system

Abstract

We provide the system. [Solution] A means of collecting communication information and performing preliminary processing to prepare for data analysis, A means for generating numerical values ​​for ability evaluation by applying natural language processing to pre-processed information, A means of creating individualized support information and educational plans based on the generated competency assessment scores, A means of automatically suggesting career path selections based on an individual's abilities, A means for collecting and analyzing operating data of machinery and equipment, and for generating and displaying an efficiency score, A means of providing optimization proposals tailored to the characteristics of machinery and equipment, and offering maintenance schedules, 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 as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional human resource management systems, there are many parts that rely on human evaluations, and the subjectivity and biases of evaluators may affect the evaluation results, so there is a problem of lack of fairness. In addition, it is difficult to propose appropriate training and career paths for each employee, and the time and costs associated with human resource management have been increasing. Furthermore, there is also a problem that the process of collecting and analyzing feedback for effectively implementing engagement improvement measures is complicated and it is difficult to make quick decisions.

Means for Solving the Problems

[0005] This invention provides a system for evaluating employee skills by collecting communication data, preprocessing it, and then performing text analysis. This method generates skill evaluation scores using natural language processing technology and automatically creates individualized feedback and training programs based on those scores. Furthermore, it can automate the suggestion of career paths tailored to employee capabilities and provide evaluations and improvement suggestions to enhance employee engagement. This eliminates bias from human evaluation, enables efficient and fair talent management, reduces resource management costs, and facilitates rapid decision-making.

[0006] "Communication data" refers to electronic information generated through internal communication within an organization, such as company emails and chat logs.

[0007] "Preprocessing" refers to a series of processes performed to prepare raw data into an analyzable format, including noise reduction and tokenization.

[0008] "Text analysis" is the process of extracting meaning from text data using natural language processing techniques and organizing the information.

[0009] A "skill evaluation score" is an indicator generated to quantitatively assess an employee's abilities, and it is a numerical value calculated based on specific criteria.

[0010] "Feedback" refers to information provided to individual employees based on their evaluation results, highlighting their strengths and areas for improvement in their work.

[0011] A "training program" is educational content provided with the aim of improving employees' skills, and it is customized to meet specific needs.

[0012] A "career path" is a plan that outlines the range of job roles and positions an employee can potentially achieve in the future.

[0013] "Engagement" is a concept that refers to the passion, attachment, and degree of involvement that employees have for the organization and their work. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] The human resource management system of this invention efficiently evaluates and develops employees by combining AI technology and natural language processing. This system is primarily operated by three entities: a server, terminals, and users.

[0036] Data collection and analysis

[0037] The server automatically collects internal communication data via APIs. Examples of collected data include emails, chat logs, and business reports.

[0038] The server preprocesses the collected data and then performs text analysis using natural language processing techniques. This analysis extracts the information necessary for evaluating employee skills.

[0039] Skill assessment and feedback

[0040] The server generates a skill evaluation score for each employee based on the analysis results. This score quantifies each employee's strengths and areas for improvement in their work.

[0041] The device provides individual employee feedback through a visual dashboard, which includes information such as praise and suggestions for improvement.

[0042] Training program and career path proposals

[0043] The server automatically generates personalized training programs based on each employee's performance score, providing each employee with opportunities for skill development tailored to their individual needs.

[0044] The server further proposes potential career paths to promote employees' long-term growth. These proposals are made taking into account the employee's abilities and interests.

[0045] Engagement evaluation and improvement

[0046] The server regularly collects feedback and engagement surveys from employees and analyzes the results to generate feedback that improves engagement across the entire organization.

[0047] For example, the feedback that employees receive includes evaluations of their contributions to recent projects and their ability to collaborate with colleagues. Furthermore, the dashboard displayed on the device allows for one-click enrollment in training courses tailored to their skills. This enables organizations to support the growth of each employee while achieving fair and efficient talent management.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] The server periodically collects communication data from data sources connected to the company's internal network. This includes logs from the company's email server and chat applications.

[0051] Step 2:

[0052] The server preprocesses the collected data, performing noise reduction and text normalization. This process prepares the data for text analysis.

[0053] Step 3:

[0054] The server analyzes the data, which has been preprocessed using natural language processing. Here, techniques such as key phrase extraction and sentiment analysis are used to extract information for evaluating employees' skills and work attitudes.

[0055] Step 4:

[0056] The server generates a skills evaluation score for each employee based on the analysis results. This score quantifies the employee's abilities and records them numerically.

[0057] Step 5:

[0058] The device updates a dashboard to provide feedback to employees based on the generated skill assessment scores. The feedback highlights their strengths and areas for improvement in their work.

[0059] Step 6:

[0060] Based on evaluation scores, the server selects training programs suitable for employees and automatically creates personalized career development plans.

[0061] Step 7:

[0062] The terminal displays training program information on a dashboard, making it easily accessible to employee users.

[0063] Step 8:

[0064] Users can review their skill assessment and training program, and voluntarily take recommended courses as needed.

[0065] Step 9:

[0066] The server regularly collects and analyzes employee feedback and engagement surveys, and generates feedback to improve engagement within the company.

[0067] Step 10:

[0068] Users can receive the results of their engagement evaluations and use them to improve their activities within the organization.

[0069] (Example 1)

[0070] 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."

[0071] In today's complex work environment, there is a need for efficient evaluation and development of talent, as well as improved engagement. The challenge lies in collecting information from diverse communication channels, appropriately analyzing and evaluating it, supporting each individual's career path, and improving the overall operational efficiency of the organization.

[0072] 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.

[0073] In this invention, the server includes means for collecting communication information and preprocessing it to prepare it for language analysis; means for applying natural language processing to the preprocessed information to generate technical evaluation values; and means for creating individual opinion exchange and training plans based on the generated technical evaluation values. This makes it possible to streamline human resource management within the organization and provide individualized feedback and skill development opportunities for each employee.

[0074] "Communication information" refers to digital data related to business activities, such as emails, chat messages, and document files within a company.

[0075] "Preprocessing" refers to the data processing steps taken before data analysis to remove unnecessary information and standardize the data format.

[0076] "Natural language processing" refers to computer technology used to understand and analyze human language.

[0077] "Technical evaluation scores" refer to the results of an evaluation that quantifies an employee's abilities and performance.

[0078] "Opinion exchange" is an interactive information provision process for providing feedback to employees based on evaluation results.

[0079] A "training plan" is a training curriculum proposed by an organization to improve the skills of its employees.

[0080] "Job career options" are proposals that outline the future direction and growth opportunities for employees' careers.

[0081] "Employee engagement" refers to the degree of involvement and passion that employees have for their work and the organization.

[0082] An "information display device" is a device that visualizes and presents digital information to the user.

[0083] "Survey results" refer to data that presents opinions and new perspectives collected from employees.

[0084] This invention is a system for streamlining human resource management, aiming to improve employee evaluation, development, and engagement within a company. This system primarily consists of three elements: a server, terminals, and users.

[0085] The server automatically collects various communication information within the company using APIs. Specifically, this includes emails, chat messages, and document files. The collected information is preprocessed to remove unnecessary information and standardize data formats. Then, natural language processing technology is applied to analyze the data and generate technical evaluation scores for each employee.

[0086] The terminal visually displays technical evaluation values ​​received from the server on an information display device. Using the user interface, the evaluation values ​​are visualized as bar graphs and radar charts, providing feedback to the user. Furthermore, the user can access training plans to improve their skills based on this feedback and register for appropriate training courses.

[0087] Furthermore, the server suggests career path options based on each individual's skills, encouraging long-term growth. Users can review these suggestions via their devices and use them as a basis for considering their career paths.

[0088] As a concrete example, a generative AI model can be used to analyze the sentiment of emails, and if there is a lot of positive feedback, it can generate an evaluation that highlights that as a strength. Furthermore, as an example of a prompt, you can input something like, "Create personalized feedback and skill-building suggestions based on the contributions of our team members to the new project," and receive a response.

[0089] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0090] Step 1:

[0091] The server automatically collects various types of communication information within the company using an API. This includes emails, chat messages, and document files. The input is all communication data generated during a given period, and the goal is to extract this data and format it for analysis. In practice, the server periodically calls the API endpoint to retrieve the latest communication data.

[0092] Step 2:

[0093] The server preprocesses the collected raw data. This involves removing unnecessary information and standardizing the data format. The input is the data collected in step 1; for example, email headers are removed, and only the necessary text is extracted. The output is a clean and consistent dataset. In this process, the server removes line breaks and whitespace to ensure data integrity.

[0094] Step 3:

[0095] The server performs analysis by applying natural language processing techniques to pre-processed data. The input is the pre-processed dataset to which a specific generative AI model is applied. The data calculations performed here include text sentiment analysis and keyword extraction. The server derives a technical evaluation score for each employee as an analysis result. The output is a result set containing these scores.

[0096] Step 4:

[0097] The server creates individual feedback and training plans based on the generated technical evaluation scores. The input is each employee's evaluation score, which the server uses to propose appropriate feedback and training plans. In actual operation, training courses are selected for skills with low evaluation scores. The output consists of specific training programs and feedback messages.

[0098] Step 5:

[0099] The terminal visually displays technical evaluation figures and feedback received from the server on an information display device. The input is data sent from the server, and the terminal visualizes this information by displaying it as bar graphs or radar charts. The output is an explicit feedback display for the user.

[0100] Step 6:

[0101] Users select and execute actions based on the feedback and training plan provided. The input is the information displayed on the device, which the user uses to choose a path for skill development. For example, they might register for a specific training course. The output is the user's selection and subsequent actions.

[0102] (Application Example 1)

[0103] 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."

[0104] To achieve efficient management and operation of machinery and robots within a factory, it is necessary to collect and appropriately analyze the operational data of each device and robot. However, conventional methods rely heavily on human subjectivity, making it difficult to achieve optimal operation and maintenance. Furthermore, a lack of concrete improvement suggestions to enhance efficiency often leads to missed opportunities for increased productivity. There is a need to solve these problems and maximize the performance of machinery and robots.

[0105] 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.

[0106] In this invention, the server includes means for collecting communication information and performing preliminary processing to prepare for data analysis, means for applying natural language processing to the preliminary processed information to generate a numerical value for performance evaluation, and means for collecting and analyzing operating data of machinery and equipment, and generating and displaying an efficiency score. This makes it possible to objectively and efficiently evaluate the operating status of machinery and robots. Furthermore, by providing optimization suggestions and maintenance schedules tailored to the characteristics based on the generated efficiency score, it is possible to optimize the production process and improve the efficiency of maintenance.

[0107] "Communication information" refers to electronic data collected from machinery and robots used within a factory, including operation logs and operating status.

[0108] "Pre-processing" refers to the data organization and transformation work performed to make collected communication information easier to analyze, and includes data standardization and noise removal.

[0109] "Natural language processing" is a technology that uses computers to analyze human language, understand its meaning, and generate it. It is also used for summarizing and classifying the analysis results.

[0110] "Performance evaluation values" are performance indicators obtained by analyzing the motion data of machinery and robots, and represent a numerical representation of efficiency and precision.

[0111] "Operation data" refers to information that includes records of tasks performed by machinery or robots and their operation history; it's like an operation log.

[0112] The "efficiency score" is an index calculated based on collected motion data, and is used to evaluate the operating status and productivity of machinery and robots.

[0113] "Optimization proposals" refer to methods and strategies proposed to improve the operation of machinery and robots, encompassing a wide range of areas such as productivity improvement and energy efficiency.

[0114] A "maintenance schedule" refers to the schedule of inspections and maintenance work necessary to maintain the performance of machinery and robots, and is a plan for regular maintenance.

[0115] The system for implementing this invention effectively manages and optimizes the performance of machinery and robots within a factory. The server collects factory communication information via an API and performs preliminary processing to prepare for data analysis. This preliminary processing unifies the raw data and removes unnecessary information, enabling efficient subsequent data analysis.

[0116] The pre-processed information is analyzed using a natural language processing library to generate numerical performance evaluations for each machine and robot. This makes it possible to objectively understand work efficiency and accuracy. In addition, an efficiency score is calculated based on the operation data collected daily from the machines and displayed visually on a dashboard. This display uses heatmaps and graphs to allow factory operators to intuitively understand the status of each piece of equipment.

[0117] Furthermore, based on the generated efficiency score, the server suggests areas for optimization. These suggestions include methods for improving productivity and reducing energy consumption. The server also helps ensure that regular maintenance plans are implemented efficiently by automatically creating maintenance schedules for machinery and equipment and notifying operators.

[0118] This approach improves the operational efficiency of machinery and robots within the factory, enabling operators to achieve advanced operational management with minimal effort. Furthermore, by utilizing generative AI models, more accurate and practical optimization suggestions are provided. One example of a prompt is, "What improvements should be made to maximize the transport efficiency of this robot?"

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server collects communication information from various machines and robots within the factory via APIs. This communication information includes operation logs and sensor operation data. The server receives this raw data and stores it in a database. The input is raw communication information, and the output is an organized dataset.

[0122] Step 2:

[0123] The server preprocesses the collected data and converts it into an analyzable format. This process filters out unnecessary data and handles outliers and missing values, preparing the data for analysis. The input is raw communication information, and the preprocessed output yields a clean dataset.

[0124] Step 3:

[0125] The server applies natural language processing (NLP) techniques to pre-processed data to analyze operations and situations recorded in a text-like format. This generates numerical performance evaluations for each machine and robot. The input is a pre-processed dataset, and the output is a numerical performance evaluation.

[0126] Step 4:

[0127] The terminal calculates an efficiency score based on the performance evaluation data received from the server and displays it on the dashboard. This display uses heatmaps and line graphs to make it visually easy for operators to understand. The input is the performance evaluation data, and the output is a visualized efficiency score.

[0128] Step 5:

[0129] The server analyzes the efficiency score and generates optimization suggestions. These include improvements to work processes and energy efficiency. The use of a generating AI model enables highly accurate suggestions. An example of this prompt might be, "What improvements should be made to maximize the transport efficiency of this robot?" The input is the efficiency score, and the output is the optimization suggestion.

[0130] Step 6:

[0131] The server automatically generates maintenance schedules for machinery and equipment, creating plans for necessary inspections and maintenance. This allows operators to perform maintenance work efficiently and at the appropriate time. Inputs are historical operational data and efficiency scores, and output is the maintenance schedule.

[0132] 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.

[0133] The human resource management system of this invention utilizes AI technology to evaluate employee skills and improve employee engagement. This system has a configuration involving three elements: a server, a terminal, and a user, and is particularly characterized by the incorporation of an emotion engine for recognizing user emotions.

[0134] First, the server collects communication data from within the company network, preprocesses it, and then applies natural language processing techniques to analyze the text data. During this process, it utilizes an emotion engine to detect the emotional tone contained in the communication data. For example, it can be used to assess employee stress levels and satisfaction levels from emails and chats.

[0135] Next, the server generates a skill evaluation score based on the analysis data. This score also incorporates data from the emotion engine, allowing for a more precise assessment of employee capabilities. Furthermore, personalized feedback and training programs are created based on the emotion analysis results. The terminal displays the generated feedback and skill evaluation score on a dashboard, making it easy for employees (users) to view.

[0136] By using an emotion engine, career path suggestions become even more personalized. The server considers the employee's emotional state and job interests to suggest the most suitable career options. In this way, users can gain a more concrete vision of their own growth.

[0137] This system also excels from the perspective of employee engagement evaluation. The server regularly collects and analyzes employee feedback and survey data. During this process, it uses an emotion engine to analyze the emotional aspects of the responses and generate more targeted improvement suggestions. The terminal then presents these suggestions to the user in a timely manner, contributing to improved organizational morale.

[0138] A concrete example is when an employee, as a user, receives a warning about their stress level on the dashboard and is introduced to a stress reduction program tailored to their needs. This allows the employee to receive the necessary support and improve their performance.

[0139] The present invention aims to achieve fair and efficient human resource management through these steps, thereby improving employee growth and well-being within the company.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The server automatically collects communication data from the company's internal email server and chat application logs. This is done using an API connection and is configured to be updated at regular intervals.

[0143] Step 2:

[0144] The server performs preprocessing on the collected communication data. Specifically, this includes tasks such as denoising text, tokenization, and normalization, converting the data into a format that is easy to analyze at this stage.

[0145] Step 3:

[0146] The server applies natural language processing to the preprocessed data and performs text analysis. This analysis includes key phrase extraction, sentiment analysis, and evaluation of emotional tone using a sentiment engine.

[0147] Step 4:

[0148] The server calculates a skill evaluation score for each employee based on the results obtained from natural language processing. In addition, emotional data obtained from the emotion engine is also incorporated into the score.

[0149] Step 5:

[0150] The device visually displays each employee's skill assessment score and sentiment analysis results on a dashboard. The displayed information includes the employee's work strengths, areas for improvement, and emotional tendencies.

[0151] Step 6:

[0152] The server automatically generates individually optimized feedback and training programs based on evaluation scores and sentiment data.

[0153] Step 7:

[0154] The terminal provides users with generated training programs and feedback content via a dashboard. Employees can refer to this and select recommended training courses.

[0155] Step 8:

[0156] The server automatically suggests appropriate career path options based on employee sentiment data and performance scores. These suggestions are based on job suitability and interests.

[0157] Step 9:

[0158] The device displays career path suggestions on a dashboard, providing a foundation for users to select one and pursue their own professional development.

[0159] Step 10:

[0160] The server periodically collects feedback and engagement surveys from employees and analyzes them using an emotion engine. This allows it to generate feedback that takes into account strategies for improving engagement.

[0161] Step 11:

[0162] The device provides employees with engagement-based feedback and offers them the opportunity to use it as a suggestion for organizational improvement.

[0163] Step 12:

[0164] Users can leverage the provided information and support programs to improve their personal performance and job satisfaction.

[0165] (Example 2)

[0166] 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 will be referred to as the "terminal."

[0167] The challenge lies in promoting individual growth and improving engagement through accurate assessment of employees' skills and psychological states. Traditional methods fail to adequately consider emotional aspects, making it difficult to provide personalized feedback and career path suggestions.

[0168] 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.

[0169] In this invention, the server includes means for collecting communication information and preprocessing it to prepare it for text analysis; means for applying natural language processing to the preprocessed information, performing sentiment analysis, and generating skill evaluation indicators; and means for creating individualized feedback and educational programs based on the generated skill evaluation indicators and sentiment data. This makes it possible to comprehensively evaluate an individual's abilities and emotional state and provide personalized support.

[0170] "Communication information" refers to messages and data sent over a network, including email, chat messages, and voice data.

[0171] "Preprocessing" refers to the initial stage of processing raw data into a format that is easy to analyze, and includes processes such as format standardization, noise reduction, and anonymization.

[0172] "Natural language processing" refers to technologies that enable machines to understand and analyze human language, including techniques for part-of-speech analysis and semantic analysis of text data.

[0173] "Emotion analysis" refers to a technology that extracts emotions and emotional tones from text and audio data to determine specific emotions.

[0174] A "skill evaluation index" is a way of expressing an individual's abilities and skills using numerical values ​​or indicators, and serves as a standard used when evaluating abilities.

[0175] "Feedback" refers to the act of providing evaluations and opinions on specific activities or performances, and offering information to encourage improvement and enhancement.

[0176] An "educational program" refers to a series of learning activities and training designed to improve an individual's skills and knowledge.

[0177] "Career path options" refers to presenting various possible paths for an individual's career growth and future professional advancement, and suggesting the most suitable career route.

[0178] "Engagement" refers to the degree of proactiveness and commitment an individual shows towards an organization or its activities, and is particularly related to employee job satisfaction and sense of participation.

[0179] This invention aims to improve the efficiency of human resource management by utilizing communication information, and is implemented using a system mainly composed of a server, terminal, and user. Specifically, the server collects communication information such as communication messages and chat data, and performs preprocessing such as standardizing the data format and anonymizing it. This makes the data suitable for analysis.

[0180] The server applies natural language processing techniques to pre-processed information to analyze the emotions contained in the text. A natural language processing engine is used for emotion analysis, for example, analyzing expressions like "I'm busy and stressed" to determine the associated emotional tone. This process allows for an understanding of each user's psychological state.

[0181] Based on the analysis results, the server generates skill evaluation metrics and suggests feedback and training programs optimized for the user. For example, if the analysis results indicate that "employees have high stress levels," a stress management training program might be recommended.

[0182] The generated feedback and skill evaluation scores are provided to the user through the device. The device has a dashboard function and is designed to display information visually, making it easier for the user to understand their own status and take steps to improve.

[0183] For example, a user can send a query to the system using the prompt, "Please tell me my current stress level and how to improve it." This allows them to receive immediate support and advice tailored to their individual situation.

[0184] This invention supports individual growth and well-being within an organization and contributes to improved employee engagement.

[0185] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0186] Step 1:

[0187] The server collects communication information transmitted over the network. Input includes emails and chat messages. The server then preprocesses this data by removing personally identifiable information and standardizing the data format. The output is anonymized data that is easy to analyze.

[0188] Step 2:

[0189] The server applies natural language processing (NLP) techniques to preprocessed data. The input is preprocessed text data. The server performs morphological analysis to extract the structure and meaning of the text. Sentiment analysis is also performed in parallel. The output is structured text data with identified emotional tones.

[0190] Step 3:

[0191] The server generates skill evaluation metrics based on the analysis results. The input is emotion analysis and NLP results, which evaluate the user's skills and emotional stability. The server performs calculations to represent this numerically and graphically. The output provides evaluation metrics regarding the user's skills and emotional state.

[0192] Step 4:

[0193] The server creates personalized feedback and training programs based on the generated skill assessment metrics and sentiment data. The input is individual user assessment data. The server generates recommendations to improve the user's specific challenges. The output includes a feedback report and a proposed training program.

[0194] Step 5:

[0195] The terminal receives feedback and evaluation metrics from the server and displays them on the dashboard. Inputs are reports and scores sent from the server. The terminal converts these into a user-friendly graphical format for visualization. Outputs are evaluation information viewable by the user.

[0196] Step 6:

[0197] Users can view their feedback and performance metrics through a dashboard. Users can input prompts into the system, such as "Please tell me how to improve my stress levels." As output, users can receive specific advice and guidance from the system.

[0198] (Application Example 2)

[0199] 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".

[0200] In today's living environment, there is a need to accurately understand the stress and emotional state of individual users and to provide appropriate support promptly. Furthermore, conventional technologies are limited to standard methods for assessing users' abilities and proposing career paths, making it difficult to provide individually optimized suggestions based on each user's characteristics and emotional changes. Therefore, the present invention aims to solve these problems and provide personalized feedback and career path suggestions while promoting stress reduction for users.

[0201] 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.

[0202] In this invention, the server includes means for collecting communication data and preprocessing it to prepare it for text analysis; means for applying natural language processing to the preprocessed data to generate a skill evaluation score; means for creating individual feedback and a skill improvement plan based on the generated skill evaluation score; means for automatically suggesting career path options based on the individual's abilities; and means for analyzing the user's emotional state and making specific suggestions to promote stress reduction based on that analysis. This enables the user to receive optimal feedback and options that take their emotional state into consideration, helping to reduce stress in daily life and promote self-growth.

[0203] "Communication data" refers to all information transmitted and received over a network, and includes various formats such as text, audio, and images.

[0204] "Preprocessing" refers to the processes performed prior to data analysis, including data cleansing and formatting standardization, as preparatory work to improve analysis efficiency.

[0205] Natural language processing is a technology that enables computers to understand, generate, and respond to human language, and is widely used in the analysis of text and audio data.

[0206] A "skill evaluation score" is a numerical assessment of a user's abilities and skills, and is used as a guideline for occupational aptitude and skill development.

[0207] "Feedback" is the process of providing opinions and reactions regarding specific actions or results, offering information to encourage improvement and motivation.

[0208] A "skills improvement plan" is a plan that an individual formulates to improve their own abilities, and it sets out specific goals and means.

[0209] "Career path options" refer to the diverse paths that users can take in their professional lives, and are proposed based on their individual abilities and interests.

[0210] "Emotional state" refers to the overall emotional state an individual is experiencing at a particular point in time, and it fluctuates based on subjective experience.

[0211] "Stress reduction" refers to alleviating the psychological or physical burden an individual is experiencing, and relaxation techniques and a suitable environment are the means to achieve this.

[0212] In this invention, a server plays a central role in collecting and preprocessing communication data. The server performs data cleansing to remove unnecessary parts from the information and convert it into a unified format. Subsequently, natural language processing is applied to generate skill evaluation scores. This process utilizes a natural language processing framework to analyze the meaning from text data and perform numerical evaluations.

[0213] On the user's device, the generated skill assessment score is visually displayed through a dashboard. This allows users to intuitively understand their abilities and aptitudes. Furthermore, the server uses an emotion engine to analyze the user's emotional state and provide optimal suggestions to promote stress reduction. This function recommends appropriate actions based on the user's current psychological state.

[0214] For example, if the server determines that a user needs to relax after a busy day at home, the device can suggest relaxation music. A key feature of this suggestion is that it is customized based on the user's past preferences and current emotional state.

[0215] Regarding generative AI models, an example of a prompt would be: "Explain how a home robot can analyze family voice data, recognize their emotional state, and provide specific suggestions to reduce stress."

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] The server receives audio data from within the home as communication data and preprocesses this data as input. Specifically, it uses speech recognition technology to remove noise and convert the audio signal into text. The output of this processing is clean text data suitable for analysis.

[0219] Step 2:

[0220] The server applies natural language processing to the pre-processed text data. This involves contextual analysis, topic recognition, and evaluation of the emotional tone of the conversation. The input to this analysis is the text data obtained in the previous step, and the output is data on individual emotional states and emotional tones.

[0221] Step 3:

[0222] The server uses an emotion engine to analyze the user's emotional state. Specifically, it analyzes the output data from the previous step to calculate the user's stress level and current emotional tendencies. The input is emotional tone data, and the output is a quantified evaluation value of the emotional state.

[0223] Step 4:

[0224] The device receives emotional state assessment values ​​and, based on that data, visually displays optimal relaxation suggestions for the user on a dashboard. These suggestions include music types and relaxation exercises. The output is a visual suggestion interface displayed on the device.

[0225] Step 5:

[0226] The user selects a suggestion presented by the device and initiates a specific action. For example, they might play suggested music or start a recommended exercise to reduce stress. The input in this step is the user's choice, and the output is the initiation of physical relaxation.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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".

[0243] The human resource management system of this invention efficiently evaluates and develops employees by combining AI technology and natural language processing. This system is primarily operated by three entities: a server, terminals, and users.

[0244] Data collection and analysis

[0245] The server automatically collects internal communication data via APIs. Examples of collected data include emails, chat logs, and business reports.

[0246] The server preprocesses the collected data and then performs text analysis using natural language processing techniques. This analysis extracts the information necessary for evaluating employee skills.

[0247] Skill assessment and feedback

[0248] The server generates a skill evaluation score for each employee based on the analysis results. This score quantifies each employee's strengths and areas for improvement in their work.

[0249] The device provides individual employee feedback through a visual dashboard, which includes information such as praise and suggestions for improvement.

[0250] Training program and career path proposals

[0251] The server automatically generates personalized training programs based on each employee's performance score, providing each employee with opportunities for skill development tailored to their individual needs.

[0252] The server further proposes potential career paths to promote employees' long-term growth. These proposals are made taking into account the employee's abilities and interests.

[0253] Engagement evaluation and improvement

[0254] The server regularly collects feedback and engagement surveys from employees and analyzes the results to generate feedback that improves engagement across the entire organization.

[0255] For example, the feedback that employees receive includes evaluations of their contributions to recent projects and their ability to collaborate with colleagues. Furthermore, the dashboard displayed on the device allows for one-click enrollment in training courses tailored to their skills. This enables organizations to support the growth of each employee while achieving fair and efficient talent management.

[0256] The following describes the processing flow.

[0257] Step 1:

[0258] The server periodically collects communication data from data sources connected to the company's internal network. This includes logs from the company's email server and chat applications.

[0259] Step 2:

[0260] The server preprocesses the collected data, performing noise reduction and text normalization. This process prepares the data for text analysis.

[0261] Step 3:

[0262] The server analyzes the data, which has been preprocessed using natural language processing. Here, techniques such as key phrase extraction and sentiment analysis are used to extract information for evaluating employees' skills and work attitudes.

[0263] Step 4:

[0264] The server generates a skills evaluation score for each employee based on the analysis results. This score quantifies the employee's abilities and records them numerically.

[0265] Step 5:

[0266] The device updates a dashboard to provide feedback to employees based on the generated skill assessment scores. The feedback highlights their strengths and areas for improvement in their work.

[0267] Step 6:

[0268] Based on evaluation scores, the server selects training programs suitable for employees and automatically creates personalized career development plans.

[0269] Step 7:

[0270] The terminal displays training program information on a dashboard, making it easily accessible to employee users.

[0271] Step 8:

[0272] Users can review their skill assessment and training program, and voluntarily take recommended courses as needed.

[0273] Step 9:

[0274] The server regularly collects and analyzes employee feedback and engagement surveys, and generates feedback to improve engagement within the company.

[0275] Step 10:

[0276] Users can receive the results of their engagement evaluations and use them to improve their activities within the organization.

[0277] (Example 1)

[0278] 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 glasses 214 will be referred to as the "terminal."

[0279] In a modern complex working environment, there is a need for efficient evaluation, cultivation, and improvement of employee engagement. The challenge is to collect information from various communication means, appropriately analyze and evaluate it, support the career paths of each individual, and improve the overall business efficiency of the organization.

[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following respective means.

[0281] In this invention, the server includes means for collecting communication information, performing preprocessing to prepare for language analysis, applying natural language processing to the preprocessed information to generate technical evaluation numerical values, and creating individual opinion exchange and training plans based on the generated technical evaluation numerical values. As a result, the personnel management within the organization is made more efficient, and it becomes possible to provide feedback and skill-upgrading opportunities suitable for individual employees.

[0282] "Communication information" refers to digital data related to business activities such as internal corporate emails, chat messages, document files, etc.

[0283] "Preprocessing" refers to a processing operation for deleting unnecessary information and unifying the data format before performing data analysis.

[0284] "Natural language processing" refers to computer technology for understanding and analyzing human language.

[0285] "Technical evaluation numerical value" is the evaluation result obtained by quantifying the capabilities and performance of employees.

[0286] "Opinion exchange" is an interactive information-providing process for providing feedback to employees based on the evaluation results.

[0287] "Training plan" is a training curriculum proposed by the organization for the purpose of improving the capabilities of employees.

[0288] "Job career options" are proposals that outline the future direction and growth opportunities for employees' careers.

[0289] "Employee engagement" refers to the degree of involvement and passion that employees have for their work and the organization.

[0290] An "information display device" is a device that visualizes and presents digital information to the user.

[0291] "Survey results" refer to data that presents opinions and new perspectives collected from employees.

[0292] This invention is a system for streamlining human resource management, aiming to improve employee evaluation, development, and engagement within a company. This system primarily consists of three elements: a server, terminals, and users.

[0293] The server automatically collects various communication information within the company using APIs. Specifically, this includes emails, chat messages, and document files. The collected information is preprocessed to remove unnecessary information and standardize data formats. Then, natural language processing technology is applied to analyze the data and generate technical evaluation scores for each employee.

[0294] The terminal visually displays technical evaluation values ​​received from the server on an information display device. Using the user interface, the evaluation values ​​are visualized as bar graphs and radar charts, providing feedback to the user. Furthermore, the user can access training plans to improve their skills based on this feedback and register for appropriate training courses.

[0295] Furthermore, the server suggests career path options based on each individual's skills, encouraging long-term growth. Users can review these suggestions via their devices and use them as a basis for considering their career paths.

[0296] As a concrete example, a generative AI model can be used to analyze the sentiment of emails, and if there is a lot of positive feedback, it can generate an evaluation that highlights that as a strength. Furthermore, as an example of a prompt, you can input something like, "Create personalized feedback and skill-building suggestions based on the contributions of our team members to the new project," and receive a response.

[0297] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0298] Step 1:

[0299] The server automatically collects various types of communication information within the company using an API. This includes emails, chat messages, and document files. The input is all communication data generated during a given period, and the goal is to extract this data and format it for analysis. In practice, the server periodically calls the API endpoint to retrieve the latest communication data.

[0300] Step 2:

[0301] The server preprocesses the collected raw data. This involves removing unnecessary information and standardizing the data format. The input is the data collected in step 1; for example, email headers are removed, and only the necessary text is extracted. The output is a clean and consistent dataset. In this process, the server removes line breaks and whitespace to ensure data integrity.

[0302] Step 3:

[0303] The server applies natural language processing technology to the preprocessed data for analysis. The input is the dataset after preprocessing, and a specific generative AI model is applied. The data operations performed here include text sentiment analysis and keyword extraction, etc. The server derives the technical evaluation numerical values for each employee as the analysis result. The output is a result set containing this numerical value.

[0304] Step 4:

[0305] Based on the generated technical evaluation numerical values, the server creates individual opinion exchanges and training plans. The input is the evaluation numerical value of each employee, and the server uses this to propose appropriate feedback and training plans. In actual operation, a training course for skills with low evaluation numerical values is selected. The output is a specific training program and feedback message.

[0306] Step 5:

[0307] The terminal visually displays the technical evaluation numerical values and feedback received from the server on an information display device. The input is the data sent from the server, and the terminal visualizes the information by displaying it as a bar graph or radar chart. The output is an explicit feedback display for the user.

[0308] Step 6:

[0309] The user selects and executes actions based on the provided feedback and training plan. The input is the information displayed on the terminal, and based on this, the user selects the path towards self-skill improvement. For example, registering for a specific training course. The output is the user's selection and subsequent actions.

[0310] (Application Example 1)

[0311] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0312] To achieve efficient management and operation of machinery and robots within a factory, it is necessary to collect and appropriately analyze the operational data of each device and robot. However, conventional methods rely heavily on human subjectivity, making it difficult to achieve optimal operation and maintenance. Furthermore, a lack of concrete improvement suggestions to enhance efficiency often leads to missed opportunities for increased productivity. There is a need to solve these problems and maximize the performance of machinery and robots.

[0313] 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.

[0314] In this invention, the server includes means for collecting communication information and performing preliminary processing to prepare for data analysis, means for applying natural language processing to the preliminary processed information to generate a numerical value for performance evaluation, and means for collecting and analyzing operating data of machinery and equipment, and generating and displaying an efficiency score. This makes it possible to objectively and efficiently evaluate the operating status of machinery and robots. Furthermore, by providing optimization suggestions and maintenance schedules tailored to the characteristics based on the generated efficiency score, it is possible to optimize the production process and improve the efficiency of maintenance.

[0315] "Communication information" refers to electronic data collected from machinery and robots used within a factory, including operation logs and operating status.

[0316] "Pre-processing" refers to the data organization and transformation work performed to make collected communication information easier to analyze, and includes data standardization and noise removal.

[0317] "Natural language processing" is a technology that uses computers to analyze human language, understand its meaning, and generate it. It is also used for summarizing and classifying the analysis results.

[0318] "Performance evaluation values" are performance indicators obtained by analyzing the motion data of machinery and robots, and represent a numerical representation of efficiency and precision.

[0319] "Operation data" refers to information that includes records of tasks performed by machinery or robots and their operation history; it's like an operation log.

[0320] The "efficiency score" is an index calculated based on collected motion data, and is used to evaluate the operating status and productivity of machinery and robots.

[0321] "Optimization proposals" refer to methods and strategies proposed to improve the operation of machinery and robots, encompassing a wide range of areas such as productivity improvement and energy efficiency.

[0322] A "maintenance schedule" refers to the schedule of inspections and maintenance work necessary to maintain the performance of machinery and robots, and is a plan for regular maintenance.

[0323] The system for implementing this invention effectively manages and optimizes the performance of machinery and robots within a factory. The server collects factory communication information via an API and performs preliminary processing to prepare for data analysis. This preliminary processing unifies the raw data and removes unnecessary information, enabling efficient subsequent data analysis.

[0324] The pre-processed information is analyzed using a natural language processing library to generate numerical performance evaluations for each machine and robot. This makes it possible to objectively understand work efficiency and accuracy. In addition, an efficiency score is calculated based on the operation data collected daily from the machines and displayed visually on a dashboard. This display uses heatmaps and graphs to allow factory operators to intuitively understand the status of each piece of equipment.

[0325] Furthermore, based on the generated efficiency score, the server suggests areas for optimization. These suggestions include methods for improving productivity and reducing energy consumption. The server also helps ensure that regular maintenance plans are implemented efficiently by automatically creating maintenance schedules for machinery and equipment and notifying operators.

[0326] This approach improves the operational efficiency of machinery and robots within the factory, enabling operators to achieve advanced operational management with minimal effort. Furthermore, by utilizing generative AI models, more accurate and practical optimization suggestions are provided. One example of a prompt is, "What improvements should be made to maximize the transport efficiency of this robot?"

[0327] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0328] Step 1:

[0329] The server collects communication information from various machines and robots within the factory via APIs. This communication information includes operation logs and sensor operation data. The server receives this raw data and stores it in a database. The input is raw communication information, and the output is an organized dataset.

[0330] Step 2:

[0331] The server preprocesses the collected data and converts it into an analyzable format. This process filters out unnecessary data and handles outliers and missing values, preparing the data for analysis. The input is raw communication information, and the preprocessed output yields a clean dataset.

[0332] Step 3:

[0333] The server applies natural language processing (NLP) techniques to pre-processed data to analyze operations and situations recorded in a text-like format. This generates numerical performance evaluations for each machine and robot. The input is a pre-processed dataset, and the output is a numerical performance evaluation.

[0334] Step 4:

[0335] The terminal calculates an efficiency score based on the performance evaluation data received from the server and displays it on the dashboard. This display uses heatmaps and line graphs to make it visually easy for operators to understand. The input is the performance evaluation data, and the output is a visualized efficiency score.

[0336] Step 5:

[0337] The server analyzes the efficiency score and generates optimization suggestions. These include improvements to work processes and energy efficiency. The use of a generating AI model enables highly accurate suggestions. An example of this prompt might be, "What improvements should be made to maximize the transport efficiency of this robot?" The input is the efficiency score, and the output is the optimization suggestion.

[0338] Step 6:

[0339] The server automatically generates maintenance schedules for machinery and equipment, creating plans for necessary inspections and maintenance. This allows operators to perform maintenance work efficiently and at the appropriate time. Inputs are historical operational data and efficiency scores, and output is the maintenance schedule.

[0340] 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.

[0341] The human resource management system of this invention utilizes AI technology to evaluate employee skills and improve employee engagement. This system has a configuration involving three elements: a server, a terminal, and a user, and is particularly characterized by the incorporation of an emotion engine for recognizing user emotions.

[0342] First, the server collects communication data from within the company network, preprocesses it, and then applies natural language processing techniques to analyze the text data. During this process, it utilizes an emotion engine to detect the emotional tone contained in the communication data. For example, it can be used to assess employee stress levels and satisfaction levels from emails and chats.

[0343] Next, the server generates a skill evaluation score based on the analysis data. This score also incorporates data from the emotion engine, allowing for a more precise assessment of employee capabilities. Furthermore, personalized feedback and training programs are created based on the emotion analysis results. The terminal displays the generated feedback and skill evaluation score on a dashboard, making it easy for employees (users) to view.

[0344] By using an emotion engine, career path suggestions become even more personalized. The server considers the employee's emotional state and job interests to suggest the most suitable career options. In this way, users can gain a more concrete vision of their own growth.

[0345] This system also excels from the perspective of employee engagement evaluation. The server regularly collects and analyzes employee feedback and survey data. During this process, it uses an emotion engine to analyze the emotional aspects of the responses and generate more targeted improvement suggestions. The terminal then presents these suggestions to the user in a timely manner, contributing to improved organizational morale.

[0346] A concrete example is when an employee, as a user, receives a warning about their stress level on the dashboard and is introduced to a stress reduction program tailored to their needs. This allows the employee to receive the necessary support and improve their performance.

[0347] The present invention aims to achieve fair and efficient human resource management through these steps, thereby improving employee growth and well-being within the company.

[0348] The following describes the processing flow.

[0349] Step 1:

[0350] The server automatically collects communication data from the company's internal email server and chat application logs. This is done using an API connection and is configured to be updated at regular intervals.

[0351] Step 2:

[0352] The server performs preprocessing on the collected communication data. Specifically, this includes tasks such as denoising text, tokenization, and normalization, converting the data into a format that is easy to analyze at this stage.

[0353] Step 3:

[0354] The server applies natural language processing to the preprocessed data and performs text analysis. This analysis includes key phrase extraction, sentiment analysis, and evaluation of emotional tone using a sentiment engine.

[0355] Step 4:

[0356] The server calculates a skill evaluation score for each employee based on the results obtained from natural language processing. In addition, emotional data obtained from the emotion engine is also incorporated into the score.

[0357] Step 5:

[0358] The device visually displays each employee's skill assessment score and sentiment analysis results on a dashboard. The displayed information includes the employee's work strengths, areas for improvement, and emotional tendencies.

[0359] Step 6:

[0360] The server automatically generates individually optimized feedback and training programs based on evaluation scores and sentiment data.

[0361] Step 7:

[0362] The terminal provides users with generated training programs and feedback content via a dashboard. Employees can refer to this and select recommended training courses.

[0363] Step 8:

[0364] The server automatically suggests appropriate career path options based on employee sentiment data and performance scores. These suggestions are based on job suitability and interests.

[0365] Step 9:

[0366] The device displays career path suggestions on a dashboard, providing a foundation for users to select one and pursue their own professional development.

[0367] Step 10:

[0368] The server periodically collects feedback and engagement surveys from employees and analyzes them using an emotion engine. This allows it to generate feedback that takes into account strategies for improving engagement.

[0369] Step 11:

[0370] The device provides employees with engagement-based feedback and offers them the opportunity to use it as a suggestion for organizational improvement.

[0371] Step 12:

[0372] Users can leverage the provided information and support programs to improve their personal performance and job satisfaction.

[0373] (Example 2)

[0374] 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".

[0375] The challenge lies in promoting individual growth and improving engagement through accurate assessment of employees' skills and psychological states. Traditional methods fail to adequately consider emotional aspects, making it difficult to provide personalized feedback and career path suggestions.

[0376] 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.

[0377] In this invention, the server includes means for collecting communication information and preprocessing it to prepare it for text analysis; means for applying natural language processing to the preprocessed information, performing sentiment analysis, and generating skill evaluation indicators; and means for creating individualized feedback and educational programs based on the generated skill evaluation indicators and sentiment data. This makes it possible to comprehensively evaluate an individual's abilities and emotional state and provide personalized support.

[0378] "Communication information" refers to messages and data sent over a network, including email, chat messages, and voice data.

[0379] "Preprocessing" refers to the initial stage of processing raw data into a format that is easy to analyze, and includes processes such as format standardization, noise reduction, and anonymization.

[0380] "Natural language processing" refers to technologies that enable machines to understand and analyze human language, including techniques for part-of-speech analysis and semantic analysis of text data.

[0381] "Emotion analysis" refers to a technology that extracts emotions and emotional tones from text and audio data to determine specific emotions.

[0382] A "skill evaluation index" is a way of expressing an individual's abilities and skills using numerical values ​​or indicators, and serves as a standard used when evaluating abilities.

[0383] "Feedback" refers to the act of providing evaluations and opinions on specific activities or performances, and offering information to encourage improvement and enhancement.

[0384] An "educational program" refers to a series of learning activities and training designed to improve an individual's skills and knowledge.

[0385] "Career path options" refers to presenting various possible paths for an individual's career growth and future professional advancement, and suggesting the most suitable career route.

[0386] "Engagement" refers to the degree of proactiveness and commitment an individual shows towards an organization or its activities, and is particularly related to employee job satisfaction and sense of participation.

[0387] This invention aims to improve the efficiency of human resource management by utilizing communication information, and is implemented using a system mainly composed of a server, terminal, and user. Specifically, the server collects communication information such as communication messages and chat data, and performs preprocessing such as standardizing the data format and anonymizing it. This makes the data suitable for analysis.

[0388] The server applies natural language processing techniques to pre-processed information to analyze the emotions contained in the text. A natural language processing engine is used for emotion analysis, for example, analyzing expressions like "I'm busy and stressed" to determine the associated emotional tone. This process allows for an understanding of each user's psychological state.

[0389] Based on the analysis results, the server generates skill evaluation metrics and suggests feedback and training programs optimized for the user. For example, if the analysis results indicate that "employees have high stress levels," a stress management training program might be recommended.

[0390] The generated feedback and skill evaluation scores are provided to the user through the device. The device has a dashboard function and is designed to display information visually, making it easier for the user to understand their own status and take steps to improve.

[0391] For example, a user can send a query to the system using the prompt, "Please tell me my current stress level and how to improve it." This allows them to receive immediate support and advice tailored to their individual situation.

[0392] This invention supports individual growth and well-being within an organization and contributes to improved employee engagement.

[0393] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0394] Step 1:

[0395] The server collects communication information transmitted over the network. Input includes emails and chat messages. The server then preprocesses this data by removing personally identifiable information and standardizing the data format. The output is anonymized data that is easy to analyze.

[0396] Step 2:

[0397] The server applies natural language processing (NLP) techniques to preprocessed data. The input is preprocessed text data. The server performs morphological analysis to extract the structure and meaning of the text. Sentiment analysis is also performed in parallel. The output is structured text data with identified emotional tones.

[0398] Step 3:

[0399] The server generates skill evaluation metrics based on the analysis results. The input is emotion analysis and NLP results, which evaluate the user's skills and emotional stability. The server performs calculations to represent this numerically and graphically. The output provides evaluation metrics regarding the user's skills and emotional state.

[0400] Step 4:

[0401] The server creates personalized feedback and training programs based on the generated skill assessment metrics and sentiment data. The input is individual user assessment data. The server generates recommendations to improve the user's specific challenges. The output includes a feedback report and a proposed training program.

[0402] Step 5:

[0403] The terminal receives feedback and evaluation metrics from the server and displays them on the dashboard. Inputs are reports and scores sent from the server. The terminal converts these into a user-friendly graphical format for visualization. Outputs are evaluation information viewable by the user.

[0404] Step 6:

[0405] Users can view their feedback and performance metrics through a dashboard. Users can input prompts into the system, such as "Please tell me how to improve my stress levels." As output, users can receive specific advice and guidance from the system.

[0406] (Application Example 2)

[0407] 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."

[0408] In today's living environment, there is a need to accurately understand the stress and emotional state of individual users and to provide appropriate support promptly. Furthermore, conventional technologies are limited to standard methods for assessing users' abilities and proposing career paths, making it difficult to provide individually optimized suggestions based on each user's characteristics and emotional changes. Therefore, the present invention aims to solve these problems and provide personalized feedback and career path suggestions while promoting stress reduction for users.

[0409] 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.

[0410] In this invention, the server includes means for collecting communication data and preprocessing it to prepare it for text analysis; means for applying natural language processing to the preprocessed data to generate a skill evaluation score; means for creating individual feedback and a skill improvement plan based on the generated skill evaluation score; means for automatically suggesting career path options based on the individual's abilities; and means for analyzing the user's emotional state and making specific suggestions to promote stress reduction based on that analysis. This enables the user to receive optimal feedback and options that take their emotional state into consideration, helping to reduce stress in daily life and promote self-growth.

[0411] "Communication data" refers to all information transmitted and received over a network, and includes various formats such as text, audio, and images.

[0412] "Preprocessing" refers to the processes performed prior to data analysis, including data cleansing and formatting standardization, as preparatory work to improve analysis efficiency.

[0413] Natural language processing is a technology that enables computers to understand, generate, and respond to human language, and is widely used in the analysis of text and audio data.

[0414] A "skill evaluation score" is a numerical assessment of a user's abilities and skills, and is used as a guideline for occupational aptitude and skill development.

[0415] "Feedback" is the process of providing opinions and reactions regarding specific actions or results, offering information to encourage improvement and motivation.

[0416] A "skills improvement plan" is a plan that an individual formulates to improve their own abilities, and it sets out specific goals and means.

[0417] "Career path options" refer to the diverse paths that users can take in their professional lives, and are proposed based on their individual abilities and interests.

[0418] "Emotional state" refers to the overall emotional state an individual is experiencing at a particular point in time, and it fluctuates based on subjective experience.

[0419] "Stress reduction" refers to alleviating the psychological or physical burden an individual is experiencing, and relaxation techniques and a suitable environment are the means to achieve this.

[0420] In this invention, a server plays a central role in collecting and preprocessing communication data. The server performs data cleansing to remove unnecessary parts from the information and convert it into a unified format. Subsequently, natural language processing is applied to generate skill evaluation scores. This process utilizes a natural language processing framework to analyze the meaning from text data and perform numerical evaluations.

[0421] On the user's device, the generated skill assessment score is visually displayed through a dashboard. This allows users to intuitively understand their abilities and aptitudes. Furthermore, the server uses an emotion engine to analyze the user's emotional state and provide optimal suggestions to promote stress reduction. This function recommends appropriate actions based on the user's current psychological state.

[0422] For example, if the server determines that a user needs to relax after a busy day at home, the device can suggest relaxation music. A key feature of this suggestion is that it is customized based on the user's past preferences and current emotional state.

[0423] Regarding generative AI models, an example of a prompt would be: "Explain how a home robot can analyze family voice data, recognize their emotional state, and provide specific suggestions to reduce stress."

[0424] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0425] Step 1:

[0426] The server receives audio data from within the home as communication data and preprocesses this data as input. Specifically, it uses speech recognition technology to remove noise and convert the audio signal into text. The output of this processing is clean text data suitable for analysis.

[0427] Step 2:

[0428] The server applies natural language processing to the pre-processed text data. This involves contextual analysis, topic recognition, and evaluation of the emotional tone of the conversation. The input to this analysis is the text data obtained in the previous step, and the output is data on individual emotional states and emotional tones.

[0429] Step 3:

[0430] The server uses an emotion engine to analyze the user's emotional state. Specifically, it analyzes the output data from the previous step to calculate the user's stress level and current emotional tendencies. The input is emotional tone data, and the output is a quantified evaluation value of the emotional state.

[0431] Step 4:

[0432] The device receives emotional state assessment values ​​and, based on that data, visually displays optimal relaxation suggestions for the user on a dashboard. These suggestions include music types and relaxation exercises. The output is a visual suggestion interface displayed on the device.

[0433] Step 5:

[0434] The user selects a suggestion presented by the device and initiates a specific action. For example, they might play suggested music or start a recommended exercise to reduce stress. The input in this step is the user's choice, and the output is the initiation of physical relaxation.

[0435] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0436] 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.

[0437] 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.

[0438] [Third Embodiment]

[0439] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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".

[0451] The human resource management system of this invention efficiently evaluates and develops employees by combining AI technology and natural language processing. This system is primarily operated by three entities: a server, terminals, and users.

[0452] Data collection and analysis

[0453] The server automatically collects internal communication data via APIs. Examples of collected data include emails, chat logs, and business reports.

[0454] The server preprocesses the collected data and then performs text analysis using natural language processing techniques. This analysis extracts the information necessary for evaluating employee skills.

[0455] Skill assessment and feedback

[0456] The server generates a skill evaluation score for each employee based on the analysis results. This score quantifies each employee's strengths and areas for improvement in their work.

[0457] The device provides individual employee feedback through a visual dashboard, which includes information such as praise and suggestions for improvement.

[0458] Training program and career path proposals

[0459] The server automatically generates personalized training programs based on each employee's performance score, providing each employee with opportunities for skill development tailored to their individual needs.

[0460] The server further proposes potential career paths to promote employees' long-term growth. These proposals are made taking into account the employee's abilities and interests.

[0461] Engagement evaluation and improvement

[0462] The server regularly collects feedback and engagement surveys from employees and analyzes the results to generate feedback that improves engagement across the entire organization.

[0463] For example, the feedback that employees receive includes evaluations of their contributions to recent projects and their ability to collaborate with colleagues. Furthermore, the dashboard displayed on the device allows for one-click enrollment in training courses tailored to their skills. This enables organizations to support the growth of each employee while achieving fair and efficient talent management.

[0464] The following describes the processing flow.

[0465] Step 1:

[0466] The server periodically collects communication data from data sources connected to the company's internal network. This includes logs from the company's email server and chat applications.

[0467] Step 2:

[0468] The server preprocesses the collected data, performing noise reduction and text normalization. This process prepares the data for text analysis.

[0469] Step 3:

[0470] The server analyzes the data, which has been preprocessed using natural language processing. Here, techniques such as key phrase extraction and sentiment analysis are used to extract information for evaluating employees' skills and work attitudes.

[0471] Step 4:

[0472] The server generates a skills evaluation score for each employee based on the analysis results. This score quantifies the employee's abilities and records them numerically.

[0473] Step 5:

[0474] The device updates a dashboard to provide feedback to employees based on the generated skill assessment scores. The feedback highlights their strengths and areas for improvement in their work.

[0475] Step 6:

[0476] Based on evaluation scores, the server selects training programs suitable for employees and automatically creates personalized career development plans.

[0477] Step 7:

[0478] The terminal displays training program information on a dashboard, making it easily accessible to employee users.

[0479] Step 8:

[0480] Users can review their skill assessment and training program, and voluntarily take recommended courses as needed.

[0481] Step 9:

[0482] The server regularly collects and analyzes employee feedback and engagement surveys, and generates feedback to improve engagement within the company.

[0483] Step 10:

[0484] Users can receive the results of their engagement evaluations and use them to improve their activities within the organization.

[0485] (Example 1)

[0486] 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."

[0487] In today's complex work environment, there is a need for efficient evaluation and development of talent, as well as improved engagement. The challenge lies in collecting information from diverse communication channels, appropriately analyzing and evaluating it, supporting each individual's career path, and improving the overall operational efficiency of the organization.

[0488] 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.

[0489] In this invention, the server includes means for collecting communication information and preprocessing it to prepare it for language analysis; means for applying natural language processing to the preprocessed information to generate technical evaluation values; and means for creating individual opinion exchange and training plans based on the generated technical evaluation values. This makes it possible to streamline human resource management within the organization and provide individualized feedback and skill development opportunities for each employee.

[0490] "Communication information" refers to digital data related to business activities, such as emails, chat messages, and document files within a company.

[0491] "Preprocessing" refers to the data processing steps taken before data analysis to remove unnecessary information and standardize the data format.

[0492] "Natural language processing" refers to computer technology used to understand and analyze human language.

[0493] "Technical evaluation scores" refer to the results of an evaluation that quantifies an employee's abilities and performance.

[0494] "Opinion exchange" is an interactive information provision process for providing feedback to employees based on evaluation results.

[0495] A "training plan" is a training curriculum proposed by an organization to improve the skills of its employees.

[0496] "Job career options" are proposals that outline the future direction and growth opportunities for employees' careers.

[0497] "Employee engagement" refers to the degree of involvement and passion that employees have for their work and the organization.

[0498] An "information display device" is a device that visualizes and presents digital information to the user.

[0499] "Survey results" refer to data that presents opinions and new perspectives collected from employees.

[0500] This invention is a system for streamlining human resource management, aiming to improve employee evaluation, development, and engagement within a company. This system primarily consists of three elements: a server, terminals, and users.

[0501] The server automatically collects various communication information within the company using APIs. Specifically, this includes emails, chat messages, and document files. The collected information is preprocessed to remove unnecessary information and standardize data formats. Then, natural language processing technology is applied to analyze the data and generate technical evaluation scores for each employee.

[0502] The terminal visually displays technical evaluation values ​​received from the server on an information display device. Using the user interface, the evaluation values ​​are visualized as bar graphs and radar charts, providing feedback to the user. Furthermore, the user can access training plans to improve their skills based on this feedback and register for appropriate training courses.

[0503] Furthermore, the server suggests career path options based on each individual's skills, encouraging long-term growth. Users can review these suggestions via their devices and use them as a basis for considering their career paths.

[0504] As a concrete example, a generative AI model can be used to analyze the sentiment of emails, and if there is a lot of positive feedback, it can generate an evaluation that highlights that as a strength. Furthermore, as an example of a prompt, you can input something like, "Create personalized feedback and skill-building suggestions based on the contributions of our team members to the new project," and receive a response.

[0505] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0506] Step 1:

[0507] The server automatically collects various types of communication information within the company using an API. This includes emails, chat messages, and document files. The input is all communication data generated during a given period, and the goal is to extract this data and format it for analysis. In practice, the server periodically calls the API endpoint to retrieve the latest communication data.

[0508] Step 2:

[0509] The server preprocesses the collected raw data. This involves removing unnecessary information and standardizing the data format. The input is the data collected in step 1; for example, email headers are removed, and only the necessary text is extracted. The output is a clean and consistent dataset. In this process, the server removes line breaks and whitespace to ensure data integrity.

[0510] Step 3:

[0511] The server performs analysis by applying natural language processing techniques to pre-processed data. The input is the pre-processed dataset to which a specific generative AI model is applied. The data calculations performed here include text sentiment analysis and keyword extraction. The server derives a technical evaluation score for each employee as an analysis result. The output is a result set containing these scores.

[0512] Step 4:

[0513] The server creates individual feedback and training plans based on the generated technical evaluation scores. The input is each employee's evaluation score, which the server uses to propose appropriate feedback and training plans. In actual operation, training courses are selected for skills with low evaluation scores. The output consists of specific training programs and feedback messages.

[0514] Step 5:

[0515] The terminal visually displays technical evaluation figures and feedback received from the server on an information display device. The input is data sent from the server, and the terminal visualizes this information by displaying it as bar graphs or radar charts. The output is an explicit feedback display for the user.

[0516] Step 6:

[0517] Users select and execute actions based on the feedback and training plan provided. The input is the information displayed on the device, which the user uses to choose a path for skill development. For example, they might register for a specific training course. The output is the user's selection and subsequent actions.

[0518] (Application Example 1)

[0519] 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."

[0520] To achieve efficient management and operation of machinery and robots within a factory, it is necessary to collect and appropriately analyze the operational data of each device and robot. However, conventional methods rely heavily on human subjectivity, making it difficult to achieve optimal operation and maintenance. Furthermore, a lack of concrete improvement suggestions to enhance efficiency often leads to missed opportunities for increased productivity. There is a need to solve these problems and maximize the performance of machinery and robots.

[0521] 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.

[0522] In this invention, the server includes means for collecting communication information and performing preliminary processing to prepare for data analysis, means for applying natural language processing to the preliminary processed information to generate a numerical value for performance evaluation, and means for collecting and analyzing operating data of machinery and equipment, and generating and displaying an efficiency score. This makes it possible to objectively and efficiently evaluate the operating status of machinery and robots. Furthermore, by providing optimization suggestions and maintenance schedules tailored to the characteristics based on the generated efficiency score, it is possible to optimize the production process and improve the efficiency of maintenance.

[0523] "Communication information" refers to electronic data collected from machinery and robots used within a factory, including operation logs and operating status.

[0524] "Pre-processing" refers to the data organization and transformation work performed to make collected communication information easier to analyze, and includes data standardization and noise removal.

[0525] "Natural language processing" is a technology that uses computers to analyze human language, understand its meaning, and generate it. It is also used for summarizing and classifying the analysis results.

[0526] "Performance evaluation values" are performance indicators obtained by analyzing the motion data of machinery and robots, and represent a numerical representation of efficiency and precision.

[0527] "Operation data" refers to information that includes records of tasks performed by machinery or robots and their operation history; it's like an operation log.

[0528] The "efficiency score" is an index calculated based on collected motion data, and is used to evaluate the operating status and productivity of machinery and robots.

[0529] "Optimization proposals" refer to methods and strategies proposed to improve the operation of machinery and robots, encompassing a wide range of areas such as productivity improvement and energy efficiency.

[0530] A "maintenance schedule" refers to the schedule of inspections and maintenance work necessary to maintain the performance of machinery and robots, and is a plan for regular maintenance.

[0531] The system for implementing this invention effectively manages and optimizes the performance of machinery and robots within a factory. The server collects factory communication information via an API and performs preliminary processing to prepare for data analysis. This preliminary processing unifies the raw data and removes unnecessary information, enabling efficient subsequent data analysis.

[0532] The pre-processed information is analyzed using a natural language processing library to generate numerical performance evaluations for each machine and robot. This makes it possible to objectively understand work efficiency and accuracy. In addition, an efficiency score is calculated based on the operation data collected daily from the machines and displayed visually on a dashboard. This display uses heatmaps and graphs to allow factory operators to intuitively understand the status of each piece of equipment.

[0533] Furthermore, based on the generated efficiency score, the server suggests areas for optimization. These suggestions include methods for improving productivity and reducing energy consumption. The server also helps ensure that regular maintenance plans are implemented efficiently by automatically creating maintenance schedules for machinery and equipment and notifying operators.

[0534] This approach improves the operational efficiency of machinery and robots within the factory, enabling operators to achieve advanced operational management with minimal effort. Furthermore, by utilizing generative AI models, more accurate and practical optimization suggestions are provided. One example of a prompt is, "What improvements should be made to maximize the transport efficiency of this robot?"

[0535] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0536] Step 1:

[0537] The server collects communication information from various machines and robots within the factory via APIs. This communication information includes operation logs and sensor operation data. The server receives this raw data and stores it in a database. The input is raw communication information, and the output is an organized dataset.

[0538] Step 2:

[0539] The server preprocesses the collected data and converts it into an analyzable format. This process filters out unnecessary data and handles outliers and missing values, preparing the data for analysis. The input is raw communication information, and the preprocessed output yields a clean dataset.

[0540] Step 3:

[0541] The server applies natural language processing (NLP) techniques to pre-processed data to analyze operations and situations recorded in a text-like format. This generates numerical performance evaluations for each machine and robot. The input is a pre-processed dataset, and the output is a numerical performance evaluation.

[0542] Step 4:

[0543] The terminal calculates an efficiency score based on the performance evaluation data received from the server and displays it on the dashboard. This display uses heatmaps and line graphs to make it visually easy for operators to understand. The input is the performance evaluation data, and the output is a visualized efficiency score.

[0544] Step 5:

[0545] The server analyzes the efficiency score and generates optimization suggestions. These include improvements to work processes and energy efficiency. The use of a generating AI model enables highly accurate suggestions. An example of this prompt might be, "What improvements should be made to maximize the transport efficiency of this robot?" The input is the efficiency score, and the output is the optimization suggestion.

[0546] Step 6:

[0547] The server automatically generates maintenance schedules for machinery and equipment, creating plans for necessary inspections and maintenance. This allows operators to perform maintenance work efficiently and at the appropriate time. Inputs are historical operational data and efficiency scores, and output is the maintenance schedule.

[0548] 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.

[0549] The human resource management system of this invention utilizes AI technology to evaluate employee skills and improve employee engagement. This system has a configuration involving three elements: a server, a terminal, and a user, and is particularly characterized by the incorporation of an emotion engine for recognizing user emotions.

[0550] First, the server collects communication data from within the company network, preprocesses it, and then applies natural language processing techniques to analyze the text data. During this process, it utilizes an emotion engine to detect the emotional tone contained in the communication data. For example, it can be used to assess employee stress levels and satisfaction levels from emails and chats.

[0551] Next, the server generates a skill evaluation score based on the analysis data. This score also incorporates data from the emotion engine, allowing for a more precise assessment of employee capabilities. Furthermore, personalized feedback and training programs are created based on the emotion analysis results. The terminal displays the generated feedback and skill evaluation score on a dashboard, making it easy for employees (users) to view.

[0552] By using an emotion engine, career path suggestions become even more personalized. The server considers the employee's emotional state and job interests to suggest the most suitable career options. In this way, users can gain a more concrete vision of their own growth.

[0553] This system also excels from the perspective of employee engagement evaluation. The server regularly collects and analyzes employee feedback and survey data. During this process, it uses an emotion engine to analyze the emotional aspects of the responses and generate more targeted improvement suggestions. The terminal then presents these suggestions to the user in a timely manner, contributing to improved organizational morale.

[0554] A concrete example is when an employee, as a user, receives a warning about their stress level on the dashboard and is introduced to a stress reduction program tailored to their needs. This allows the employee to receive the necessary support and improve their performance.

[0555] The present invention aims to achieve fair and efficient human resource management through these steps, thereby improving employee growth and well-being within the company.

[0556] The following describes the processing flow.

[0557] Step 1:

[0558] The server automatically collects communication data from the company's internal email server and chat application logs. This is done using an API connection and is configured to be updated at regular intervals.

[0559] Step 2:

[0560] The server performs preprocessing on the collected communication data. Specifically, this includes tasks such as denoising text, tokenization, and normalization, converting the data into a format that is easy to analyze at this stage.

[0561] Step 3:

[0562] The server applies natural language processing to the preprocessed data and performs text analysis. This analysis includes key phrase extraction, sentiment analysis, and evaluation of emotional tone using a sentiment engine.

[0563] Step 4:

[0564] The server calculates a skill evaluation score for each employee based on the results obtained from natural language processing. In addition, emotional data obtained from the emotion engine is also incorporated into the score.

[0565] Step 5:

[0566] The device visually displays each employee's skill assessment score and sentiment analysis results on a dashboard. The displayed information includes the employee's work strengths, areas for improvement, and emotional tendencies.

[0567] Step 6:

[0568] The server automatically generates individually optimized feedback and training programs based on evaluation scores and sentiment data.

[0569] Step 7:

[0570] The terminal provides users with generated training programs and feedback content via a dashboard. Employees can refer to this and select recommended training courses.

[0571] Step 8:

[0572] The server automatically suggests appropriate career path options based on employee sentiment data and performance scores. These suggestions are based on job suitability and interests.

[0573] Step 9:

[0574] The device displays career path suggestions on a dashboard, providing a foundation for users to select one and pursue their own professional development.

[0575] Step 10:

[0576] The server periodically collects feedback and engagement surveys from employees and analyzes them using an emotion engine. This allows it to generate feedback that takes into account strategies for improving engagement.

[0577] Step 11:

[0578] The device provides employees with engagement-based feedback and offers them the opportunity to use it as a suggestion for organizational improvement.

[0579] Step 12:

[0580] Users can leverage the provided information and support programs to improve their personal performance and job satisfaction.

[0581] (Example 2)

[0582] 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."

[0583] The challenge lies in promoting individual growth and improving engagement through accurate assessment of employees' skills and psychological states. Traditional methods fail to adequately consider emotional aspects, making it difficult to provide personalized feedback and career path suggestions.

[0584] 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.

[0585] In this invention, the server includes means for collecting communication information and preprocessing it to prepare it for text analysis; means for applying natural language processing to the preprocessed information, performing sentiment analysis, and generating skill evaluation indicators; and means for creating individualized feedback and educational programs based on the generated skill evaluation indicators and sentiment data. This makes it possible to comprehensively evaluate an individual's abilities and emotional state and provide personalized support.

[0586] "Communication information" refers to messages and data sent over a network, including email, chat messages, and voice data.

[0587] "Preprocessing" refers to the initial stage of processing raw data into a format that is easy to analyze, and includes processes such as format standardization, noise reduction, and anonymization.

[0588] "Natural language processing" refers to technologies that enable machines to understand and analyze human language, including techniques for part-of-speech analysis and semantic analysis of text data.

[0589] "Emotion analysis" refers to a technology that extracts emotions and emotional tones from text and audio data to determine specific emotions.

[0590] A "skill evaluation index" is a way of expressing an individual's abilities and skills using numerical values ​​or indicators, and serves as a standard used when evaluating abilities.

[0591] "Feedback" refers to the act of providing evaluations and opinions on specific activities or performances, and offering information to encourage improvement and enhancement.

[0592] An "educational program" refers to a series of learning activities and training designed to improve an individual's skills and knowledge.

[0593] "Career path options" refers to presenting various possible paths for an individual's career growth and future professional advancement, and suggesting the most suitable career route.

[0594] "Engagement" refers to the degree of proactiveness and commitment an individual shows towards an organization or its activities, and is particularly related to employee job satisfaction and sense of participation.

[0595] This invention aims to improve the efficiency of human resource management by utilizing communication information, and is implemented using a system mainly composed of a server, terminal, and user. Specifically, the server collects communication information such as communication messages and chat data, and performs preprocessing such as standardizing the data format and anonymizing it. This makes the data suitable for analysis.

[0596] The server applies natural language processing techniques to pre-processed information to analyze the emotions contained in the text. A natural language processing engine is used for emotion analysis, for example, analyzing expressions like "I'm busy and stressed" to determine the associated emotional tone. This process allows for an understanding of each user's psychological state.

[0597] Based on the analysis results, the server generates skill evaluation metrics and suggests feedback and training programs optimized for the user. For example, if the analysis results indicate that "employees have high stress levels," a stress management training program might be recommended.

[0598] The generated feedback and skill evaluation scores are provided to the user through the device. The device has a dashboard function and is designed to display information visually, making it easier for the user to understand their own status and take steps to improve.

[0599] For example, a user can send a query to the system using the prompt, "Please tell me my current stress level and how to improve it." This allows them to receive immediate support and advice tailored to their individual situation.

[0600] This invention supports individual growth and well-being within an organization and contributes to improved employee engagement.

[0601] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0602] Step 1:

[0603] The server collects communication information transmitted over the network. Input includes emails and chat messages. The server then preprocesses this data by removing personally identifiable information and standardizing the data format. The output is anonymized data that is easy to analyze.

[0604] Step 2:

[0605] The server applies natural language processing (NLP) techniques to preprocessed data. The input is preprocessed text data. The server performs morphological analysis to extract the structure and meaning of the text. Sentiment analysis is also performed in parallel. The output is structured text data with identified emotional tones.

[0606] Step 3:

[0607] The server generates skill evaluation metrics based on the analysis results. The input is emotion analysis and NLP results, which evaluate the user's skills and emotional stability. The server performs calculations to represent this numerically and graphically. The output provides evaluation metrics regarding the user's skills and emotional state.

[0608] Step 4:

[0609] The server creates personalized feedback and training programs based on the generated skill assessment metrics and sentiment data. The input is individual user assessment data. The server generates recommendations to improve the user's specific challenges. The output includes a feedback report and a proposed training program.

[0610] Step 5:

[0611] The terminal receives feedback and evaluation metrics from the server and displays them on the dashboard. Inputs are reports and scores sent from the server. The terminal converts these into a user-friendly graphical format for visualization. Outputs are evaluation information viewable by the user.

[0612] Step 6:

[0613] Users can view their feedback and performance metrics through a dashboard. Users can input prompts into the system, such as "Please tell me how to improve my stress levels." As output, users can receive specific advice and guidance from the system.

[0614] (Application Example 2)

[0615] 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."

[0616] In today's living environment, there is a need to accurately understand the stress and emotional state of individual users and to provide appropriate support promptly. Furthermore, conventional technologies are limited to standard methods for assessing users' abilities and proposing career paths, making it difficult to provide individually optimized suggestions based on each user's characteristics and emotional changes. Therefore, the present invention aims to solve these problems and provide personalized feedback and career path suggestions while promoting stress reduction for users.

[0617] 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.

[0618] In this invention, the server includes means for collecting communication data and preprocessing it to prepare it for text analysis; means for applying natural language processing to the preprocessed data to generate a skill evaluation score; means for creating individual feedback and a skill improvement plan based on the generated skill evaluation score; means for automatically suggesting career path options based on the individual's abilities; and means for analyzing the user's emotional state and making specific suggestions to promote stress reduction based on that analysis. This enables the user to receive optimal feedback and options that take their emotional state into consideration, helping to reduce stress in daily life and promote self-growth.

[0619] "Communication data" refers to all information transmitted and received over a network, and includes various formats such as text, audio, and images.

[0620] "Preprocessing" refers to the processes performed prior to data analysis, including data cleansing and formatting standardization, as preparatory work to improve analysis efficiency.

[0621] Natural language processing is a technology that enables computers to understand, generate, and respond to human language, and is widely used in the analysis of text and audio data.

[0622] A "skill evaluation score" is a numerical assessment of a user's abilities and skills, and is used as a guideline for occupational aptitude and skill development.

[0623] "Feedback" is the process of providing opinions and reactions regarding specific actions or results, offering information to encourage improvement and motivation.

[0624] A "skills improvement plan" is a plan that an individual formulates to improve their own abilities, and it sets out specific goals and means.

[0625] "Career path options" refer to the diverse paths that users can take in their professional lives, and are proposed based on their individual abilities and interests.

[0626] "Emotional state" refers to the overall emotional state an individual is experiencing at a particular point in time, and it fluctuates based on subjective experience.

[0627] "Stress reduction" refers to alleviating the psychological or physical burden an individual is experiencing, and relaxation techniques and a suitable environment are the means to achieve this.

[0628] In this invention, a server plays a central role in collecting and preprocessing communication data. The server performs data cleansing to remove unnecessary parts from the information and convert it into a unified format. Subsequently, natural language processing is applied to generate skill evaluation scores. This process utilizes a natural language processing framework to analyze the meaning from text data and perform numerical evaluations.

[0629] On the user's device, the generated skill assessment score is visually displayed through a dashboard. This allows users to intuitively understand their abilities and aptitudes. Furthermore, the server uses an emotion engine to analyze the user's emotional state and provide optimal suggestions to promote stress reduction. This function recommends appropriate actions based on the user's current psychological state.

[0630] For example, if the server determines that a user needs to relax after a busy day at home, the device can suggest relaxation music. A key feature of this suggestion is that it is customized based on the user's past preferences and current emotional state.

[0631] Regarding generative AI models, an example of a prompt would be: "Explain how a home robot can analyze family voice data, recognize their emotional state, and provide specific suggestions to reduce stress."

[0632] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0633] Step 1:

[0634] The server receives audio data from within the home as communication data and preprocesses this data as input. Specifically, it uses speech recognition technology to remove noise and convert the audio signal into text. The output of this processing is clean text data suitable for analysis.

[0635] Step 2:

[0636] The server applies natural language processing to the pre-processed text data. This involves contextual analysis, topic recognition, and evaluation of the emotional tone of the conversation. The input to this analysis is the text data obtained in the previous step, and the output is data on individual emotional states and emotional tones.

[0637] Step 3:

[0638] The server uses an emotion engine to analyze the user's emotional state. Specifically, it analyzes the output data from the previous step to calculate the user's stress level and current emotional tendencies. The input is emotional tone data, and the output is a quantified evaluation value of the emotional state.

[0639] Step 4:

[0640] The device receives emotional state assessment values ​​and, based on that data, visually displays optimal relaxation suggestions for the user on a dashboard. These suggestions include music types and relaxation exercises. The output is a visual suggestion interface displayed on the device.

[0641] Step 5:

[0642] The user selects a suggestion presented by the device and initiates a specific action. For example, they might play suggested music or start a recommended exercise to reduce stress. The input in this step is the user's choice, and the output is the initiation of physical relaxation.

[0643] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0644] 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.

[0645] 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.

[0646] [Fourth Embodiment]

[0647] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0648] 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.

[0649] 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).

[0650] 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.

[0651] 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.

[0652] 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).

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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".

[0660] The human resource management system of this invention efficiently evaluates and develops employees by combining AI technology and natural language processing. This system is primarily operated by three entities: a server, terminals, and users.

[0661] Data collection and analysis

[0662] The server automatically collects internal communication data via APIs. Examples of collected data include emails, chat logs, and business reports.

[0663] The server preprocesses the collected data and then performs text analysis using natural language processing techniques. This analysis extracts the information necessary for evaluating employee skills.

[0664] Skill assessment and feedback

[0665] The server generates a skill evaluation score for each employee based on the analysis results. This score quantifies each employee's strengths and areas for improvement in their work.

[0666] The device provides individual employee feedback through a visual dashboard, which includes information such as praise and suggestions for improvement.

[0667] Training program and career path proposals

[0668] The server automatically generates personalized training programs based on each employee's performance score, providing each employee with opportunities for skill development tailored to their individual needs.

[0669] The server further proposes potential career paths to promote employees' long-term growth. These proposals are made taking into account the employee's abilities and interests.

[0670] Engagement evaluation and improvement

[0671] The server regularly collects feedback and engagement surveys from employees and analyzes the results to generate feedback that improves engagement across the entire organization.

[0672] For example, the feedback that employees receive includes evaluations of their contributions to recent projects and their ability to collaborate with colleagues. Furthermore, the dashboard displayed on the device allows for one-click enrollment in training courses tailored to their skills. This enables organizations to support the growth of each employee while achieving fair and efficient talent management.

[0673] The following describes the processing flow.

[0674] Step 1:

[0675] The server periodically collects communication data from data sources connected to the company's internal network. This includes logs from the company's email server and chat applications.

[0676] Step 2:

[0677] The server preprocesses the collected data, performing noise reduction and text normalization. This process prepares the data for text analysis.

[0678] Step 3:

[0679] The server analyzes the data, which has been preprocessed using natural language processing. Here, techniques such as key phrase extraction and sentiment analysis are used to extract information for evaluating employees' skills and work attitudes.

[0680] Step 4:

[0681] The server generates a skills evaluation score for each employee based on the analysis results. This score quantifies the employee's abilities and records them numerically.

[0682] Step 5:

[0683] The device updates a dashboard to provide feedback to employees based on the generated skill assessment scores. The feedback highlights their strengths and areas for improvement in their work.

[0684] Step 6:

[0685] Based on evaluation scores, the server selects training programs suitable for employees and automatically creates personalized career development plans.

[0686] Step 7:

[0687] The terminal displays training program information on a dashboard, making it easily accessible to employee users.

[0688] Step 8:

[0689] Users can review their skill assessment and training program, and voluntarily take recommended courses as needed.

[0690] Step 9:

[0691] The server regularly collects and analyzes employee feedback and engagement surveys, and generates feedback to improve engagement within the company.

[0692] Step 10:

[0693] Users can receive the results of their engagement evaluations and use them to improve their activities within the organization.

[0694] (Example 1)

[0695] 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".

[0696] In today's complex work environment, there is a need for efficient evaluation and development of talent, as well as improved engagement. The challenge lies in collecting information from diverse communication channels, appropriately analyzing and evaluating it, supporting each individual's career path, and improving the overall operational efficiency of the organization.

[0697] 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.

[0698] In this invention, the server includes means for collecting communication information and preprocessing it to prepare it for language analysis; means for applying natural language processing to the preprocessed information to generate technical evaluation values; and means for creating individual opinion exchange and training plans based on the generated technical evaluation values. This makes it possible to streamline human resource management within the organization and provide individualized feedback and skill development opportunities for each employee.

[0699] "Communication information" refers to digital data related to business activities, such as emails, chat messages, and document files within a company.

[0700] "Preprocessing" refers to the data processing steps taken before data analysis to remove unnecessary information and standardize the data format.

[0701] "Natural language processing" refers to computer technology used to understand and analyze human language.

[0702] "Technical evaluation scores" refer to the results of an evaluation that quantifies an employee's abilities and performance.

[0703] "Opinion exchange" is an interactive information provision process for providing feedback to employees based on evaluation results.

[0704] A "training plan" is a training curriculum proposed by an organization to improve the skills of its employees.

[0705] "Job career options" are proposals that outline the future direction and growth opportunities for employees' careers.

[0706] "Employee engagement" refers to the degree of involvement and passion that employees have for their work and the organization.

[0707] An "information display device" is a device that visualizes and presents digital information to the user.

[0708] "Survey results" refer to data that presents opinions and new perspectives collected from employees.

[0709] This invention is a system for streamlining human resource management, aiming to improve employee evaluation, development, and engagement within a company. This system primarily consists of three elements: a server, terminals, and users.

[0710] The server automatically collects various communication information within the company using APIs. Specifically, this includes emails, chat messages, and document files. The collected information is preprocessed to remove unnecessary information and standardize data formats. Then, natural language processing technology is applied to analyze the data and generate technical evaluation scores for each employee.

[0711] The terminal visually displays technical evaluation values ​​received from the server on an information display device. Using the user interface, the evaluation values ​​are visualized as bar graphs and radar charts, providing feedback to the user. Furthermore, the user can access training plans to improve their skills based on this feedback and register for appropriate training courses.

[0712] Furthermore, the server suggests career path options based on each individual's skills, encouraging long-term growth. Users can review these suggestions via their devices and use them as a basis for considering their career paths.

[0713] As a concrete example, a generative AI model can be used to analyze the sentiment of emails, and if there is a lot of positive feedback, it can generate an evaluation that highlights that as a strength. Furthermore, as an example of a prompt, you can input something like, "Create personalized feedback and skill-building suggestions based on the contributions of our team members to the new project," and receive a response.

[0714] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0715] Step 1:

[0716] The server automatically collects various types of communication information within the company using an API. This includes emails, chat messages, and document files. The input is all communication data generated during a given period, and the goal is to extract this data and format it for analysis. In practice, the server periodically calls the API endpoint to retrieve the latest communication data.

[0717] Step 2:

[0718] The server preprocesses the collected raw data. This involves removing unnecessary information and standardizing the data format. The input is the data collected in step 1; for example, email headers are removed, and only the necessary text is extracted. The output is a clean and consistent dataset. In this process, the server removes line breaks and whitespace to ensure data integrity.

[0719] Step 3:

[0720] The server performs analysis by applying natural language processing techniques to pre-processed data. The input is the pre-processed dataset to which a specific generative AI model is applied. The data calculations performed here include text sentiment analysis and keyword extraction. The server derives a technical evaluation score for each employee as an analysis result. The output is a result set containing these scores.

[0721] Step 4:

[0722] The server creates individual feedback and training plans based on the generated technical evaluation scores. The input is each employee's evaluation score, which the server uses to propose appropriate feedback and training plans. In actual operation, training courses are selected for skills with low evaluation scores. The output consists of specific training programs and feedback messages.

[0723] Step 5:

[0724] The terminal visually displays technical evaluation figures and feedback received from the server on an information display device. The input is data sent from the server, and the terminal visualizes this information by displaying it as bar graphs or radar charts. The output is an explicit feedback display for the user.

[0725] Step 6:

[0726] Users select and execute actions based on the feedback and training plan provided. The input is the information displayed on the device, which the user uses to choose a path for skill development. For example, they might register for a specific training course. The output is the user's selection and subsequent actions.

[0727] (Application Example 1)

[0728] 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".

[0729] To achieve efficient management and operation of machinery and robots within a factory, it is necessary to collect and appropriately analyze the operational data of each device and robot. However, conventional methods rely heavily on human subjectivity, making it difficult to achieve optimal operation and maintenance. Furthermore, a lack of concrete improvement suggestions to enhance efficiency often leads to missed opportunities for increased productivity. There is a need to solve these problems and maximize the performance of machinery and robots.

[0730] 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.

[0731] In this invention, the server includes means for collecting communication information and performing preliminary processing to prepare for data analysis, means for applying natural language processing to the preliminary processed information to generate a numerical value for performance evaluation, and means for collecting and analyzing operating data of machinery and equipment, and generating and displaying an efficiency score. This makes it possible to objectively and efficiently evaluate the operating status of machinery and robots. Furthermore, by providing optimization suggestions and maintenance schedules tailored to the characteristics based on the generated efficiency score, it is possible to optimize the production process and improve the efficiency of maintenance.

[0732] "Communication information" refers to electronic data collected from machinery and robots used within a factory, including operation logs and operating status.

[0733] "Pre-processing" refers to the data organization and transformation work performed to make collected communication information easier to analyze, and includes data standardization and noise removal.

[0734] "Natural language processing" is a technology that uses computers to analyze human language, understand its meaning, and generate it. It is also used for summarizing and classifying the analysis results.

[0735] "Performance evaluation values" are performance indicators obtained by analyzing the motion data of machinery and robots, and represent a numerical representation of efficiency and precision.

[0736] "Operation data" refers to information that includes records of tasks performed by machinery or robots and their operation history; it's like an operation log.

[0737] The "efficiency score" is an index calculated based on collected motion data, and is used to evaluate the operating status and productivity of machinery and robots.

[0738] "Optimization proposals" refer to methods and strategies proposed to improve the operation of machinery and robots, encompassing a wide range of areas such as productivity improvement and energy efficiency.

[0739] A "maintenance schedule" refers to the schedule of inspections and maintenance work necessary to maintain the performance of machinery and robots, and is a plan for regular maintenance.

[0740] The system for implementing this invention effectively manages and optimizes the performance of machinery and robots within a factory. The server collects factory communication information via an API and performs preliminary processing to prepare for data analysis. This preliminary processing unifies the raw data and removes unnecessary information, enabling efficient subsequent data analysis.

[0741] The pre-processed information is analyzed using a natural language processing library to generate numerical performance evaluations for each machine and robot. This makes it possible to objectively understand work efficiency and accuracy. In addition, an efficiency score is calculated based on the operation data collected daily from the machines and displayed visually on a dashboard. This display uses heatmaps and graphs to allow factory operators to intuitively understand the status of each piece of equipment.

[0742] Furthermore, based on the generated efficiency score, the server suggests areas for optimization. These suggestions include methods for improving productivity and reducing energy consumption. The server also helps ensure that regular maintenance plans are implemented efficiently by automatically creating maintenance schedules for machinery and equipment and notifying operators.

[0743] This approach improves the operational efficiency of machinery and robots within the factory, enabling operators to achieve advanced operational management with minimal effort. Furthermore, by utilizing generative AI models, more accurate and practical optimization suggestions are provided. One example of a prompt is, "What improvements should be made to maximize the transport efficiency of this robot?"

[0744] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0745] Step 1:

[0746] The server collects communication information from various machines and robots within the factory via APIs. This communication information includes operation logs and sensor operation data. The server receives this raw data and stores it in a database. The input is raw communication information, and the output is an organized dataset.

[0747] Step 2:

[0748] The server preprocesses the collected data and converts it into an analyzable format. This process filters out unnecessary data and handles outliers and missing values, preparing the data for analysis. The input is raw communication information, and the preprocessed output yields a clean dataset.

[0749] Step 3:

[0750] The server applies natural language processing (NLP) techniques to pre-processed data to analyze operations and situations recorded in a text-like format. This generates numerical performance evaluations for each machine and robot. The input is a pre-processed dataset, and the output is a numerical performance evaluation.

[0751] Step 4:

[0752] The terminal calculates an efficiency score based on the performance evaluation data received from the server and displays it on the dashboard. This display uses heatmaps and line graphs to make it visually easy for operators to understand. The input is the performance evaluation data, and the output is a visualized efficiency score.

[0753] Step 5:

[0754] The server analyzes the efficiency score and generates optimization suggestions. These include improvements to work processes and energy efficiency. The use of a generating AI model enables highly accurate suggestions. An example of this prompt might be, "What improvements should be made to maximize the transport efficiency of this robot?" The input is the efficiency score, and the output is the optimization suggestion.

[0755] Step 6:

[0756] The server automatically generates maintenance schedules for machinery and equipment, creating plans for necessary inspections and maintenance. This allows operators to perform maintenance work efficiently and at the appropriate time. Inputs are historical operational data and efficiency scores, and output is the maintenance schedule.

[0757] 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.

[0758] The human resource management system of this invention utilizes AI technology to evaluate employee skills and improve employee engagement. This system has a configuration involving three elements: a server, a terminal, and a user, and is particularly characterized by the incorporation of an emotion engine for recognizing user emotions.

[0759] First, the server collects communication data from within the company network, preprocesses it, and then applies natural language processing techniques to analyze the text data. During this process, it utilizes an emotion engine to detect the emotional tone contained in the communication data. For example, it can be used to assess employee stress levels and satisfaction levels from emails and chats.

[0760] Next, the server generates a skill evaluation score based on the analysis data. This score also incorporates data from the emotion engine, allowing for a more precise assessment of employee capabilities. Furthermore, personalized feedback and training programs are created based on the emotion analysis results. The terminal displays the generated feedback and skill evaluation score on a dashboard, making it easy for employees (users) to view.

[0761] By using an emotion engine, career path suggestions become even more personalized. The server considers the employee's emotional state and job interests to suggest the most suitable career options. In this way, users can gain a more concrete vision of their own growth.

[0762] This system also excels from the perspective of employee engagement evaluation. The server regularly collects and analyzes employee feedback and survey data. During this process, it uses an emotion engine to analyze the emotional aspects of the responses and generate more targeted improvement suggestions. The terminal then presents these suggestions to the user in a timely manner, contributing to improved organizational morale.

[0763] A concrete example is when an employee, as a user, receives a warning about their stress level on the dashboard and is introduced to a stress reduction program tailored to their needs. This allows the employee to receive the necessary support and improve their performance.

[0764] The present invention aims to achieve fair and efficient human resource management through these steps, thereby improving employee growth and well-being within the company.

[0765] The following describes the processing flow.

[0766] Step 1:

[0767] The server automatically collects communication data from the company's internal email server and chat application logs. This is done using an API connection and is configured to be updated at regular intervals.

[0768] Step 2:

[0769] The server performs preprocessing on the collected communication data. Specifically, this includes tasks such as denoising text, tokenization, and normalization, converting the data into a format that is easy to analyze at this stage.

[0770] Step 3:

[0771] The server applies natural language processing to the preprocessed data and performs text analysis. This analysis includes key phrase extraction, sentiment analysis, and evaluation of emotional tone using a sentiment engine.

[0772] Step 4:

[0773] The server calculates a skill evaluation score for each employee based on the results obtained from natural language processing. In addition, emotional data obtained from the emotion engine is also incorporated into the score.

[0774] Step 5:

[0775] The device visually displays each employee's skill assessment score and sentiment analysis results on a dashboard. The displayed information includes the employee's work strengths, areas for improvement, and emotional tendencies.

[0776] Step 6:

[0777] The server automatically generates individually optimized feedback and training programs based on evaluation scores and sentiment data.

[0778] Step 7:

[0779] The terminal provides users with generated training programs and feedback content via a dashboard. Employees can refer to this and select recommended training courses.

[0780] Step 8:

[0781] The server automatically suggests appropriate career path options based on employee sentiment data and performance scores. These suggestions are based on job suitability and interests.

[0782] Step 9:

[0783] The device displays career path suggestions on a dashboard, providing a foundation for users to select one and pursue their own professional development.

[0784] Step 10:

[0785] The server periodically collects feedback and engagement surveys from employees and analyzes them using an emotion engine. This allows it to generate feedback that takes into account strategies for improving engagement.

[0786] Step 11:

[0787] The device provides employees with engagement-based feedback and offers them the opportunity to use it as a suggestion for organizational improvement.

[0788] Step 12:

[0789] Users can leverage the provided information and support programs to improve their personal performance and job satisfaction.

[0790] (Example 2)

[0791] 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".

[0792] The challenge lies in promoting individual growth and improving engagement through accurate assessment of employees' skills and psychological states. Traditional methods fail to adequately consider emotional aspects, making it difficult to provide personalized feedback and career path suggestions.

[0793] 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.

[0794] In this invention, the server includes means for collecting communication information and preprocessing it to prepare it for text analysis; means for applying natural language processing to the preprocessed information, performing sentiment analysis, and generating skill evaluation indicators; and means for creating individualized feedback and educational programs based on the generated skill evaluation indicators and sentiment data. This makes it possible to comprehensively evaluate an individual's abilities and emotional state and provide personalized support.

[0795] "Communication information" refers to messages and data sent over a network, including email, chat messages, and voice data.

[0796] "Preprocessing" refers to the initial stage of processing raw data into a format that is easy to analyze, and includes processes such as format standardization, noise reduction, and anonymization.

[0797] "Natural language processing" refers to technologies that enable machines to understand and analyze human language, including techniques for part-of-speech analysis and semantic analysis of text data.

[0798] "Emotion analysis" refers to a technology that extracts emotions and emotional tones from text and audio data to determine specific emotions.

[0799] A "skill evaluation index" is a way of expressing an individual's abilities and skills using numerical values ​​or indicators, and serves as a standard used when evaluating abilities.

[0800] "Feedback" refers to the act of providing evaluations and opinions on specific activities or performances, and offering information to encourage improvement and enhancement.

[0801] An "educational program" refers to a series of learning activities and training designed to improve an individual's skills and knowledge.

[0802] "Career path options" refers to presenting various possible paths for an individual's career growth and future professional advancement, and suggesting the most suitable career route.

[0803] "Engagement" refers to the degree of proactiveness and commitment an individual shows towards an organization or its activities, and is particularly related to employee job satisfaction and sense of participation.

[0804] This invention aims to improve the efficiency of human resource management by utilizing communication information, and is implemented using a system mainly composed of a server, terminal, and user. Specifically, the server collects communication information such as communication messages and chat data, and performs preprocessing such as standardizing the data format and anonymizing it. This makes the data suitable for analysis.

[0805] The server applies natural language processing techniques to pre-processed information to analyze the emotions contained in the text. A natural language processing engine is used for emotion analysis, for example, analyzing expressions like "I'm busy and stressed" to determine the associated emotional tone. This process allows for an understanding of each user's psychological state.

[0806] Based on the analysis results, the server generates skill evaluation metrics and suggests feedback and training programs optimized for the user. For example, if the analysis results indicate that "employees have high stress levels," a stress management training program might be recommended.

[0807] The generated feedback and skill evaluation scores are provided to the user through the device. The device has a dashboard function and is designed to display information visually, making it easier for the user to understand their own status and take steps to improve.

[0808] For example, a user can send a query to the system using the prompt, "Please tell me my current stress level and how to improve it." This allows them to receive immediate support and advice tailored to their individual situation.

[0809] This invention supports individual growth and well-being within an organization and contributes to improved employee engagement.

[0810] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0811] Step 1:

[0812] The server collects communication information transmitted over the network. Input includes emails and chat messages. The server then preprocesses this data by removing personally identifiable information and standardizing the data format. The output is anonymized data that is easy to analyze.

[0813] Step 2:

[0814] The server applies natural language processing (NLP) techniques to preprocessed data. The input is preprocessed text data. The server performs morphological analysis to extract the structure and meaning of the text. Sentiment analysis is also performed in parallel. The output is structured text data with identified emotional tones.

[0815] Step 3:

[0816] The server generates skill evaluation metrics based on the analysis results. The input is emotion analysis and NLP results, which evaluate the user's skills and emotional stability. The server performs calculations to represent this numerically and graphically. The output provides evaluation metrics regarding the user's skills and emotional state.

[0817] Step 4:

[0818] The server creates personalized feedback and training programs based on the generated skill assessment metrics and sentiment data. The input is individual user assessment data. The server generates recommendations to improve the user's specific challenges. The output includes a feedback report and a proposed training program.

[0819] Step 5:

[0820] The terminal receives feedback and evaluation metrics from the server and displays them on the dashboard. Inputs are reports and scores sent from the server. The terminal converts these into a user-friendly graphical format for visualization. Outputs are evaluation information viewable by the user.

[0821] Step 6:

[0822] Users can view their feedback and performance metrics through a dashboard. Users can input prompts into the system, such as "Please tell me how to improve my stress levels." As output, users can receive specific advice and guidance from the system.

[0823] (Application Example 2)

[0824] 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".

[0825] In today's living environment, there is a need to accurately understand the stress and emotional state of individual users and to provide appropriate support promptly. Furthermore, conventional technologies are limited to standard methods for assessing users' abilities and proposing career paths, making it difficult to provide individually optimized suggestions based on each user's characteristics and emotional changes. Therefore, the present invention aims to solve these problems and provide personalized feedback and career path suggestions while promoting stress reduction for users.

[0826] 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.

[0827] In this invention, the server includes means for collecting communication data and preprocessing it to prepare it for text analysis; means for applying natural language processing to the preprocessed data to generate a skill evaluation score; means for creating individual feedback and a skill improvement plan based on the generated skill evaluation score; means for automatically suggesting career path options based on the individual's abilities; and means for analyzing the user's emotional state and making specific suggestions to promote stress reduction based on that analysis. This enables the user to receive optimal feedback and options that take their emotional state into consideration, helping to reduce stress in daily life and promote self-growth.

[0828] "Communication data" refers to all information transmitted and received over a network, and includes various formats such as text, audio, and images.

[0829] "Preprocessing" refers to the processes performed prior to data analysis, including data cleansing and formatting standardization, as preparatory work to improve analysis efficiency.

[0830] Natural language processing is a technology that enables computers to understand, generate, and respond to human language, and is widely used in the analysis of text and audio data.

[0831] A "skill evaluation score" is a numerical assessment of a user's abilities and skills, and is used as a guideline for occupational aptitude and skill development.

[0832] "Feedback" is the process of providing opinions and reactions regarding specific actions or results, offering information to encourage improvement and motivation.

[0833] A "skills improvement plan" is a plan that an individual formulates to improve their own abilities, and it sets out specific goals and means.

[0834] "Career path options" refer to the diverse paths that users can take in their professional lives, and are proposed based on their individual abilities and interests.

[0835] "Emotional state" refers to the overall emotional state an individual is experiencing at a particular point in time, and it fluctuates based on subjective experience.

[0836] "Stress reduction" refers to alleviating the psychological or physical burden an individual is experiencing, and relaxation techniques and a suitable environment are the means to achieve this.

[0837] In this invention, a server plays a central role in collecting and preprocessing communication data. The server performs data cleansing to remove unnecessary parts from the information and convert it into a unified format. Subsequently, natural language processing is applied to generate skill evaluation scores. This process utilizes a natural language processing framework to analyze the meaning from text data and perform numerical evaluations.

[0838] On the user's device, the generated skill assessment score is visually displayed through a dashboard. This allows users to intuitively understand their abilities and aptitudes. Furthermore, the server uses an emotion engine to analyze the user's emotional state and provide optimal suggestions to promote stress reduction. This function recommends appropriate actions based on the user's current psychological state.

[0839] For example, if the server determines that a user needs to relax after a busy day at home, the device can suggest relaxation music. A key feature of this suggestion is that it is customized based on the user's past preferences and current emotional state.

[0840] Regarding generative AI models, an example of a prompt would be: "Explain how a home robot can analyze family voice data, recognize their emotional state, and provide specific suggestions to reduce stress."

[0841] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0842] Step 1:

[0843] The server receives audio data from within the home as communication data and preprocesses this data as input. Specifically, it uses speech recognition technology to remove noise and convert the audio signal into text. The output of this processing is clean text data suitable for analysis.

[0844] Step 2:

[0845] The server applies natural language processing to the pre-processed text data. This involves contextual analysis, topic recognition, and evaluation of the emotional tone of the conversation. The input to this analysis is the text data obtained in the previous step, and the output is data on individual emotional states and emotional tones.

[0846] Step 3:

[0847] The server uses an emotion engine to analyze the user's emotional state. Specifically, it analyzes the output data from the previous step to calculate the user's stress level and current emotional tendencies. The input is emotional tone data, and the output is a quantified evaluation value of the emotional state.

[0848] Step 4:

[0849] The device receives emotional state assessment values ​​and, based on that data, visually displays optimal relaxation suggestions for the user on a dashboard. These suggestions include music types and relaxation exercises. The output is a visual suggestion interface displayed on the device.

[0850] Step 5:

[0851] The user selects a suggestion presented by the device and initiates a specific action. For example, they might play suggested music or start a recommended exercise to reduce stress. The input in this step is the user's choice, and the output is the initiation of physical relaxation.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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."

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] The following is further disclosed regarding the embodiments described above.

[0874] (Claim 1)

[0875] A means of collecting communication data, preprocessing it, and preparing it for text analysis,

[0876] A means for generating skill evaluation scores by applying natural language processing to preprocessed data,

[0877] A means for creating individualized feedback and training programs based on the generated skill assessment scores,

[0878] A means of automatically suggesting career path options based on individual abilities,

[0879] A means to regularly evaluate employee engagement and automatically generate improvement suggestions,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, which visually displays skill evaluation scores based on natural language processing on a dashboard.

[0883] (Claim 3)

[0884] The system according to claim 1, which analyzes feedback and survey results collected from employees and automatically generates feedback to improve work efficiency based on those results.

[0885] "Example 1"

[0886] (Claim 1)

[0887] A means for collecting communication information, performing preprocessing, and preparing it for language analysis,

[0888] A means for generating technical evaluation values ​​by applying natural language processing to pre-processed information,

[0889] A means of creating individual opinion exchanges and training plans based on the generated technical evaluation figures,

[0890] A means of automatically suggesting career options based on an individual's skills,

[0891] A means to periodically evaluate the level of involvement of organizational personnel and automatically generate improvement measures,

[0892] (Methods for selecting and recommending appropriate training courses from the database,

[0893] A means of performing sentiment analysis on communication logs and generating feedback,

[0894] A means of generating automated action suggestions based on daily tasks,

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, which visually displays technical evaluation values ​​based on natural language processing on an information display device.

[0898] (Claim 3)

[0899] The system according to claim 1, which analyzes opinions and survey results collected from organizational personnel and automatically generates discussions for improving work efficiency based on those results.

[0900] "Application Example 1"

[0901] (Claim 1)

[0902] A means of collecting communication information and performing preliminary processing to prepare for data analysis,

[0903] A means for generating numerical values ​​for ability evaluation by applying natural language processing to pre-processed information,

[0904] A means of creating individualized support information and educational plans based on the generated competency assessment scores,

[0905] A means of automatically suggesting career path selections based on an individual's abilities,

[0906] A means for collecting and analyzing operating data of machinery and equipment, and for generating and displaying an efficiency score,

[0907] A means of providing optimization proposals tailored to the characteristics of machinery and equipment, and offering maintenance schedules,

[0908] A system that includes this.

[0909] (Claim 2)

[0910] The system according to claim 1, which visually displays a skill evaluation score based on natural language processing on a display surface.

[0911] (Claim 3)

[0912] The system according to claim 1, which analyzes the operation history collected from a machine and automatically generates an optimization report to improve operational efficiency based on that analysis.

[0913] "Example 2 of combining an emotion engine"

[0914] (Claim 1)

[0915] A means for collecting communication information, performing preprocessing, and preparing it for text analysis,

[0916] A means for applying natural language processing to pre-processed information, performing sentiment analysis, and generating skill evaluation indicators,

[0917] A means of creating individualized feedback and educational programs based on generated skill assessment metrics and emotional data,

[0918] A means of automatically suggesting career path options based on an individual's abilities and emotional state,

[0919] A means of regularly and automatically generating improvement suggestions to enhance engagement by evaluating the psychological state of individuals,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, which visually displays skill evaluation indicators based on natural language processing and sentiment analysis on a display device.

[0923] (Claim 3)

[0924] The system according to claim 1, which analyzes the results of evaluations and opinions collected from individuals and automatically generates opinions for improving work efficiency based on those results.

[0925] "Application example 2 when combining with an emotional engine"

[0926] (Claim 1)

[0927] A means of collecting communication data, preprocessing it, and preparing it for text analysis,

[0928] A means for generating skill evaluation scores by applying natural language processing to preprocessed data,

[0929] A means of creating individualized feedback and skill improvement plans based on the generated skill assessment scores,

[0930] A means of automatically suggesting career path options based on an individual's abilities,

[0931] A means of analyzing the emotional state of users and making specific suggestions to promote stress reduction based on that analysis,

[0932] A means to regularly evaluate user engagement and automatically generate improvement suggestions,

[0933] A system that includes this.

[0934] (Claim 2)

[0935] The system according to claim 1, which visually displays a skill evaluation score based on natural language processing on a display screen.

[0936] (Claim 3)

[0937] The system according to claim 1, which analyzes feedback and survey results collected from users and automatically generates feedback for improving business efficiency based on that analysis. [Explanation of Symbols]

[0938] 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. A means of collecting communication information and performing preliminary processing to prepare for data analysis, A means for generating numerical values ​​for ability evaluation by applying natural language processing to pre-processed information, A means of creating individualized support information and educational plans based on the generated competency assessment scores, A means of automatically suggesting career path selections based on an individual's abilities, A means for collecting and analyzing operating data of machinery and equipment, and generating and displaying an efficiency score, A means of providing optimization proposals tailored to the characteristics of machinery and equipment, and offering maintenance schedules, A system that includes this.

2. The system according to claim 1, which visually displays a skill evaluation score based on natural language processing on a display surface.

3. The system according to claim 1, which analyzes the operation history collected from a machine and automatically generates an optimization report for improving operational efficiency based on that analysis.

Images