for streamlining business workflows. The output consists of specific improvement suggestions, which are provided to administrators.

[0324] Step 8:

[0325] The terminal notifies the administrator of improvement suggestions from the server and collects feedback. The input is the improvement suggestion generated in step 7. This is notified to the administrator's console and provides a function to record feedback on the improvement suggestion. Specifically, the system communicates business improvement suggestions to the administrator through the notification system and collects opinions through a feedback form.

[0326] Step 9:

[0327] Users provide feedback to the system anonymously. The input consists of anonymous feedback and suggestions from employees. Users fill out a pre-prepared form and submit it to the server. This process includes anonymization techniques to prevent the identification of individuals.

[0328] Step 10:

[0329] The server aggregates anonymously collected opinions and compiles them into regular reports. The input is the anonymous feedback obtained in step 9. This is stored in a database and aggregated at regular intervals to generate a summary report. This report is provided to managers and management to help with the continuous improvement of the work environment.

[0330] (Application Example 1)

[0331] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0332] Within a company, it is difficult to grasp employee stress and emotions in real time and take appropriate action quickly based on that information. Furthermore, providing employees with concrete career advancement opportunities and mechanisms to encourage self-growth are also crucial challenges. In addition, there is a need to collect feedback while maintaining anonymity, identify bottlenecks in operations, and implement countermeasures, all with the aim of continuously improving the workplace environment. The need for a system that can comprehensively manage employee mental health and career programs is increasing.

[0333] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0334] In this invention, the server includes means for collecting and analyzing employee communication information, means for determining the employee's emotions and stress level, and means for notifying the administrator based on the determination results. This enables appropriate monitoring of employees' mental health status within the company and allows for quick and effective responses. Furthermore, it supports employee self-growth by analyzing work history and skill data and generating and presenting career plans. At the same time, it contributes to improving the work environment by collecting anonymous feedback, identifying areas for improvement in the workplace, and notifying administrators of optimal improvement suggestions.

[0335] "Communication information" refers to data that includes the content of emails, chats, and other communications used by employees for work purposes.

[0336] "Emotional and stress levels" are indicators that show the psychological state of employees and are used to evaluate the mental health status in that workplace environment.

[0337] A "manager" refers to a person within a company who is responsible for managing employees' duties and mental health, and taking appropriate action as needed.

[0338] "Anonymity" refers to a state in which care is taken to ensure that the individual providing the information is not identified, thereby providing an environment where people can express their opinions with peace of mind.

[0339] "Work history" refers to information that includes records of the work performed, positions held, and achievements of an employee to date.

[0340] "Skill data" refers to data that includes information about the knowledge, skills, and abilities that employees possess.

[0341] A "career plan" outlines the job goals and necessary skill development plans that employees should achieve in the future.

[0342] A "bottleneck" refers to an obstacle or point in a business process that reduces efficiency and is an area that needs improvement.

[0343] To realize this invention, a server, a terminal, and a user must work together to form a system. The server collects communication information from employees within the company in real time and analyzes the data using natural language processing technology to determine emotions and stress levels. Google Cloud Natural Language API is suitable as the software to use. If the determined stress score exceeds a certain threshold, the server immediately notifies the administrator.

[0344] Users access the system using their smartphones or computers and input their career-related questions. The server generates a career plan based on the employee's work history and skills data, and presents advice to the user via their device. PostgreSQL is used as the database, and Node.js and Express are used for the backend.

[0345] Anonymous feedback is collected using an app built with React Native, and the opinions are aggregated and compiled into a report by a server. This report is presented to administrators and management via the user's device, contributing to improvements in the work environment.

[0346] For example, if an employee sends an email containing keywords indicating work-related stress, the server analyzes the content and calculates a high stress score. Based on these results, it automatically suggests online resources for leadership training and stress management to the administrator. Furthermore, users can receive specific advice from the generating AI model by entering prompts such as, "Please tell me my current stress level and suggestions for career improvement."

[0347] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0348] Step 1:

[0349] The server collects employee email and chat data from the company's internal communication platform as input. This data is converted into a format that can be analyzed in real time, preparing it for natural language processing. As output, it generates parseable text data.

[0350] Step 2:

[0351] The server uses the Google Cloud Natural Language API to analyze text data. Specifically, it performs sentiment analysis to detect sentiment scores and stress levels based on individual messages. The output of this process is each employee's stress score.

[0352] Step 3:

[0353] The server checks if the stress score, which is the result of the analysis, exceeds a certain threshold. This threshold is pre-configured, and when the score exceeds it, an alert is sent to the administrator. The alert includes a brief explanation of the employee's stress level.

[0354] Step 4:

[0355] Users input their career consultation requests into the system using their smartphones or computers. The server then uses this input to read the employee's work history and skills data from a database and applies it to a career plan generation algorithm. The output of this algorithm is a proposal for skill development and a career plan.

[0356] Step 5:

[0357] The device presents the generated career plan to the user through the user interface. The user can refer to this plan and obtain a concrete action plan for self-improvement. At this point, the user can also provide the generating AI model with the prompt "Please give me suggestions for improving my skills" to obtain further advice.

[0358] Step 6:

[0359] The terminal collects user feedback through an anonymous feedback input function and sends it to the server. The server aggregates and analyzes the received feedback and generates a report for improving the workplace environment. This report is provided to administrators, contributing to the improvement process.

[0360] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0361] This invention provides a system that combines an emotion engine to more accurately determine employees' emotions and stress levels. This system is designed to effectively prevent employee turnover and improve employee engagement.

[0362] The server not only collects and analyzes communication information, but also utilizes an emotion engine to recognize emotions from text. This emotion engine uses natural language processing techniques and machine learning algorithms to identify emotions in text data and evaluate their degree. The server integrates this emotion data with previous analysis results to determine more detailed emotions and stress levels. These detailed results are used to more accurately understand employees' health and mental burden.

[0363] Furthermore, the server generates personalized notifications and suggestions based on this emotion recognition. For example, if an employee has negative emotions indicating a high stress level, the server creates suggestions that provide resources and support to help alleviate that stress. The terminal then presents these suggestions to the employee, making them readily available.

[0364] As a concrete example, consider a case where a user experiences anxiety about communication in their daily work. The server collects the user's chat records and analyzes them using an emotion engine. From this analysis, it determines whether the user is experiencing anxiety or stress. The server then suggests mental health support resources to the user and guides them to use these resources via their device. This allows for early intervention before the problem escalates.

[0365] The server also aggregates anonymous feedback data and uses a sentiment engine to analyze the sentiment of the posts. Based on this analysis, it categorizes the feedback, understands the overall sentiment trends of the company, and reports areas for improvement to administrators.

[0366] To implement this invention, it is necessary to integrate the emotion engine with existing employee management systems and build a framework for follow-up based on individual emotion data. This will enable companies to rapidly and accurately support the mental health of their employees.

[0367] The following describes the processing flow.

[0368] Step 1:

[0369] The server collects employee email and chat communication information in real time. APIs and data pipelines are used for collection, creating a system that efficiently gathers data from various platforms.

[0370] Step 2:

[0371] The server supplies the collected communication information to the emotion engine. The emotion engine uses natural language processing (NLP) to analyze the text data and identify each employee's emotional tone and subjective emotional state. Specifically, it evaluates keywords and context within the text to generate an emotion score.

[0372] Step 3:

[0373] The server integrates emotional scores with employee profile data to determine detailed emotional states and stress levels. This allows for an assessment of how much attention is needed based on the stress score.

[0374] Step 4:

[0375] The server automatically generates personalized notifications and suggestions based on the determined emotional state and stress level. For example, if the user is experiencing high stress levels, it will suggest resources and support contacts that can help reduce stress.

[0376] Step 5:

[0377] The device displays generated notifications and suggestions to the user. These notifications are sent to the user's mobile device or PC, designed for immediate review.

[0378] Step 6:

[0379] Users review notifications and suggestions received through their devices and utilize the provided resources and support as needed. This usage data is also reflected in subsequent analyses and stored as learning material for the system.

[0380] Step 7:

[0381] Users submit their opinions about the work environment through an anonymous feedback form. The submitted feedback is used as an opportunity for them to express their dissatisfaction and suggestions for improvement.

[0382] Step 8:

[0383] The server analyzes anonymously collected feedback using an emotion engine. It analyzes the emotional tone of the feedback and assesses the overall emotional trends within the organization. This classifies the feedback as positive, negative, or neutral.

[0384] Step 9:

[0385] Based on the sentiment analysis results, the server generates a report identifying areas for improvement. This report includes specific improvement suggestions based on the feedback, which can be used to support decision-making across the organization.

[0386] Step 10:

[0387] The terminals facilitate quick action by displaying generated reports on a dashboard accessible to administrators and management. This visualization aims to continuously improve the overall organizational environment.

[0388] (Example 2)

[0389] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0390] There is a growing need to accurately monitor employees' emotions and stress levels and provide appropriate support early on. However, traditional systems struggle to grasp the emotional state of individual employees in real time and to provide rapid, individualized follow-up. Furthermore, they lack sufficient functionality to effectively utilize employee feedback to improve the organization as a whole.

[0391] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0392] In this invention, the server includes means for collecting and preprocessing employee information, means for identifying and evaluating emotions using natural language processing techniques and machine learning algorithms, and means for generating personalized suggestions based on emotions and stress levels. This makes it possible to understand employees' emotions and stress levels in more detail and quickly, and to provide appropriate support.

[0393] "Information" refers to all data collected from employee emails, chat history, internal social media posts, and other sources.

[0394] "Preprocessing" refers to the process of cleaning and tokenizing data in order to convert collected information into an analyzable format.

[0395] "Natural language processing technology" refers to the technology used by computers to understand human language and interpret emotions and intentions.

[0396] A "machine learning algorithm" refers to a method that automatically learns rules and knowledge from data to perform classification and prediction.

[0397] "Sentiment identification and evaluation" refers to the process of extracting emotions from text and analyzing the type and intensity of those emotions.

[0398] "Proposal generation" refers to creating specific action plans and resources to provide to employees based on the analysis results.

[0399] This invention provides a system for accurately identifying and responding quickly to employee emotions and stress levels. This enables companies to improve employee well-being and support efficient business operations. The system is implemented with a configuration including servers, terminals, and users.

[0400] The server collects various employee information and is equipped with an emotion engine that uses natural language processing technology and machine learning algorithms. The server first collects information, cleans up unnecessary data, and performs preprocessing by tokenizing it. Then, it identifies emotions from the text using natural language processing technology and evaluates the degree of those emotions using machine learning algorithms. This process makes it possible to specifically understand which employees are experiencing stress.

[0401] The terminal receives notifications from the server and provides personalized suggestions to individual employees. For example, if a particular employee shows signs of stress, the terminal will present them with resources and support information to alleviate that stress. This information is provided in the form of links or other means for instant access.

[0402] Users can use the system while maintaining their privacy and can also provide feedback anonymously. This allows for more feedback to be gathered, which helps to understand the sentiment trends across the organization.

[0403] As a concrete example, consider the case of a user who experiences anxiety in their daily work. The server uses a generative AI model to execute a prompt message, "Analyze the emotion of this text," and analyzes the user's chat history. If the emotion engine identifies anxiety, the server generates a notification that includes relaxation techniques and counseling services. The terminal presents this to the user, and continuous monitoring is performed to determine if support is needed.

[0404] By implementing this system, companies can provide prompt and appropriate support to their employees, significantly contributing to the improvement of the workplace environment.

[0405] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0406] Step 1:

[0407] The server collects information such as employee emails, chat history, and internal social media posts. The input consists of unprocessed data from each information source. The server uses APIs to collect this data and performs real-time data ingestion. The output is a raw dataset awaiting preprocessing.

[0408] Step 2:

[0409] The server preprocesses the collected raw data. The input is the raw data collected in Step 1. In this step, data cleaning is performed to remove meaningless strings and special characters. Furthermore, the data is tokenized and converted into a format that is easy to analyze using natural language processing. The output is a clean, tokenized dataset.

[0410] Step 3:

[0411] The server identifies and evaluates emotions using natural language processing techniques and machine learning algorithms. The input is tokenized data processed in step 2. The emotion engine utilizes a generative AI model and executes the prompt "Analyze the emotion of this text" to detect the emotional state of each message. The output is a dataset with emotion labels.

[0412] Step 4:

[0413] The server calculates each employee's stress level based on the results of the sentiment analysis. The input is the sentiment-labeled data obtained in step 3. The stress level is quantified by comparing it to a pre-set baseline value. The output is a dataset containing each employee's stress level.

[0414] Step 5:

[0415] The server generates personalized suggestions for employees based on their emotions and stress levels. The input is the stress level data obtained in step 4. Using the generation AI model, it creates a specific action plan based on the prompt message, "Create suggestions for employees showing signs of high stress." The output is a dataset of personalized suggestions as notification content.

[0416] Step 6:

[0417] The terminal receives the suggestion notification sent from the server and presents it to the employee. The input is the individual suggestion data generated in step 5. Specifically, the notification is displayed on the terminal and includes links and action buttons to allow the employee to easily access resources. The output is the notification display information as provided to the employee.

[0418] Step 7:

[0419] The server collects and analyzes anonymous feedback from employees. Input data is gathered through feedback forms and surveys. An emotion engine is used to classify the feedback content and analyze the organization's emotional trends. The output is an organizational emotional analysis report.

[0420] (Application Example 2)

[0421] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0422] The current lack of detailed assessments of employees' emotions and stress levels presents a challenge in implementing appropriate measures to prevent turnover and improve engagement. Furthermore, the absence of a system for emotionally evaluating employee feedback and understanding the overall emotional trends within the organization makes it difficult to implement swift and effective corrective measures.

[0423] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0424] In this invention, the server includes means for collecting and analyzing employee communication information, means for determining emotions and stress levels based on the analysis and proposing stress reduction measures as necessary, means for notifying employees and managers, and means for anonymously collecting opinions and evaluating emotions. This enables detailed information about employees' mental states and early intervention for appropriate improvements.

[0425] "Communication information" refers to text data such as emails and chat messages exchanged by employees in the course of their work.

[0426] An "emotion engine" is a system that uses natural language processing technology and machine learning algorithms to identify emotions from text data and evaluate their intensity.

[0427] "Stress level" refers to the degree of mental burden on an employee, as determined by an emotional engine.

[0428] "Methods for collecting opinions anonymously" refer to ways in which employees can provide their opinions without them being known to third parties.

[0429] "Follow-up" refers to activities that provide ongoing support and suggestions to employees based on emotional data.

[0430] "Emotional trends" refer to the overall patterns and tendencies of individual employees' emotions within an organization.

[0431] An "improvement proposal" is a plan that outlines specific measures to address business processes and organizational sentiment based on the analysis results.

[0432] The system that realizes this invention implements a program that collects and analyzes employee communication information. The server collects text data from messaging apps and email systems that employees use on a daily basis and analyzes it using natural language processing techniques and machine learning algorithms. For the analysis, generative AI models suitable for sentiment analysis, such as Google's BERT model or OpenAI's GPT-3, are used.

[0433] The emotion engine identifies emotions from text data and determines stress levels. Based on this information, the server suggests stress relief measures and mental health support resources, and sends notifications to administrators and the employee via their devices. The notifications include links to specific resources and methods for mental health care.

[0434] Furthermore, anonymous feedback is collected from employees, and emotional evaluations are performed using an emotion engine to understand the emotional trends of the entire organization. The server aggregates this data, reports the company's overall emotional trends to managers, and proposes necessary business improvements and support systems.

[0435] As a concrete example, when a user experiences communication difficulties during delivery work, the server analyzes the message content and sends a follow-up notification to the user guiding them to a counseling service to reduce stress. Links to the necessary resources are provided in a format that can be immediately accessed on a smartphone. This process supports employees' mental health early on and improves job satisfaction.

[0436] Examples of prompt statements are as follows:

[0437] "Explain how to create a program that assesses employees' emotions and stress levels and suggests appropriate support resources."

[0438] "Please provide specific steps for analyzing an organization's emotional trends based on emotional data and proposing improvement plans."

[0439] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0440] Step 1:

[0441] The server collects text data from messaging apps and email systems used by employees. In this step, the collected text data is sent to the server as input, preparing foundational data for a comprehensive understanding of employee intent and context. The output is a set of verified text data.

[0442] Step 2:

[0443] The server uses an emotion engine to analyze the collected text data and identify the emotion (positive, negative, or neutral) of each message. The input is the text data obtained in step 1, and natural language processing techniques and machine learning algorithms (e.g., BERT, GPT-3) are used. The output is the emotion determination result for each message.

[0444] Step 3:

[0445] The server quantifies employees' stress levels based on the emotion analysis results. To calculate the stress score, it takes the output of the emotion engine as input and applies an algorithm that quantifies the degree of stress. The output is each employee's stress score, and appropriate resource suggestions are made based on this.

[0446] Step 4:

[0447] The user receives stress level notifications sent from the server on their device. Inputs include a stress score and corresponding suggestions, while output is a notification message that the user can view. The system then allows the user to access the suggested mental health support resources.

[0448] Step 5:

[0449] The server receives the feedback provided by employees from the anonymous opinion collection form and analyzes it with an emotion engine. The input is the text data of the anonymous feedback, and emotion evaluation and opinion classification are performed. The output is the emotion evaluation result and the categorized feedback.

[0450] Step 6:

[0451] Based on the aggregated feedback data and the emotion analysis results, the server creates a report for reporting the overall emotion trend of the organization to the administrator. The input is the output of Step 5, and the output is a report for the administrator including the visualized data. This enables the formulation of business improvement and support systems as needed.

[0452] 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 the voice indicating the 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.

[0453] The data generation model 58 is a so-called generative AI (Artificial Intelligence). As an example of the data generation model 58, there is ChatGPT (Internet search <URL: https: / / openai.com / blog / chatgpt>), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0454] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0455] [Third Embodiment]

[0456] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0457] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0458] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0459] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0460] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0461] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0462] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0463] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0464] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0465] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0466] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0467] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0468] The system according to the present invention provides a comprehensive solution for preventing employee turnover and improving employee engagement within a company.

[0469] First, the server collects employee communication information, such as emails and chat messages, in real time. Based on this information, the server uses natural language processing technology to analyze the data and evaluate the employee's emotions and stress level. If the resulting stress score exceeds a certain threshold, the server notifies the administrator with an alert. Upon receiving this notification, the administrator can quickly take the necessary actions.

[0470] Next, users can input their career-related questions into the system. The server then conducts a detailed analysis of the employee's work history and skills data. Based on this, it generates skill development and career plans for the employee and provides appropriate advice to the user via the terminal.

[0471] Furthermore, to propose improvements to the work environment, the server collects and analyzes communication information and business data within the group. Based on this information, it identifies bottlenecks and specific problems in business processes and creates appropriate improvement plans. The terminals have the functionality to notify administrators of these proposals and collect feedback.

[0472] Furthermore, users can anonymously provide opinions and feedback to the system. The server collects these opinions anonymously and periodically generates summarized reports. Terminals can then present these reports to administrators and management to help further improve the work environment.

[0473] As a concrete example, suppose an employee is experiencing stress. The server analyzes the frequency of negative keywords in the employee's emails and determines a high stress score. Based on this, the server automatically notifies the administrator. When a user seeks career advice through the system, the server analyzes the history and suggests specific methods for skill development and online learning resources. The terminal then immediately presents the results to the user, encouraging their self-improvement.

[0474] To implement the present invention, it is necessary to apply the above system architecture and set up data collection and analysis algorithms that are appropriate for the corporate environment. This makes it possible to understand the feelings of employees and provide appropriate care and support.

[0475] The following describes the processing flow.

[0476] Step 1:

[0477] The server collects employee communication information, such as emails and chat messages, in real time. To collect this information, it connects to various communication platforms and retrieves data via the necessary APIs.

[0478] Step 2:

[0479] The server analyzes the collected communication information using natural language processing technology. This analysis identifies keywords and sentence structures that indicate emotion, tone, and stress within the text data, and applies an algorithm to evaluate each employee's emotional state and stress level.

[0480] Step 3:

[0481] The server calculates a stress score based on the analysis results. If the calculated stress score exceeds a pre-set threshold, it determines that the employee is experiencing excessive stress.

[0482] Step 4:

[0483] The server automatically sends notifications to administrators regarding employees with high stress levels. These notifications include the employee's stress score and a summary of the suspected causes.

[0484] Step 5:

[0485] Users log in to the career counseling interface and enter their questions and requests. The career counseling content should include specific details about future goals, desired skill development, etc.

[0486] Step 6:

[0487] The server retrieves the user's work history and current skills data from the database and analyzes it. The analysis considers past achievements, skill growth rates, industry trends, and other factors to develop an optimal career plan.

[0488] Step 7:

[0489] The server generates a career plan and a concrete action plan for skill development based on the user's plan. This includes recommended educational courses, training programs, and next steps to take.

[0490] Step 8:

[0491] The device displays the generated career plan and action plan on the user's screen, prompting them to review and make selections, thereby supporting the user in proactively improving their skills.

[0492] Step 9:

[0493] Users submit anonymous feedback about their workplace through a dedicated form, writing down their opinions and suggestions for improvement. The feedback provided covers topics such as the work environment, management policies, and the quality of communication.

[0494] Step 10:

[0495] The server automatically aggregates and analyzes the collected anonymous feedback. Based on the analysis results, it creates a report that includes improvement suggestions while maintaining anonymity.

[0496] Step 11:

[0497] The terminal presents the generated reports to administrators and management, proposing specific actions for improving the workplace environment. This information is displayed in the form of a dashboard or periodic reports.

[0498] (Example 1)

[0499] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0500] When employee stress and engagement decline significantly within a company, it often negatively impacts organizational performance and employee turnover. However, directly observing employees' accurate emotional states and job satisfaction is difficult, and insufficient timely care and support remain challenges. Furthermore, a lack of support for individual employee skill development and career development also contributes to the difficulty in improving the workplace environment.

[0501] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0502] In this invention, the server includes means for collecting and statistically analyzing information, means for inferring emotions or psychological states based on the analysis, and means for providing information to administrators based on the inference results. This makes it possible to grasp the emotional state of employees in real time and provide intervention and support at the appropriate time. Furthermore, by providing means for anonymous opinion collection and analysis of work history and skills information, it becomes possible to create career plans tailored to individual employees and promote improvements in the workplace environment throughout the organization.

[0503] "Information" refers to data transmitted by organizations and individuals, encompassing all communications related to emotions and business operations.

[0504] "Statistical analysis" is the process of analyzing collected data using statistical methods to extract meaningful information.

[0505] "Emotion" refers to an element that indicates an individual's psychological state, and is a numerical evaluation of positive or negative mental processes.

[0506] "Psychological state" refers to an individual's overall mental condition, including their emotions, mood, and level of stress.

[0507] "Inference" is the process of predicting a state that has not yet been clearly observed, based on collected data.

[0508] A "manager" is someone within an organization who is responsible for supervising the work of other members and helping them achieve their best performance.

[0509] "Providing information" means presenting insights and warnings obtained from analysis in an appropriate manner, and giving the target audience the material they need to make decisions.

[0510] "Opinion gathering" refers to obtaining diverse feedback through a process in which users can anonymously submit their thoughts and opinions.

[0511] "Work history" refers to a record of the duties and responsibilities an employee has held in the past, and is information that indicates their professional experience.

[0512] "Skills information" refers to data on the knowledge and abilities possessed by individual employees and is used to evaluate their skill levels and expertise.

[0513] A "career plan" is a proposal or blueprint that outlines the career goals and career path that an employee wishes to achieve in the future.

[0514] The system for realizing this invention is configured as follows: The server is primarily responsible for automatically collecting information through communication methods (email, chat, etc.) used by employees within the company. In this process, an API is used to efficiently acquire communication information. Specifically, it is common to use the email protocol for email systems and the messaging API for chat systems.

[0515] The server uses natural language processing techniques to perform sentiment analysis on the collected information. Libraries such as Python's NLTK and spaCy can be used to extract key phrases and quantify employees' emotions and stress levels.

[0516] Users can input questions and concerns about their careers through the system's interface. The entered data is sent to the server, which performs a detailed analysis based on past work experience and skills information. Analysis tools such as Pandas and Scikit-learn can be used for data processing. Based on the results of this analysis, the system generates skill improvement suggestions and career plans for the user.

[0517] The generated career plan and advice are displayed to the user via their device. The device interface is designed to be intuitive and easy for users to understand, and is provided as a web application. This allows users to quickly access recommended actions and learning resources.

[0518] Furthermore, the server analyzes communication information and business data within the group to identify potential problems occurring within business processes. This analysis utilizes data streaming using Apache Kafka and Hadoop for big data analysis. For identified areas for improvement, appropriate improvement suggestions are formulated and provided to the administrator. This information is notified to the administrator via the terminal, and feedback is also collected.

[0519] Furthermore, users can submit feedback anonymously to the system, and the server compiles this feedback to create a summary report. This report is presented to administrators and management via terminals and used to improve the work environment.

[0520] As a concrete example, by inputting a prompt such as "What workplace improvements would be effective in reducing employee stress levels?" into the AI ​​model, the AI ​​can generate improvement measures and present them to managers as actionable suggestions. Through this entire process, companies can understand their employees' feelings and respond quickly and appropriately, thereby revitalizing the workplace and improving employee satisfaction.

[0521] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0522] Step 1:

[0523] The server collects communication information from the company's email and chat systems. Input includes each employee's email data and chat logs. This data is retrieved in real time using an API, organized, and stored in a database. Specifically, it calls the communication platform's API and receives the data in JSON format. Then, it parses the JSON data to extract the necessary information and prepares it for analysis.

[0524] Step 2:

[0525] The server applies natural language processing to the collected communication information to perform sentiment analysis. The input is the message text obtained in step 1. The server uses Python's NLTK and spaCy libraries to tokenize the text data and calculate sentiment scores. The output of this process is the sentiment score and stress level associated with each message, which is used to evaluate the psychological state of employees.

[0526] Step 3:

[0527] The server notifies the administrator of the results of the sentiment analysis. The inputs are the sentiment score and stress level generated in step 2. If these exceed a certain threshold, the server sends an alert to the administrator using Twilio or the SMTP protocol. Specifically, it generates the body of the alert email and sends the notification to the specified recipient address.

[0528] Step 4:

[0529] Users input career consultations through the system interface. This input includes questions and consultation details from individual employees. This information is entered into a web form or chatbot and sent to the server. Specific operations include validating the input data on the user interface and sending that data to the server.

[0530] Step 5:

[0531] The server analyzes employee work history and skill data based on career consultations from users. The input consists of employee work history data and the consultation content from step 4. This data is analyzed using Pandas and Scikit-learn to generate skill development methods and career plans. The output of this process is a career plan tailored to each employee, supporting users in their independent growth.

[0532] Step 6:

[0533] The terminal presents the user with the career plan received from the server. The input is the career plan generated in step 5. This is displayed on the user interface and summarized in a way that the user can easily understand. Specifically, the key points of the career plan are displayed on the web dashboard, and links to related resources are provided.

[0534] Step 7:

[0535] The server analyzes communication information and business data within a group to generate suggestions for improving business processes. Input includes communication information and business performance data from the entire organization. This data is analyzed using big data technologies such as Hadoop to identify bottlenecks. The improvement suggestions based on this analysis are crucial for streamlining business workflows. The output consists of specific improvement suggestions, which are provided to administrators.

[0536] Step 8:

[0537] The terminal notifies the administrator of improvement suggestions from the server and collects feedback. The input is the improvement suggestion generated in step 7. This is notified to the administrator's console and provides a function to record feedback on the improvement suggestion. Specifically, the system communicates business improvement suggestions to the administrator through the notification system and collects opinions through a feedback form.

[0538] Step 9:

[0539] Users provide feedback to the system anonymously. The input consists of anonymous feedback and suggestions from employees. Users fill out a pre-prepared form and submit it to the server. This process includes anonymization techniques to prevent the identification of individuals.

[0540] Step 10:

[0541] The server aggregates anonymously collected opinions and compiles them into regular reports. The input is the anonymous feedback obtained in step 9. This is stored in a database and aggregated at regular intervals to generate a summary report. This report is provided to managers and management to help with the continuous improvement of the work environment.

[0542] (Application Example 1)

[0543] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0544] Within a company, it is difficult to grasp employee stress and emotions in real time and take appropriate action quickly based on that information. Furthermore, providing employees with concrete career advancement opportunities and mechanisms to encourage self-growth are also crucial challenges. In addition, there is a need to collect feedback while maintaining anonymity, identify bottlenecks in operations, and implement countermeasures, all with the aim of continuously improving the workplace environment. The need for a system that can comprehensively manage employee mental health and career programs is increasing.

[0545] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0546] In this invention, the server includes means for collecting and analyzing employee communication information, means for determining the employee's emotions and stress level, and means for notifying the administrator based on the determination results. This enables appropriate monitoring of employees' mental health status within the company and allows for quick and effective responses. Furthermore, it supports employee self-growth by analyzing work history and skill data and generating and presenting career plans. At the same time, it contributes to improving the work environment by collecting anonymous feedback, identifying areas for improvement in the workplace, and notifying administrators of optimal improvement suggestions.

[0547] "Communication information" refers to data that includes the content of emails, chats, and other communications used by employees for work purposes.

[0548] "Emotional and stress levels" are indicators that show the psychological state of employees and are used to evaluate the mental health status in that workplace environment.

[0549] A "manager" refers to a person within a company who is responsible for managing employees' duties and mental health, and taking appropriate action as needed.

[0550] "Anonymity" refers to a state in which care is taken to ensure that the individual providing the information is not identified, thereby providing an environment where people can express their opinions with peace of mind.

[0551] "Work history" refers to information that includes records of the work performed, positions held, and achievements of an employee to date.

[0552] "Skill data" refers to data that includes information about the knowledge, skills, and abilities that employees possess.

[0553] A "career plan" outlines the job goals and necessary skill development plans that employees should achieve in the future.

[0554] A "bottleneck" refers to an obstacle or point in a business process that reduces efficiency and is an area that needs improvement.

[0555] To realize this invention, a server, a terminal, and a user must work together to form a system. The server collects communication information from employees within the company in real time and analyzes the data using natural language processing technology to determine emotions and stress levels. Google Cloud Natural Language API is suitable as the software to use. If the determined stress score exceeds a certain threshold, the server immediately notifies the administrator.

[0556] Users access the system using their smartphones or computers and input their career-related questions. The server generates a career plan based on the employee's work history and skills data, and presents advice to the user via their device. PostgreSQL is used as the database, and Node.js and Express are used for the backend.

[0557] Anonymous feedback is collected using an app built with React Native, and the opinions are aggregated and compiled into a report by a server. This report is presented to administrators and management via the user's device, contributing to improvements in the work environment.

[0558] For example, if an employee sends an email containing keywords indicating work-related stress, the server analyzes the content and calculates a high stress score. Based on these results, it automatically suggests online resources for leadership training and stress management to the administrator. Furthermore, users can receive specific advice from the generating AI model by entering prompts such as, "Please tell me my current stress level and suggestions for career improvement."

[0559] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0560] Step 1:

[0561] The server collects employee email and chat data from the company's internal communication platform as input. This data is converted into a format that can be analyzed in real time, preparing it for natural language processing. As output, it generates parseable text data.

[0562] Step 2:

[0563] The server uses the Google Cloud Natural Language API to analyze text data. Specifically, it performs sentiment analysis to detect sentiment scores and stress levels based on individual messages. The output of this process is each employee's stress score.

[0564] Step 3:

[0565] The server checks if the stress score, which is the result of the analysis, exceeds a certain threshold. This threshold is pre-configured, and when the score exceeds it, an alert is sent to the administrator. The alert includes a brief explanation of the employee's stress level.

[0566] Step 4:

[0567] Users input their career consultation requests into the system using their smartphones or computers. The server then uses this input to read the employee's work history and skills data from a database and applies it to a career plan generation algorithm. The output of this algorithm is a proposal for skill development and a career plan.

[0568] Step 5:

[0569] The device presents the generated career plan to the user through the user interface. The user can refer to this plan and obtain a concrete action plan for self-improvement. At this point, the user can also provide the generating AI model with the prompt "Please give me suggestions for improving my skills" to obtain further advice.

[0570] Step 6:

[0571] The terminal collects user feedback through an anonymous feedback input function and sends it to the server. The server aggregates and analyzes the received feedback and generates a report for improving the workplace environment. This report is provided to administrators, contributing to the improvement process.

[0572] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0573] This invention provides a system that combines an emotion engine to more accurately determine employees' emotions and stress levels. This system is designed to effectively prevent employee turnover and improve employee engagement.

[0574] The server not only collects and analyzes communication information, but also utilizes an emotion engine to recognize emotions from text. This emotion engine uses natural language processing techniques and machine learning algorithms to identify emotions in text data and evaluate their degree. The server integrates this emotion data with previous analysis results to determine more detailed emotions and stress levels. These detailed results are used to more accurately understand employees' health and mental burden.

[0575] Furthermore, the server generates personalized notifications and suggestions based on this emotion recognition. For example, if an employee has negative emotions indicating a high stress level, the server creates suggestions that provide resources and support to help alleviate that stress. The terminal then presents these suggestions to the employee, making them readily available.

[0576] As a concrete example, consider a case where a user experiences anxiety about communication in their daily work. The server collects the user's chat records and analyzes them using an emotion engine. From this analysis, it determines whether the user is experiencing anxiety or stress. The server then suggests mental health support resources to the user and guides them to use these resources via their device. This allows for early intervention before the problem escalates.

[0577] The server also aggregates anonymous feedback data and uses a sentiment engine to analyze the sentiment of the posts. Based on this analysis, it categorizes the feedback, understands the overall sentiment trends of the company, and reports areas for improvement to administrators.

[0578] To implement this invention, it is necessary to integrate the emotion engine with existing employee management systems and build a framework for follow-up based on individual emotion data. This will enable companies to rapidly and accurately support the mental health of their employees.

[0579] The following describes the processing flow.

[0580] Step 1:

[0581] The server collects employee email and chat communication information in real time. APIs and data pipelines are used for collection, creating a system that efficiently gathers data from various platforms.

[0582] Step 2:

[0583] The server supplies the collected communication information to the emotion engine. The emotion engine uses natural language processing (NLP) to analyze the text data and identify each employee's emotional tone and subjective emotional state. Specifically, it evaluates keywords and context within the text to generate an emotion score.

[0584] Step 3:

[0585] The server integrates emotional scores with employee profile data to determine detailed emotional states and stress levels. This allows for an assessment of how much attention is needed based on the stress score.

[0586] Step 4:

[0587] The server automatically generates personalized notifications and suggestions based on the determined emotional state and stress level. For example, if the user is experiencing high stress levels, it will suggest resources and support contacts that can help reduce stress.

[0588] Step 5:

[0589] The device displays generated notifications and suggestions to the user. These notifications are sent to the user's mobile device or PC, designed for immediate review.

[0590] Step 6:

[0591] Users review notifications and suggestions received through their devices and utilize the provided resources and support as needed. This usage data is also reflected in subsequent analyses and stored as learning material for the system.

[0592] Step 7:

[0593] Users submit their opinions about the work environment through an anonymous feedback form. The submitted feedback is used as an opportunity for them to express their dissatisfaction and suggestions for improvement.

[0594] Step 8:

[0595] The server analyzes anonymously collected feedback using an emotion engine. It analyzes the emotional tone of the feedback and assesses the overall emotional trends within the organization. This classifies the feedback as positive, negative, or neutral.

[0596] Step 9:

[0597] Based on the sentiment analysis results, the server generates a report identifying areas for improvement. This report includes specific improvement suggestions based on the feedback, which can be used to support decision-making across the organization.

[0598] Step 10:

[0599] The terminals facilitate quick action by displaying generated reports on a dashboard accessible to administrators and management. This visualization aims to continuously improve the overall organizational environment.

[0600] (Example 2)

[0601] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0602] There is a growing need to accurately monitor employees' emotions and stress levels and provide appropriate support early on. However, traditional systems struggle to grasp the emotional state of individual employees in real time and to provide rapid, individualized follow-up. Furthermore, they lack sufficient functionality to effectively utilize employee feedback to improve the organization as a whole.

[0603] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0604] In this invention, the server includes means for collecting and preprocessing employee information, means for identifying and evaluating emotions using natural language processing techniques and machine learning algorithms, and means for generating personalized suggestions based on emotions and stress levels. This makes it possible to understand employees' emotions and stress levels in more detail and quickly, and to provide appropriate support.

[0605] "Information" refers to all data collected from employee emails, chat history, internal social media posts, and other sources.

[0606] "Preprocessing" refers to the process of cleaning and tokenizing data in order to convert collected information into an analyzable format.

[0607] "Natural language processing technology" refers to the technology used by computers to understand human language and interpret emotions and intentions.

[0608] A "machine learning algorithm" refers to a method that automatically learns rules and knowledge from data to perform classification and prediction.

[0609] "Sentiment identification and evaluation" refers to the process of extracting emotions from text and analyzing the type and intensity of those emotions.

[0610] "Proposal generation" refers to creating specific action plans and resources to provide to employees based on the analysis results.

[0611] This invention provides a system for accurately identifying and responding quickly to employee emotions and stress levels. This enables companies to improve employee well-being and support efficient business operations. The system is implemented with a configuration including servers, terminals, and users.

[0612] The server collects various employee information and is equipped with an emotion engine that uses natural language processing technology and machine learning algorithms. The server first collects information, cleans up unnecessary data, and performs preprocessing by tokenizing it. Then, it identifies emotions from the text using natural language processing technology and evaluates the degree of those emotions using machine learning algorithms. This process makes it possible to specifically understand which employees are experiencing stress.

[0613] The terminal receives notifications from the server and provides personalized suggestions to individual employees. For example, if a particular employee shows signs of stress, the terminal will present them with resources and support information to alleviate that stress. This information is provided in the form of links or other means for instant access.

[0614] Users can use the system while maintaining their privacy and can also provide feedback anonymously. This allows for more feedback to be gathered, which helps to understand the sentiment trends across the organization.

[0615] As a concrete example, consider the case of a user who experiences anxiety in their daily work. The server uses a generative AI model to execute a prompt message, "Analyze the emotion of this text," and analyzes the user's chat history. If the emotion engine identifies anxiety, the server generates a notification that includes relaxation techniques and counseling services. The terminal presents this to the user, and continuous monitoring is performed to determine if support is needed.

[0616] By implementing this system, companies can provide prompt and appropriate support to their employees, significantly contributing to the improvement of the workplace environment.

[0617] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0618] Step 1:

[0619] The server collects information such as employee emails, chat history, and internal social media posts. The input consists of unprocessed data from each information source. The server uses APIs to collect this data and performs real-time data ingestion. The output is a raw dataset awaiting preprocessing.

[0620] Step 2:

[0621] The server preprocesses the collected raw data. The input is the raw data collected in Step 1. In this step, data cleaning is performed to remove meaningless strings and special characters. Furthermore, the data is tokenized and converted into a format that is easy to analyze using natural language processing. The output is a clean, tokenized dataset.

[0622] Step 3:

[0623] The server identifies and evaluates emotions using natural language processing techniques and machine learning algorithms. The input is tokenized data processed in step 2. The emotion engine utilizes a generative AI model and executes the prompt "Analyze the emotion of this text" to detect the emotional state of each message. The output is a dataset with emotion labels.

[0624] Step 4:

[0625] The server calculates each employee's stress level based on the results of the sentiment analysis. The input is the sentiment-labeled data obtained in step 3. The stress level is quantified by comparing it to a pre-set baseline value. The output is a dataset containing each employee's stress level.

[0626] Step 5:

[0627] The server generates personalized suggestions for employees based on their emotions and stress levels. The input is the stress level data obtained in step 4. Using the generation AI model, it creates a specific action plan based on the prompt message, "Create suggestions for employees showing signs of high stress." The output is a dataset of personalized suggestions as notification content.

[0628] Step 6:

[0629] The terminal receives the suggestion notification sent from the server and presents it to the employee. The input is the individual suggestion data generated in step 5. Specifically, the notification is displayed on the terminal and includes links and action buttons to allow the employee to easily access resources. The output is the notification display information as provided to the employee.

[0630] Step 7:

[0631] The server collects and analyzes anonymous feedback from employees. Input data is gathered through feedback forms and surveys. An emotion engine is used to classify the feedback content and analyze the organization's emotional trends. The output is an organizational emotional analysis report.

[0632] (Application Example 2)

[0633] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0634] The current lack of detailed assessments of employees' emotions and stress levels presents a challenge in implementing appropriate measures to prevent turnover and improve engagement. Furthermore, the absence of a system for emotionally evaluating employee feedback and understanding the overall emotional trends within the organization makes it difficult to implement swift and effective corrective measures.

[0635] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0636] In this invention, the server includes means for collecting and analyzing employee communication information, means for determining emotions and stress levels based on the analysis and proposing stress reduction measures as necessary, means for notifying employees and managers, and means for anonymously collecting opinions and evaluating emotions. This enables detailed information about employees' mental states and early intervention for appropriate improvements.

[0637] "Communication information" refers to text data such as emails and chat messages exchanged by employees in the course of their work.

[0638] An "emotion engine" is a system that uses natural language processing technology and machine learning algorithms to identify emotions from text data and evaluate their intensity.

[0639] "Stress level" refers to the degree of mental burden on an employee, as determined by an emotional engine.

[0640] "Methods for collecting opinions anonymously" refer to ways in which employees can provide their opinions without them being known to third parties.

[0641] "Follow-up" refers to activities that provide ongoing support and suggestions to employees based on emotional data.

[0642] "Emotional trends" refer to the overall patterns and tendencies of individual employees' emotions within an organization.

[0643] An "improvement proposal" is a plan that outlines specific measures to address business processes and organizational sentiment based on the analysis results.

[0644] The system that realizes this invention implements a program that collects and analyzes employee communication information. The server collects text data from messaging apps and email systems that employees use on a daily basis and analyzes it using natural language processing techniques and machine learning algorithms. For the analysis, generative AI models suitable for sentiment analysis, such as Google's BERT model or OpenAI's GPT-3, are used.

[0645] The emotion engine identifies emotions from text data and determines stress levels. Based on this information, the server suggests stress relief measures and mental health support resources, and sends notifications to administrators and the employee via their devices. The notifications include links to specific resources and methods for mental health care.

[0646] Furthermore, anonymous feedback is collected from employees, and emotional evaluations are performed using an emotion engine to understand the emotional trends of the entire organization. The server aggregates this data, reports the company's overall emotional trends to managers, and proposes necessary business improvements and support systems.

[0647] As a concrete example, when a user experiences communication difficulties during delivery work, the server analyzes the message content and sends a follow-up notification to the user guiding them to a counseling service to reduce stress. Links to the necessary resources are provided in a format that can be immediately accessed on a smartphone. This process supports employees' mental health early on and improves job satisfaction.

[0648] Examples of prompt statements are as follows:

[0649] "Explain how to create a program that assesses employees' emotions and stress levels and suggests appropriate support resources."

[0650] "Please provide specific steps for analyzing an organization's emotional trends based on emotional data and proposing improvement plans."

[0651] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0652] Step 1:

[0653] The server collects text data from messaging apps and email systems used by employees. In this step, the collected text data is sent to the server as input, preparing foundational data for a comprehensive understanding of employee intent and context. The output is a set of verified text data.

[0654] Step 2:

[0655] The server uses an emotion engine to analyze the collected text data and identify the emotion (positive, negative, or neutral) of each message. The input is the text data obtained in step 1, and natural language processing techniques and machine learning algorithms (e.g., BERT, GPT-3) are used. The output is the emotion determination result for each message.

[0656] Step 3:

[0657] The server quantifies employees' stress levels based on the emotion analysis results. To calculate the stress score, it takes the output of the emotion engine as input and applies an algorithm that quantifies the degree of stress. The output is each employee's stress score, and appropriate resource suggestions are made based on this.

[0658] Step 4:

[0659] The user receives stress level notifications sent from the server on their device. Inputs include a stress score and corresponding suggestions, while output is a notification message that the user can view. The system then allows the user to access the suggested mental health support resources.

[0660] Step 5:

[0661] The server receives feedback provided by employees from the anonymous opinion collection form and analyzes it using the sentiment engine. The input is the text data of the anonymous feedback, and sentiment evaluation and opinion classification are performed. The output is the sentiment evaluation result and the categorized feedback.

[0662] Step 6:

[0663] Based on the aggregated feedback data and sentiment analysis results, the server creates a report for reporting the overall sentiment trend of the organization to the administrator. The input is the output of Step 5, and the output is a report for the administrator including visualized data. This enables the formulation of business improvement and support systems as needed.

[0664] 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 user input with respect to 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.

[0665] The data generation model 58 is a so-called generative AI (Artificial Intelligence). As an example of the data generation model 58, there is ChatGPT (Internet search <URL: https: / / openai.com / blog / chatgpt>), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0666] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0667] [Fourth Embodiment]

[0668] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0669] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0670] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0671] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0672] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0673] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0674] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0675] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0676] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0677] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0678] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0679] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0680] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0681] The system according to the present invention provides a comprehensive solution for preventing employee turnover and improving employee engagement within a company.

[0682] First, the server collects employee communication information, such as emails and chat messages, in real time. Based on this information, the server uses natural language processing technology to analyze the data and evaluate the employee's emotions and stress level. If the resulting stress score exceeds a certain threshold, the server notifies the administrator with an alert. Upon receiving this notification, the administrator can quickly take the necessary actions.

[0683] Next, users can input their career-related questions into the system. The server then conducts a detailed analysis of the employee's work history and skills data. Based on this, it generates skill development and career plans for the employee and provides appropriate advice to the user via the terminal.

[0684] Furthermore, to propose improvements to the work environment, the server collects and analyzes communication information and business data within the group. Based on this information, it identifies bottlenecks and specific problems in business processes and creates appropriate improvement plans. The terminals have the functionality to notify administrators of these proposals and collect feedback.

[0685] Furthermore, users can anonymously provide opinions and feedback to the system. The server collects these opinions anonymously and periodically generates summarized reports. Terminals can then present these reports to administrators and management to help further improve the work environment.

[0686] As a concrete example, suppose an employee is experiencing stress. The server analyzes the frequency of negative keywords in the employee's emails and determines a high stress score. Based on this, the server automatically notifies the administrator. When a user seeks career advice through the system, the server analyzes the history and suggests specific methods for skill development and online learning resources. The terminal then immediately presents the results to the user, encouraging their self-improvement.

[0687] To implement the present invention, it is necessary to apply the above system architecture and set up data collection and analysis algorithms that are appropriate for the corporate environment. This makes it possible to understand the feelings of employees and provide appropriate care and support.

[0688] The following describes the processing flow.

[0689] Step 1:

[0690] The server collects employee communication information, such as emails and chat messages, in real time. To collect this information, it connects to various communication platforms and retrieves data via the necessary APIs.

[0691] Step 2:

[0692] The server analyzes the collected communication information using natural language processing technology. This analysis identifies keywords and sentence structures that indicate emotion, tone, and stress within the text data, and applies an algorithm to evaluate each employee's emotional state and stress level.

[0693] Step 3:

[0694] The server calculates a stress score based on the analysis results. If the calculated stress score exceeds a pre-set threshold, it determines that the employee is experiencing excessive stress.

[0695] Step 4:

[0696] The server automatically sends notifications to administrators regarding employees with high stress levels. These notifications include the employee's stress score and a summary of the suspected causes.

[0697] Step 5:

[0698] Users log in to the career counseling interface and enter their questions and requests. The career counseling content should include specific details about future goals, desired skill development, etc.

[0699] Step 6:

[0700] The server retrieves the user's work history and current skills data from the database and analyzes it. The analysis considers past achievements, skill growth rates, industry trends, and other factors to develop an optimal career plan.

[0701] Step 7:

[0702] The server generates a career plan and a concrete action plan for skill development based on the user's plan. This includes recommended educational courses, training programs, and next steps to take.

[0703] Step 8:

[0704] The device displays the generated career plan and action plan on the user's screen, prompting them to review and make selections, thereby supporting the user in proactively improving their skills.

[0705] Step 9:

[0706] Users submit anonymous feedback about their workplace through a dedicated form, writing down their opinions and suggestions for improvement. The feedback provided covers topics such as the work environment, management policies, and the quality of communication.

[0707] Step 10:

[0708] The server automatically aggregates and analyzes the collected anonymous feedback. Based on the analysis results, it creates a report that includes improvement suggestions while maintaining anonymity.

[0709] Step 11:

[0710] The terminal presents the generated reports to administrators and management, proposing specific actions for improving the workplace environment. This information is displayed in the form of a dashboard or periodic reports.

[0711] (Example 1)

[0712] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0713] When employee stress and engagement decline significantly within a company, it often negatively impacts organizational performance and employee turnover. However, directly observing employees' accurate emotional states and job satisfaction is difficult, and insufficient timely care and support remain challenges. Furthermore, a lack of support for individual employee skill development and career development also contributes to the difficulty in improving the workplace environment.

[0714] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0715] In this invention, the server includes means for collecting and statistically analyzing information, means for inferring emotions or psychological states based on the analysis, and means for providing information to administrators based on the inference results. This makes it possible to grasp the emotional state of employees in real time and provide intervention and support at the appropriate time. Furthermore, by providing means for anonymous opinion collection and analysis of work history and skills information, it becomes possible to create career plans tailored to individual employees and promote improvements in the workplace environment throughout the organization.

[0716] "Information" refers to data transmitted by organizations and individuals, encompassing all communications related to emotions and business operations.

[0717] "Statistical analysis" is the process of analyzing collected data using statistical methods to extract meaningful information.

[0718] "Emotion" refers to an element that indicates an individual's psychological state, and is a numerical evaluation of positive or negative mental processes.

[0719] "Psychological state" refers to an individual's overall mental condition, including their emotions, mood, and level of stress.

[0720] "Inference" is the process of predicting a state that has not yet been clearly observed, based on collected data.

[0721] A "manager" is someone within an organization who is responsible for supervising the work of other members and helping them achieve their best performance.

[0722] "Providing information" means presenting insights and warnings obtained from analysis in an appropriate manner, and giving the target audience the material they need to make decisions.

[0723] "Opinion gathering" refers to obtaining diverse feedback through a process in which users can anonymously submit their thoughts and opinions.

[0724] "Work history" refers to a record of the duties and responsibilities an employee has held in the past, and is information that indicates their professional experience.

[0725] "Skills information" refers to data on the knowledge and abilities possessed by individual employees and is used to evaluate their skill levels and expertise.

[0726] A "career plan" is a proposal or blueprint that outlines the career goals and career path that an employee wishes to achieve in the future.

[0727] The system for realizing this invention is configured as follows: The server is primarily responsible for automatically collecting information through communication methods (email, chat, etc.) used by employees within the company. In this process, an API is used to efficiently acquire communication information. Specifically, it is common to use the email protocol for email systems and the messaging API for chat systems.

[0728] The server uses natural language processing techniques to perform sentiment analysis on the collected information. Libraries such as Python's NLTK and spaCy can be used to extract key phrases and quantify employees' emotions and stress levels.

[0729] Users can input questions and concerns about their careers through the system's interface. The entered data is sent to the server, which performs a detailed analysis based on past work experience and skills information. Analysis tools such as Pandas and Scikit-learn can be used for data processing. Based on the results of this analysis, the system generates skill improvement suggestions and career plans for the user.

[0730] The generated career plan and advice are displayed to the user via their device. The device interface is designed to be intuitive and easy for users to understand, and is provided as a web application. This allows users to quickly access recommended actions and learning resources.

[0731] Furthermore, the server analyzes communication information and business data within the group to identify potential problems occurring within business processes. This analysis utilizes data streaming using Apache Kafka and Hadoop for big data analysis. For identified areas for improvement, appropriate improvement suggestions are formulated and provided to the administrator. This information is notified to the administrator via the terminal, and feedback is also collected.

[0732] Furthermore, users can submit feedback anonymously to the system, and the server compiles this feedback to create a summary report. This report is presented to administrators and management via terminals and used to improve the work environment.

[0733] As a concrete example, by inputting a prompt such as "What workplace improvements would be effective in reducing employee stress levels?" into the AI ​​model, the AI ​​can generate improvement measures and present them to managers as actionable suggestions. Through this entire process, companies can understand their employees' feelings and respond quickly and appropriately, thereby revitalizing the workplace and improving employee satisfaction.

[0734] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0735] Step 1:

[0736] The server collects communication information from the company's email and chat systems. Input includes each employee's email data and chat logs. This data is retrieved in real time using an API, organized, and stored in a database. Specifically, it calls the communication platform's API and receives the data in JSON format. Then, it parses the JSON data to extract the necessary information and prepares it for analysis.

[0737] Step 2:

[0738] The server applies natural language processing to the collected communication information to perform sentiment analysis. The input is the message text obtained in step 1. The server uses Python's NLTK and spaCy libraries to tokenize the text data and calculate sentiment scores. The output of this process is the sentiment score and stress level associated with each message, which is used to evaluate the psychological state of employees.

[0739] Step 3:

[0740] The server notifies the administrator of the results of the sentiment analysis. The inputs are the sentiment score and stress level generated in step 2. If these exceed a certain threshold, the server sends an alert to the administrator using Twilio or the SMTP protocol. Specifically, it generates the body of the alert email and sends the notification to the specified recipient address.

[0741] Step 4:

[0742] Users input career consultations through the system interface. This input includes questions and consultation details from individual employees. This information is entered into a web form or chatbot and sent to the server. Specific operations include validating the input data on the user interface and sending that data to the server.

[0743] Step 5:

[0744] The server analyzes employee work history and skill data based on career consultations from users. The input consists of employee work history data and the consultation content from step 4. This data is analyzed using Pandas and Scikit-learn to generate skill development methods and career plans. The output of this process is a career plan tailored to each employee, supporting users in their independent growth.

[0745] Step 6:

[0746] The terminal presents the user with the career plan received from the server. The input is the career plan generated in step 5. This is displayed on the user interface and summarized in a way that the user can easily understand. Specifically, the key points of the career plan are displayed on the web dashboard, and links to related resources are provided.

[0747] Step 7:

[0748] The server analyzes communication information and business data within a group to generate suggestions for improving business processes. Input includes communication information and business performance data from the entire organization. This data is analyzed using big data technologies such as Hadoop to identify bottlenecks. The improvement suggestions based on this analysis are crucial for streamlining business workflows. The output consists of specific improvement suggestions, which are provided to administrators.

[0749] Step 8:

[0750] The terminal notifies the administrator of improvement suggestions from the server and collects feedback. The input is the improvement suggestion generated in step 7. This is notified to the administrator's console and provides a function to record feedback on the improvement suggestion. Specifically, the system communicates business improvement suggestions to the administrator through the notification system and collects opinions through a feedback form.

[0751] Step 9:

[0752] Users provide feedback to the system anonymously. The input consists of anonymous feedback and suggestions from employees. Users fill out a pre-prepared form and submit it to the server. This process includes anonymization techniques to prevent the identification of individuals.

[0753] Step 10:

[0754] The server aggregates anonymously collected opinions and compiles them into regular reports. The input is the anonymous feedback obtained in step 9. This is stored in a database and aggregated at regular intervals to generate a summary report. This report is provided to managers and management to help with the continuous improvement of the work environment.

[0755] (Application Example 1)

[0756] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0757] Within a company, it is difficult to grasp employee stress and emotions in real time and take appropriate action quickly based on that information. Furthermore, providing employees with concrete career advancement opportunities and mechanisms to encourage self-growth are also crucial challenges. In addition, there is a need to collect feedback while maintaining anonymity, identify bottlenecks in operations, and implement countermeasures, all with the aim of continuously improving the workplace environment. The need for a system that can comprehensively manage employee mental health and career programs is increasing.

[0758] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0759] In this invention, the server includes means for collecting and analyzing employee communication information, means for determining the employee's emotions and stress level, and means for notifying the administrator based on the determination results. This enables appropriate monitoring of employees' mental health status within the company and allows for quick and effective responses. Furthermore, it supports employee self-growth by analyzing work history and skill data and generating and presenting career plans. At the same time, it contributes to improving the work environment by collecting anonymous feedback, identifying areas for improvement in the workplace, and notifying administrators of optimal improvement suggestions.

[0760] "Communication information" refers to data that includes the content of emails, chats, and other communications used by employees for work purposes.

[0761] "Emotional and stress levels" are indicators that show the psychological state of employees and are used to evaluate the mental health status in that workplace environment.

[0762] A "manager" refers to a person within a company who is responsible for managing employees' duties and mental health, and taking appropriate action as needed.

[0763] "Anonymity" refers to a state in which care is taken to ensure that the individual providing the information is not identified, thereby providing an environment where people can express their opinions with peace of mind.

[0764] "Work history" refers to information that includes records of the work performed, positions held, and achievements of an employee to date.

[0765] "Skill data" refers to data that includes information about the knowledge, skills, and abilities that employees possess.

[0766] A "career plan" outlines the job goals and necessary skill development plans that employees should achieve in the future.

[0767] A "bottleneck" refers to an obstacle or point in a business process that reduces efficiency and is an area that needs improvement.

[0768] To realize this invention, a server, a terminal, and a user must work together to form a system. The server collects communication information from employees within the company in real time and analyzes the data using natural language processing technology to determine emotions and stress levels. Google Cloud Natural Language API is suitable as the software to use. If the determined stress score exceeds a certain threshold, the server immediately notifies the administrator.

[0769] Users access the system using their smartphones or computers and input their career-related questions. The server generates a career plan based on the employee's work history and skills data, and presents advice to the user via their device. PostgreSQL is used as the database, and Node.js and Express are used for the backend.

[0770] Anonymous feedback is collected using an app built with React Native, and the opinions are aggregated and compiled into a report by a server. This report is presented to administrators and management via the user's device, contributing to improvements in the work environment.

[0771] For example, if an employee sends an email containing keywords indicating work-related stress, the server analyzes the content and calculates a high stress score. Based on these results, it automatically suggests online resources for leadership training and stress management to the administrator. Furthermore, users can receive specific advice from the generating AI model by entering prompts such as, "Please tell me my current stress level and suggestions for career improvement."

[0772] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0773] Step 1:

[0774] The server collects employee email and chat data from the company's internal communication platform as input. This data is converted into a format that can be analyzed in real time, preparing it for natural language processing. As output, it generates parseable text data.

[0775] Step 2:

[0776] The server uses the Google Cloud Natural Language API to analyze text data. Specifically, it performs sentiment analysis to detect sentiment scores and stress levels based on individual messages. The output of this process is each employee's stress score.

[0777] Step 3:

[0778] The server checks if the stress score, which is the result of the analysis, exceeds a certain threshold. This threshold is pre-configured, and when the score exceeds it, an alert is sent to the administrator. The alert includes a brief explanation of the employee's stress level.

[0779] Step 4:

[0780] Users input their career consultation requests into the system using their smartphones or computers. The server then uses this input to read the employee's work history and skills data from a database and applies it to a career plan generation algorithm. The output of this algorithm is a proposal for skill development and a career plan.

[0781] Step 5:

[0782] The device presents the generated career plan to the user through the user interface. The user can refer to this plan and obtain a concrete action plan for self-improvement. At this point, the user can also provide the generating AI model with the prompt "Please give me suggestions for improving my skills" to obtain further advice.

[0783] Step 6:

[0784] The terminal collects user feedback through an anonymous feedback input function and sends it to the server. The server aggregates and analyzes the received feedback and generates a report for improving the workplace environment. This report is provided to administrators, contributing to the improvement process.

[0785] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0786] This invention provides a system that combines an emotion engine to more accurately determine employees' emotions and stress levels. This system is designed to effectively prevent employee turnover and improve employee engagement.

[0787] The server not only collects and analyzes communication information, but also utilizes an emotion engine to recognize emotions from text. This emotion engine uses natural language processing techniques and machine learning algorithms to identify emotions in text data and evaluate their degree. The server integrates this emotion data with previous analysis results to determine more detailed emotions and stress levels. These detailed results are used to more accurately understand employees' health and mental burden.

[0788] Furthermore, the server generates personalized notifications and suggestions based on this emotion recognition. For example, if an employee has negative emotions indicating a high stress level, the server creates suggestions that provide resources and support to help alleviate that stress. The terminal then presents these suggestions to the employee, making them readily available.

[0789] As a concrete example, consider a case where a user experiences anxiety about communication in their daily work. The server collects the user's chat records and analyzes them using an emotion engine. From this analysis, it determines whether the user is experiencing anxiety or stress. The server then suggests mental health support resources to the user and guides them to use these resources via their device. This allows for early intervention before the problem escalates.

[0790] The server also aggregates anonymous feedback data and uses a sentiment engine to analyze the sentiment of the posts. Based on this analysis, it categorizes the feedback, understands the overall sentiment trends of the company, and reports areas for improvement to administrators.

[0791] To implement this invention, it is necessary to integrate the emotion engine with existing employee management systems and build a framework for follow-up based on individual emotion data. This will enable companies to rapidly and accurately support the mental health of their employees.

[0792] The following describes the processing flow.

[0793] Step 1:

[0794] The server collects employee email and chat communication information in real time. APIs and data pipelines are used for collection, creating a system that efficiently gathers data from various platforms.

[0795] Step 2:

[0796] The server supplies the collected communication information to the emotion engine. The emotion engine uses natural language processing (NLP) to analyze the text data and identify each employee's emotional tone and subjective emotional state. Specifically, it evaluates keywords and context within the text to generate an emotion score.

[0797] Step 3:

[0798] The server integrates emotional scores with employee profile data to determine detailed emotional states and stress levels. This allows for an assessment of how much attention is needed based on the stress score.

[0799] Step 4:

[0800] The server automatically generates personalized notifications and suggestions based on the determined emotional state and stress level. For example, if the user is experiencing high stress levels, it will suggest resources and support contacts that can help reduce stress.

[0801] Step 5:

[0802] The device displays generated notifications and suggestions to the user. These notifications are sent to the user's mobile device or PC, designed for immediate review.

[0803] Step 6:

[0804] Users review notifications and suggestions received through their devices and utilize the provided resources and support as needed. This usage data is also reflected in subsequent analyses and stored as learning material for the system.

[0805] Step 7:

[0806] Users submit their opinions about the work environment through an anonymous feedback form. The submitted feedback is used as an opportunity for them to express their dissatisfaction and suggestions for improvement.

[0807] Step 8:

[0808] The server analyzes anonymously collected feedback using an emotion engine. It analyzes the emotional tone of the feedback and assesses the overall emotional trends within the organization. This classifies the feedback as positive, negative, or neutral.

[0809] Step 9:

[0810] Based on the sentiment analysis results, the server generates a report identifying areas for improvement. This report includes specific improvement suggestions based on the feedback, which can be used to support decision-making across the organization.

[0811] Step 10:

[0812] The terminals facilitate quick action by displaying generated reports on a dashboard accessible to administrators and management. This visualization aims to continuously improve the overall organizational environment.

[0813] (Example 2)

[0814] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0815] There is a growing need to accurately monitor employees' emotions and stress levels and provide appropriate support early on. However, traditional systems struggle to grasp the emotional state of individual employees in real time and to provide rapid, individualized follow-up. Furthermore, they lack sufficient functionality to effectively utilize employee feedback to improve the organization as a whole.

[0816] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0817] In this invention, the server includes means for collecting and preprocessing employee information, means for identifying and evaluating emotions using natural language processing techniques and machine learning algorithms, and means for generating personalized suggestions based on emotions and stress levels. This makes it possible to understand employees' emotions and stress levels in more detail and quickly, and to provide appropriate support.

[0818] "Information" refers to all data collected from employee emails, chat history, internal social media posts, and other sources.

[0819] "Preprocessing" refers to the process of cleaning and tokenizing data in order to convert collected information into an analyzable format.

[0820] "Natural language processing technology" refers to the technology used by computers to understand human language and interpret emotions and intentions.

[0821] A "machine learning algorithm" refers to a method that automatically learns rules and knowledge from data to perform classification and prediction.

[0822] "Sentiment identification and evaluation" refers to the process of extracting emotions from text and analyzing the type and intensity of those emotions.

[0823] "Proposal generation" refers to creating specific action plans and resources to provide to employees based on the analysis results.

[0824] This invention provides a system for accurately identifying and responding quickly to employee emotions and stress levels. This enables companies to improve employee well-being and support efficient business operations. The system is implemented with a configuration including servers, terminals, and users.

[0825] The server collects various employee information and is equipped with an emotion engine that uses natural language processing technology and machine learning algorithms. The server first collects information, cleans up unnecessary data, and performs preprocessing by tokenizing it. Then, it identifies emotions from the text using natural language processing technology and evaluates the degree of those emotions using machine learning algorithms. This process makes it possible to specifically understand which employees are experiencing stress.

[0826] The terminal receives notifications from the server and provides personalized suggestions to individual employees. For example, if a particular employee shows signs of stress, the terminal will present them with resources and support information to alleviate that stress. This information is provided in the form of links or other means for instant access.

[0827] Users can use the system while maintaining their privacy and can also provide feedback anonymously. This allows for more feedback to be gathered, which helps to understand the sentiment trends across the organization.

[0828] As a concrete example, consider the case of a user who experiences anxiety in their daily work. The server uses a generative AI model to execute a prompt message, "Analyze the emotion of this text," and analyzes the user's chat history. If the emotion engine identifies anxiety, the server generates a notification that includes relaxation techniques and counseling services. The terminal presents this to the user, and continuous monitoring is performed to determine if support is needed.

[0829] By implementing this system, companies can provide prompt and appropriate support to their employees, significantly contributing to the improvement of the workplace environment.

[0830] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0831] Step 1:

[0832] The server collects information such as employee emails, chat history, and internal social media posts. The input consists of unprocessed data from each information source. The server uses APIs to collect this data and performs real-time data ingestion. The output is a raw dataset awaiting preprocessing.

[0833] Step 2:

[0834] The server preprocesses the collected raw data. The input is the raw data collected in Step 1. In this step, data cleaning is performed to remove meaningless strings and special characters. Furthermore, the data is tokenized and converted into a format that is easy to analyze using natural language processing. The output is a clean, tokenized dataset.

[0835] Step 3:

[0836] The server identifies and evaluates emotions using natural language processing techniques and machine learning algorithms. The input is tokenized data processed in step 2. The emotion engine utilizes a generative AI model and executes the prompt "Analyze the emotion of this text" to detect the emotional state of each message. The output is a dataset with emotion labels.

[0837] Step 4:

[0838] The server calculates each employee's stress level based on the results of the sentiment analysis. The input is the sentiment-labeled data obtained in step 3. The stress level is quantified by comparing it to a pre-set baseline value. The output is a dataset containing each employee's stress level.

[0839] Step 5:

[0840] The server generates personalized suggestions for employees based on their emotions and stress levels. The input is the stress level data obtained in step 4. Using the generation AI model, it creates a specific action plan based on the prompt message, "Create suggestions for employees showing signs of high stress." The output is a dataset of personalized suggestions as notification content.

[0841] Step 6:

[0842] The terminal receives the suggestion notification sent from the server and presents it to the employee. The input is the individual suggestion data generated in step 5. Specifically, the notification is displayed on the terminal and includes links and action buttons to allow the employee to easily access resources. The output is the notification display information as provided to the employee.

[0843] Step 7:

[0844] The server collects and analyzes anonymous feedback from employees. Input data is gathered through feedback forms and surveys. An emotion engine is used to classify the feedback content and analyze the organization's emotional trends. The output is an organizational emotional analysis report.

[0845] (Application Example 2)

[0846] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0847] The current lack of detailed assessments of employees' emotions and stress levels presents a challenge in implementing appropriate measures to prevent turnover and improve engagement. Furthermore, the absence of a system for emotionally evaluating employee feedback and understanding the overall emotional trends within the organization makes it difficult to implement swift and effective corrective measures.

[0848] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0849] In this invention, the server includes means for collecting and analyzing employee communication information, means for determining emotions and stress levels based on the analysis and proposing stress reduction measures as necessary, means for notifying employees and managers, and means for anonymously collecting opinions and evaluating emotions. This enables detailed information about employees' mental states and early intervention for appropriate improvements.

[0850] "Communication information" refers to text data such as emails and chat messages exchanged by employees in the course of their work.

[0851] An "emotion engine" is a system that uses natural language processing technology and machine learning algorithms to identify emotions from text data and evaluate their intensity.

[0852] "Stress level" refers to the degree of mental burden on an employee, as determined by an emotional engine.

[0853] "Methods for collecting opinions anonymously" refer to ways in which employees can provide their opinions without them being known to third parties.

[0854] "Follow-up" refers to activities that provide ongoing support and suggestions to employees based on emotional data.

[0855] "Emotional trends" refer to the overall patterns and tendencies of individual employees' emotions within an organization.

[0856] An "improvement proposal" is a plan that outlines specific measures to address business processes and organizational sentiment based on the analysis results.

[0857] The system that realizes this invention implements a program that collects and analyzes employee communication information. The server collects text data from messaging apps and email systems that employees use on a daily basis and analyzes it using natural language processing techniques and machine learning algorithms. For the analysis, generative AI models suitable for sentiment analysis, such as Google's BERT model or OpenAI's GPT-3, are used.

[0858] The emotion engine identifies emotions from text data and determines stress levels. Based on this information, the server suggests stress relief measures and mental health support resources, and sends notifications to administrators and the employee via their devices. The notifications include links to specific resources and methods for mental health care.

[0859] Furthermore, anonymous feedback is collected from employees, and emotional evaluations are performed using an emotion engine to understand the emotional trends of the entire organization. The server aggregates this data, reports the company's overall emotional trends to managers, and proposes necessary business improvements and support systems.

[0860] As a concrete example, when a user experiences communication difficulties during delivery work, the server analyzes the message content and sends a follow-up notification to the user guiding them to a counseling service to reduce stress. Links to the necessary resources are provided in a format that can be immediately accessed on a smartphone. This process supports employees' mental health early on and improves job satisfaction.

[0861] Examples of prompt statements are as follows:

[0862] "Explain how to create a program that assesses employees' emotions and stress levels and suggests appropriate support resources."

[0863] "Please provide specific steps for analyzing an organization's emotional trends based on emotional data and proposing improvement plans."

[0864] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0865] Step 1:

[0866] The server collects text data from messaging apps and email systems used by employees. In this step, the collected text data is sent to the server as input, preparing foundational data for a comprehensive understanding of employee intent and context. The output is a set of verified text data.

[0867] Step 2:

[0868] The server uses an emotion engine to analyze the collected text data and identify the emotion (positive, negative, or neutral) of each message. The input is the text data obtained in step 1, and natural language processing techniques and machine learning algorithms (e.g., BERT, GPT-3) are used. The output is the emotion determination result for each message.

[0869] Step 3:

[0870] The server quantifies the stress level of employees based on the sentiment analysis results. To calculate the stress score, an algorithm for quantifying the degree of stress is applied using the output of the sentiment engine as input. The output is the stress score for each employee, and appropriate resource proposals are made based on this score.

[0871] Step 4:

[0872] The user receives a notification of the stress level sent from the server on the terminal. The inputs are the stress score and the proposed content based on it, and the output is a notification message that the user can view. As an operation, the user is enabled to access the proposed mental health support resources.

[0873] Step 5:

[0874] The server receives feedback provided by employees from the anonymous opinion collection form and analyzes this with the sentiment engine. The input is the text data of the anonymous feedback, and sentiment evaluation and opinion classification are performed. The output is the sentiment evaluation result and the categorized feedback.

[0875] Step 6:

[0876] The server creates a report for reporting the overall sentiment trend of the organization to the administrator based on the aggregated feedback data and the sentiment analysis results. The input is the output of Step 5, and the output is a report for the administrator that includes visualized data. This enables the formulation of business improvements and support systems as needed.

[0877] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0878] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0879] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0880] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0881] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0882] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0883] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0884] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0885] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0886] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0887] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0888] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0889] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0890] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0891] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0892] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0893] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0894] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0895] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0896] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0897] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0898] The following is further disclosed regarding the embodiments described above.

[0899] (Claim 1)

[0900] Means for collecting and analyzing employee communication information,

[0901] A means for determining the emotions and stress levels of employees based on the analysis thereof,

[0902] A means of notifying the administrator based on the judgment result,

[0903] Methods for collecting opinions from employees anonymously,

[0904] A means of collecting and reporting such opinions while maintaining anonymity,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] A means of analyzing employee work history and skills data,

[0908] A means for generating skill development and career plans based on the analysis results,

[0909] A means of presenting the generated plan to the employees,

[0910] The system according to claim 1, further comprising:

[0911] (Claim 3)

[0912] A means of analyzing communication information within a group to identify areas for improvement in business processes,

[0913] A means for creating optimal improvement proposals for the identified areas for improvement,

[0914] A means of notifying the administrator of the improvement proposal,

[0915] The system according to claim 1, further comprising:

[0916] "Example 1"

[0917] (Claim 1)

[0918] Means for collecting information and performing statistical analysis,

[0919] A means for inferring emotions or psychological states based on the analysis,

[0920] A means of providing information to the administrator based on the estimation results,

[0921] Methods for collecting opinions anonymously,

[0922] A means of organizing and reporting such opinions while maintaining anonymity,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] A means of analyzing work history and skills information,

[0926] A means for creating a skills improvement or career plan based on the analysis results,

[0927] The system according to claim 1, further comprising means for displaying the created plan to a user.

[0928] (Claim 3)

[0929] A means of analyzing information within an organization and identifying areas for improvement in business procedures,

[0930] A means for formulating the optimal improvement proposal for the identified areas for improvement,

[0931] The system according to claim 1, further comprising means for presenting the improvement proposal to the administrator.

[0932] "Application Example 1"

[0933] (Claim 1)

[0934] Means for collecting and analyzing employee communication information,

[0935] A means for determining the emotions and stress levels of employees based on the analysis thereof,

[0936] A means of notifying the administrator based on the judgment result,

[0937] Methods for collecting opinions from employees anonymously,

[0938] A means of collecting and reporting such opinions while maintaining anonymity,

[0939] A means for employees to track their own stress levels and propose countermeasures,

[0940] A system that includes this.

[0941] (Claim 2)

[0942] A means of analyzing employee work history and skills data,

[0943] A means for generating skill development and career plans based on the analysis results,

[0944] A means of presenting the generated plan to the employees,

[0945] A means of providing a platform for employees to submit anonymous feedback,

[0946] The system according to claim 1, further comprising:

[0947] (Claim 3)

[0948] A means of analyzing communication information within a group to identify areas for improvement in business processes,

[0949] A means for creating optimal improvement proposals for the identified areas for improvement,

[0950] A means of notifying the administrator of the improvement proposal,

[0951] A means of proposing online resources to support stress management and skill development,

[0952] The system according to claim 1, further comprising:

[0953] "Example 2 of combining an emotion engine"

[0954] (Claim 1)

[0955] Means for collecting and pre-processing employee information,

[0956] A means for identifying and evaluating emotions using natural language processing technology and machine learning algorithms,

[0957] A means of generating personalized suggestions based on emotions and stress levels,

[0958] A means of presenting the proposal to employees via an information device,

[0959] A means of collecting feedback from employees and reporting areas for improvement,

[0960] A system that includes this.

[0961] (Claim 2)

[0962] A means of analyzing work history and skills data to suggest skill improvement and career paths,

[0963] Enter text here: The system according to claim 1.

[0964] (Claim 3)

[0965] A means of analyzing communication information, identifying areas for improvement, and proposing solutions.

[0966] Using information technology, a means of introducing appropriate resources to employees,

[0967] Enter text here: The system according to claim 1.

[0968] "Application example 2 when combining with an emotional engine"

[0969] (Claim 1)

[0970] Means for collecting and analyzing employee communication information,

[0971] A means for determining the emotions and stress levels of employees based on the analysis and proposing stress reduction measures as needed,

[0972] A means of notifying the manager and the employee based on the determination result,

[0973] A method for anonymously collecting opinions from employees and evaluating the sentiment of those opinions using an emotion engine,

[0974] A means of aggregating and reporting the evaluated opinions while maintaining anonymity,

[0975] A system that includes this.

[0976] (Claim 2)

[0977] A means of analyzing employee work history and skills information,

[0978] A means for generating skill development and career plans based on the analysis results, and for providing follow-up based on individual emotional data,

[0979] A means of presenting the generated plan to employees and proposing follow-up measures,

[0980] The system according to claim 1, further comprising:

[0981] (Claim 3)

[0982] A means of analyzing communication information within a group to identify areas for improvement in business processes and the overall sentiment trends of the organization,

[0983] A means for creating optimal improvement proposals based on the identified areas for improvement and emotional trends,

[0984] Means for notifying the administrator of the improvement suggestion and including follow-up suggestions as necessary,

[0985] The system according to claim 1, further comprising: [Explanation of symbols]

[0986] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting and analyzing employee communication information, A means for determining the emotions and stress levels of employees based on the analysis thereof, A means of notifying the administrator based on the judgment result, Methods for collecting opinions from employees anonymously, A means of collecting and reporting such opinions while maintaining anonymity, A system that includes this.

2. A means of analyzing employee work history and skills data, A means for generating skill development and career plans based on the analysis results, A means of presenting the generated plan to the employees, The system according to claim 1, further comprising:

3. A means of analyzing communication information within a group to identify areas for improvement in business processes, A means for creating optimal improvement proposals for the identified areas for improvement, A means of notifying the administrator of the improvement proposal, The system according to claim 1, further comprising:

Images