system

The system addresses inefficiencies in understanding employee skills and experience by using generative AI for data storage, analysis, and recommendation, optimizing personnel and training plans to enhance organizational productivity and competitiveness.

JP2026175177APending Publication Date: 2026-11-02SOFTBANK GROUP CORP
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2025069967
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2025-04-21
Publication Date
2026-11-02

AI Technical Summary

Technical Problem

Existing systems face challenges in accurately and comprehensively understanding employee skills and experience, leading to inefficient personnel placement and training plans, which compromises organizational productivity and operational efficiency, and lack objectivity in talent development strategies.

Method used

A system utilizing a data storage unit, analysis unit, and recommendation unit powered by generative AI to collect, analyze, and visualize employee-specific skill and experience information, automatically recommending personnel placement and training plans based on comprehensive data analysis.

Benefits of technology

Enables efficient, objective, and real-time human resource management, optimizing personnel placement and training plans, enhancing organizational productivity and competitiveness by leveraging generative AI for data analysis and recommendation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026175177000001_ABST
    Figure 2026175177000001_ABST
Patent Text Reader

Abstract

We provide the system. [Solution] This invention relates to a system that stores employee skill and experience information in a database, automatically collects and analyzes the information using generative AI, visualizes each employee's skills and experience, and efficiently and objectively plans optimal personnel placement and training. Specifically, it centrally manages diverse information such as skills, experience, qualifications, project history, training history, and evaluation history entered by employees and staff, and the generative AI analyzes this data, including unstructured data, using natural language processing and machine learning to automatically generate skill distribution, growth trends, and future predictions. This enables efficient use of vast amounts of employee data, improving the productivity of the entire organization and optimizing human resource development.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method executed by at least one processor, the method comprising the steps of: receiving a user utterance; adding the user utterance to a prompt that includes an instruction sentence related to a description of a chatbot character; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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] The problems this invention aims to solve are: the difficulty in accurately and comprehensively understanding the skills and experience of each employee within an organization; the need for staff to manually review vast amounts of employee data, requiring significant human resources and time; the inefficiency of optimizing personnel placement and developing appropriate training plans based on employee skills and experience; and the resulting inability to fully utilize employee capabilities, leading to decreased overall organizational productivity and operational efficiency. Furthermore, conventional methods make it difficult to continuously track and analyze changes and growth in employee skills and experience, making it impossible to systematically plan future talent development and appropriate personnel placement. In addition, personnel placement and training selection that depend on the subjective opinions and experiences of the person in charge can compromise objectivity and fairness. Therefore, in order to maximize employee capabilities and aptitudes and enhance organizational competitiveness, there is a need for a system that can automatically and accurately collect and analyze information on employee skills and experience, and efficiently realize optimal personnel placement and training plans. [Means for solving the problem]

[0005] As a means of solving the problem, the system provides a data storage unit that stores employee-specific skill and experience information in a database; an analysis unit that automatically collects the employee-specific skill and experience information stored in the data storage unit using generative AI, analyzes each employee's skill level and years of experience using analytical algorithms including natural language processing and machine learning, and visualizes the skill and experience distribution; and a recommendation unit that accepts the required skill and experience conditions for each project and job content as input based on the analysis results of the analysis unit, automatically extracts employees who meet the conditions and recommends them as candidates for personnel placement, and further automatically extracts employees whose skill level is below a predetermined threshold and recommends them as training candidates, with at least a portion of the processing of the analysis unit and recommendation unit being performed by generative AI. By providing a system that comprehensively and accurately grasps the skills and experience of each employee, it becomes possible to efficiently and objectively plan optimal personnel placement and training plans. [Brief explanation of the drawing]

[0006] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0007] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0008] First, let's explain the terminology used in the following explanation.

[0009] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0010] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0011] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0012] 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).

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, when three or more matters are expressed in a connected manner using "and / or", the same concept as that for "A and / or B" applies.

[0014] [First Embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 includes a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of the "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, camera 42, and communication I / F 44 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user inputs. The touch panel 38A receives a user input from contact of an indicator by detecting the contact of the indicator (for example, a pen, a finger, or the like). The microphone 38B receives a user input by voice by detecting the user's voice. The control unit 46A in the processor 46 transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A, a speaker 40B, and the like, and presents data to the user 20 by outputting the data in a representation form (for example, voice and / or text) perceptible to the user 20. The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs voice in accordance with instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to the network 54. The communication I / Fs 44 and 26 manage the exchange of various types of information between the processor 46 and the processor 28 via the network 54.

[0022] Figure 2 illustrates an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0025] 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 the 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 processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models. 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.

[0026] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0027] (Example 1)

[0028] The flow of a specific process in Example 1 will now be described. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0029] (Embodiments for carrying out the present invention)

[0030] Embodiments of the present invention will be described in more specific and detail. The system of the present invention consists of a server and a plurality of terminals. The server is equipped with a data storage unit, an analysis unit, and a recommendation unit, and the terminals function as interfaces for employees and staff to input information and view analysis results and recommendation results.

[0031] First, regarding the input of employee information, employees can either self-report their skills and experience using a dedicated application or web browser running on their terminals, or a person in charge can upload existing documents such as interview records, daily work reports, evaluation sheets, and project reports. For example, employees can input detailed information for each specific skill item, such as "programming (Python, Java, C++)", "sales (corporate sales, individual sales)", "languages ​​(English, Spanish, Chinese)", "project management (agile, waterfall)", and "leadership experience (team leader, project manager)", including the level (1-5 levels, or beginner, intermediate, advanced, etc.), years of experience, qualifications, project names, and results. Documents uploaded by the person in charge can be in various formats, including PDF, Word, spreadsheet files, and text files, and it is also possible to upload multiple documents at once.

[0032] Information entered and uploaded from the terminal is sent to the data storage unit on the server. The data storage unit is designed as a structured database with multiple attributes, including employee ID, name, department, job title, skill items, skill level, years of experience, qualifications, project history, training history, evaluation history, and a free-text field. For example, employee A's record stores detailed information such as "Programming: Python level 5 (7 years of experience), Java level 4 (5 years of experience), Project Management: Agile experience 3 years, Leadership experience: Project Manager twice." Furthermore, the content of training the employee has taken in the past, qualifications obtained, and details of projects they have participated in (project name, duration, role, results, evaluation comments, etc.) are also recorded chronologically.

[0033] The analysis department uses generative AI running on a server to comprehensively analyze the vast amount of employee information stored in the data storage unit. The generative AI utilizes natural language processing technology to extract keywords and context related to skills and experience from free-text fields and uploaded documents. For example, if an employee writes, "I led a team of 5 people as a team leader in launching a new business," "I have experience conducting multiple business negotiations in English with overseas customers," and "I participated in a project to improve business efficiency using AI technology," the generative AI will automatically extract and quantify skills and experience such as "leadership experience," "English proficiency," "AI technology," "business efficiency," and "handling overseas customers." Furthermore, it extracts project names, duration, roles, results, evaluation scores, and supervisor comments from uploaded project reports and evaluation sheets, and adds them to the database as supporting information for employees' skills and experience.

[0034] Furthermore, the generative AI uses machine learning algorithms to analyze each employee's skill level and years of experience in multiple dimensions, visualizing the skill and experience distribution across the entire organization. For example, it can automatically generate heatmaps and graphs of "programming skill distribution," "sales experience years distribution," "language proficiency distribution," and "leadership experience distribution" for all employees, allowing users to see at a glance which skills are strengths and weaknesses within the organization. In addition, it can visualize each employee's skill growth history and training history over time, displaying growth trends in graphs and charts, such as "programming skills improved from level 3 to level 5 in the past two years" or "sales skills significantly improved after training."

[0035] Generative AI also has the ability to learn from past data and predict future skill development potential and suitability. For example, an employee who has participated in multiple training sessions in the past and whose skill level has steadily improved may be judged as having potential for further growth and recommended as a leader candidate or core member of a new project. Furthermore, the AI ​​can learn the characteristics of employees who have received high evaluations in specific projects (skill composition, years of experience, training history, etc.), identify other employees with similar characteristics, and extract them as talent with promising future potential.

[0036] The recommendation department accepts input from terminals regarding the skills and experience required for each project and job content, based on the analysis results from the analysis department. For example, a person in charge might input multiple conditions such as "for new development projects, programming skills (Python level 4 or higher), project management experience (2 years or more), and English proficiency (TOEIC score of 700 or higher)." The recommendation department uses generative AI to automatically extract employees who meet all the conditions from the database and generate the optimal personnel placement plan. For example, if there are multiple employees who meet the conditions, the AI ​​will automatically propose the optimal team composition, taking into account factors such as the balance of skills and experience, past project participation history, current workload, and growth forecast. Furthermore, it automatically extracts employees whose skill levels are below a predetermined threshold and generates individually optimized training plans. For example, it might recommend "Sales Training A for employees with sales skills below level 3," "Language Training B for employees with language proficiency below a certain level," or "Leadership Training C for employees without leadership experience," automatically assigning the most suitable training content to each employee.

[0037] Recommendation and analysis results are sent from the server to terminals, where they can be viewed by the person in charge or employees. For example, the person in charge can view dashboards showing "optimal personnel placement plans for each project," "overall skill distribution," "list of trainees," and "individual employee growth predictions." Employees themselves can also check their own skill evaluations, growth history, and recommended training content from their terminals. Furthermore, the person in charge can change conditions or perform additional filtering from their terminal to retrieve recommendation results in real time.

[0038] The use of generative AI is essential at every stage of processing, including extracting information from unstructured text data, quantifying the skills and experience of each employee, visualizing skill distribution and growth trends, automatically generating optimal personnel placement plans and training programs, and predicting future growth. For example, even when new skill items or evaluation criteria are added, AI automatically updates its analytical model through continuous learning, improving the accuracy of analysis and recommendations. Furthermore, AI can automatically detect skill gaps across the organization and warn of organizational challenges in advance, such as "there is a high probability of a shortage of AI engineers within the next three years" or "there is a shortage of experienced leaders in specific departments."

[0039] Furthermore, the system supports multiple languages, allowing for centralized management of employee data from overseas locations, enabling global talent allocation and training planning. The AI ​​automatically adjusts for differences in evaluation standards and skill sets across countries, facilitating the formation of international project teams and the selection of participants for global training programs.

[0040] Furthermore, with security and privacy protection in mind, employee information is encrypted and stored, and access rights are strictly managed. For example, employees are only allowed to view employee information within their own department, while management can view company-wide data, implementing access control according to roles.

[0041] Thus, in this embodiment of the present invention, the terminal is primarily responsible for inputting employee information and displaying analysis and recommendation results, while the server handles core processing such as data storage, analysis and recommendation processing by generative AI, and database management. The generative AI runs on the server and enables advanced processing such as analysis of vast amounts of employee data, complex recommendation logic, and growth prediction. By linking the terminal and server, real-time and highly accurate human resource management can be achieved, leading to improved organizational productivity and optimized human resource development. For example, it becomes a robust system that can flexibly and quickly respond to all kinds of human resource strategies, such as organizational restructuring, new business launches, global expansion, DX promotion, leadership development, skill gap closure, and training effectiveness measurement.

[0042] (System Configuration)

[0043] The system according to this embodiment comprises a data storage unit, an analysis unit, a recommendation unit, an interface unit, a security management unit, a log management unit, and an AI prompt generation unit. The data storage unit has the function of centrally storing diverse data such as skill information, experience information, qualification acquisition history, project participation history, training attendance history, evaluation history, daily work reports, interview records, and free-text fields for each employee. For example, when an employee inputs skills such as "Programming (Python level 5, Java level 4, C++ level 3)," "Sales (5 years of corporate sales experience, 2 years of individual sales experience)," and "Language (English TOEIC 850, Chinese HSK level 4)" from a terminal, or when a person in charge uploads interview records or daily work reports, or when detailed information such as project name, role, period, results, and evaluation comments is recorded, all of this information is linked to each employee ID and stored in the database. Furthermore, it can integrate and manage both structured and unstructured data, such as images of certificates when an employee acquires a new qualification, the results of questionnaires after training, and evaluation comments from supervisors.

[0044] The analysis department has the capability to comprehensively analyze the vast amount of employee information stored in the data storage department using generative AI. For example, it utilizes natural language processing technology to extract keywords and context related to skills and experience from free-text fields and uploaded documents, quantifying employees' skill sets and experience levels. For instance, from descriptions such as "led a team of 5 people as a team leader in launching a new business," "experienced multiple business negotiations with overseas clients in English," and "participated in a business efficiency improvement project utilizing AI technology," it extracts skills and experiences such as "leadership experience," "English proficiency," "AI technology," "business efficiency improvement," and "handling overseas clients," automatically generating a skill map for each employee. Furthermore, it uses machine learning algorithms to analyze each employee's skill level and years of experience in multiple dimensions, visualizing the overall skill and experience distribution of the organization as heatmaps and graphs. For example, it automatically generates "programming skill distribution," "sales experience years distribution," "language proficiency distribution," and "leadership experience distribution," allowing users to quickly understand which skills are strengths and which areas are weaknesses within the organization. Furthermore, it is possible to visualize each employee's skill growth history and training history over time, displaying growth trends in graphs and charts, such as "Programming skills improved from level 3 to level 5 in the past two years" or "Sales skills significantly improved after training." In addition, the generative AI learns from past data and has the function to predict the potential for future skill improvement and aptitude. For example, if an employee has taken multiple training courses in the past and their skill level has steadily improved, it can be determined that further growth can be expected and recommended as a leader candidate or a core member of a new project.

[0045] The recommendation department, based on the analysis results from the analysis department, accepts input from terminals regarding the skills and experience required for each project and job content. Using a generative AI, it automatically extracts employees who meet all the relevant conditions from the database and generates optimal personnel placement plans. For example, if a person in charge inputs multiple conditions such as "for a new development project, programming skills (Python level 4 or higher), project management experience (2 years or more), and English proficiency (TOEIC score of 700 or higher)," and there are multiple employees who meet the conditions, the AI ​​will automatically propose the optimal team composition, taking into account the balance of skills and experience, past project participation history, current workload, and growth forecasts. It also automatically extracts employees whose skill levels are below a predetermined threshold and generates individually optimized training plans. For example, it automatically assigns the most suitable training content to each employee, such as "recommending sales training A for employees with sales skills below level 3," "proposing language training B for employees with language proficiency below a certain level," and "recommending leadership training C for employees without leadership experience." Furthermore, during organizational restructuring, new business launches, or global expansion, the necessary skill sets can be redefined, and generative AI can extract the most suitable personnel from all employees to form new teams.

[0046] The interface section provides a user interface for employees and staff to input information from their terminals and view analysis results and recommendations. For example, it includes an input form for employees to self-report their skills and experience, a file upload function for staff to upload existing documents such as interview records, daily work reports, evaluation sheets, and project reports, a visual display function to show analysis results and recommendations in various formats such as graphs, lists, heatmaps, and dashboards, and a search and filtering function for staff to change conditions or perform additional filtering. Furthermore, it also provides a My Page function where employees can check their own skill evaluations, growth history, and recommended training content for the future.

[0047] The Security Management Department is responsible for information security and privacy protection, including encrypted storage of employee information, access rights management, encrypted communications, login authentication, and data backup. For example, employee information is encrypted and stored, access rights are strictly managed, and access control according to role is implemented, such as allowing employees to view only employee information in their own department, while management can view company-wide data. Furthermore, all communications between terminals and servers are encrypted to prevent unauthorized access and information leaks. Login authentication is strengthened using multi-factor authentication and one-time passwords, and there is also a function to encourage periodic password changes. Data backups are performed automatically on a regular basis, and a system is in place to enable rapid recovery in the event of a disaster or failure.

[0048] The Log Management Department meticulously records and manages the entire system's operation history, access history, data update history, and error history. For example, it records in chronological order who viewed, edited, or deleted which employee information and when, what operations were performed from which terminal, when and how AI analysis and recommendation processes were executed, and detailed logs of errors and anomalies. This information is used for audits, troubleshooting, and security measures. Logs are backed up regularly and can be searched, extracted, and analyzed by administrators as needed.

[0049] The AI ​​prompt generation unit automatically generates optimal prompts for the generation AI, improving the accuracy of the AI's analysis and recommendation processes. For example, when extracting skills and experience from unstructured text data, it generates a prompt such as, "Extract project name, assigned tasks, technologies used, acquired skills, and results from the following employee work reports, and organize them by employee ID," and inputs this prompt into the AI. When predicting employee growth, it generates a prompt such as, "Based on the following employees' skill evaluation history and training history over the past three years, predict the skills that can be expected to improve in the next year and the reasons why." When generating optimal personnel placement plans, it generates a prompt such as, "Extract employees who meet all of the following conditions, and propose the optimal team composition considering the balance of skills and experience, past project participation history, current workload, and growth predictions." When extracting training candidates, it generates a prompt such as, "Extract employees with sales skills below level 3, and propose the optimal training content considering their past training history and growth trends." These prompts are automatically optimized according to the AI's learning progress and the content of the data being analyzed, continuously improving the accuracy of the AI's output.

[0050] As described above, the system according to this embodiment includes a data storage unit, an analysis unit, a recommendation unit, an interface unit, a security management unit, a log management unit, and an AI prompt generation unit, all of which work together to comprehensively and accurately grasp the skills and experience of each employee, enabling the efficient and objective formulation of optimal personnel placement and training plans. By utilizing generative AI, it is possible to achieve advanced human resource management that was previously difficult, such as analysis of unstructured data, talent extraction under complex conditions, growth prediction, and optimization of training plans.

[0051] (Implementation Steps)

[0052] Step 1: Entering and collecting employee information Employees or designated personnel use terminals to input information such as skills, experience, qualifications, project history, training history, performance evaluation history, daily work reports, interview records, and free-text fields. For example, employees can input skills such as "Programming (Python level 5, Java level 4)," "Sales (5 years of corporate sales experience)," and "Language (English TOEIC 850)," while designated personnel can upload interview records, daily work reports, and project reports. The system supports various document formats, including PDF, Word, spreadsheets, and text files, and allows for the uploading of multiple documents at once.

[0053] Step 2: Storage and management in the database Information entered and uploaded from the terminal is sent to the data storage unit on the server and centrally managed as a structured database with attributes such as skills, experience, qualifications, project history, training history, evaluation history, and free-text fields for each employee ID. For example, employee A's record will store detailed information such as "Programming: Python level 5 (7 years of experience), Project Management: Agile experience 3 years."

[0054] Step 3: AI analysis of unstructured data Using a generation AI, keywords and context related to skills and experience are extracted from free-text fields and uploaded documents to quantify employees' skill sets and experience levels. For example, from descriptions such as "Leaded a team of 5 people as a team leader in launching a new business" or "Had multiple business negotiations with overseas clients in English," skills and experience such as leadership experience, English proficiency, and handling overseas clients are extracted. As a concrete example of a prompt, the generation AI is input with the following: "Extract project name, assigned tasks, technologies used, acquired skills, and results from the following employee work reports, and organize them by employee ID."

[0055] Step 4: Visualization of skills and experience and analysis of growth history Using generative AI and machine learning algorithms, the system analyzes each employee's skill level and years of experience in multiple dimensions, visualizing the overall skill and experience distribution within the organization as heatmaps and graphs. Furthermore, it visualizes each employee's skill growth history and training history over time, displaying growth trends in graphs and charts. As a concrete example of a prompt, the generative AI is inputted with the following message: "Based on the skill evaluation history and training history of the following employees over the past three years, please graph their skill growth trends over time."

[0056] Step 5: Future Forecasting and Aptitude Analysis Using a generative AI, past data is learned to predict future skill improvement potential and aptitude. For example, an employee who has participated in multiple training sessions in the past and whose skill level has steadily improved will be judged as having potential for further growth and will be recommended as a leader candidate or a core member of a new project. As a specific example of a prompt, the following will be entered into the generative AI: "Based on the following employee's past skill evaluation history and training participation history, predict the skills that can be expected to improve in the next year and the reasons why."

[0057] Step 6: Optimizing staffing and training plans Based on the analysis results from the analysis department, the system allows users to input the required skills and experience for each project and task via a terminal. The AI ​​then automatically extracts employees who meet all the criteria from the database and generates optimal personnel placement plans and individually optimized training plans. For example, by inputting conditions such as "for a new development project, programming skills (Python level 4 or higher), project management experience (2 years or more), and English proficiency (TOEIC score of 700 or higher)," the AI ​​proposes the optimal team composition. A concrete example of a prompt message would be to input to the AI: "Extract employees who meet all of the following conditions and propose the optimal team composition considering the balance of skills and experience, past project participation history, current workload, and growth forecast."

[0058] Step 7: Display of analysis and recommendation results and feedback The system sends analysis and recommendation results from the server to terminals, allowing staff and employees to view them in various formats such as graphs, lists, heatmaps, and dashboards. Staff can view dashboards showing "optimal personnel placement plans for each project," "overall skill distribution," "training target lists," and "individual employee growth predictions," while employees can also check their own skill evaluations, growth history, and recommended training content. Staff can retrieve recommendation results in real time by changing conditions or applying additional filters.

[0059] (Specific use cases)

[0060] For example, consider a scenario where an organization is launching a new business system development project. The project leader needs to select the most suitable personnel and assemble a project team. In this case, the project leader uses the terminal's interface to input multiple skill requirements for the project, such as "programming skills (Python level 4 or higher), project management experience (2 years or more), English communication skills (TOEIC score of 700 or higher), and knowledge of cloud infrastructure (1 year or more of practical experience)." Furthermore, depending on the nature of the project, prior experience participating in large-scale projects or having completed leadership training can also be added as requirements.

[0061] This input information is sent to the recommendation department on the server, which then accesses data stored in the data storage unit, including skill information, experience information, qualifications, project history, training history, evaluation history, and free-text fields for all employees. The recommendation department uses a generation AI to generate a prompt message, for example, "Extract employees who meet all of the following conditions, and propose the optimal team composition considering the balance of skills and experience, past project participation history, current workload, and growth forecast," and inputs it into the AI. The generation AI automatically extracts employees who meet all the conditions, such as "Employee ID 123: Python level 5, 3 years of project management experience, TOEIC score of 800, 2 years of cloud infrastructure experience, experience participating in large-scale projects, completed leadership training," and then automatically generates the optimal team composition by comprehensively considering the balance of skills and experience, past project participation history, current workload, and growth forecast.

[0062] Furthermore, the analysis department uses generative AI to visualize the skill distribution, experience distribution, and growth history of each employee, outputting data such as "Python skill distribution," "project management experience distribution," "English proficiency distribution," and "cloud infrastructure experience distribution" as heatmaps and graphs. In addition, based on each employee's growth trends and past training history, it predicts the potential for future skill improvement and aptitude, outputting analysis results such as "Employee ID 123's programming skills improved from level 3 to level 5 in the past two years, and further growth can be expected" and "Employee ID 456's project management ability significantly improved after taking leadership training." This allows project leaders to select the most suitable personnel, taking into account not only the presence or absence of skills and experience, but also growth trends and future aptitude.

[0063] Furthermore, the recommendation system automatically identifies employees who do not meet the required skill levels for the project and generates individually optimized training plans. For example, it might recommend "Python Training A for employees with Python skills below level 4," "Project Management Training B for employees with less than two years of project management experience," or "English Training C for employees with a TOEIC score below 700," automatically assigning the most suitable training content to each employee. An example of a prompt to the generating AI would be: "Based on the following employee skill evaluations and training history, please suggest the most suitable training content to meet the required skill levels for the project."

[0064] In such use cases, the system enables project leaders and staff to efficiently and objectively formulate optimal personnel placement and training plans by leveraging the advanced analytical capabilities of generating AI, without having to individually review vast amounts of employee data. This is achieved through a series of steps: inputting and collecting employee information, storing and managing it in a database, AI analysis of unstructured data, visualization of skills and experience and analysis of growth history, future prediction and aptitude analysis, optimization of personnel placement and training plans, and displaying and providing feedback on analysis and recommendation results. This allows for improved productivity and optimized talent development across the entire organization.

[0065] (Application Example 1) The flow of a specific process in Application Example 1 will be explained below. Each part of the system described below is implemented by a data processing device 12 and a smart device 14. The data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0066] (Embodiments for carrying out the present invention)

[0067] Embodiments of the present invention will be described in more detail. The system of the present invention comprehensively databases all information of staff in nursing care settings, including skills, experience, qualifications, care history, emergency response experience, infectious disease response experience, medical care implementation history, communication ability, dementia care experience, training attendance history, evaluation history, daily work reports, and free-text fields. It then uses generative AI to analyze this information from multiple perspectives and automatically formulates optimal staff allocation and individually optimized training plans.

[0068] First, the data storage department records and manages extremely detailed information for each care staff member. For example, for staff member A, it records "Dementia care: Level 4", "Medical care: Level 3", "Communication: Level 5", "Emergency response experience: 2 times", "Infection control experience: 1 time", "Qualifications held: Certified care worker, Dementia care specialist", "Care history: Responsible for user A for 3 months, responsible for user B for 1 year", "Daily work report: April 1, 2024, responded to a fall incident at night", "Evaluation history: Supervisor evaluation A for FY2023", "Training attendance history: May 2023, attended dementia care training". Skills, experience, qualifications, assignment history, daily work records, evaluations, and training history are recorded in detail using numbers and text. For Staff B, the system records information such as "Dementia care: Level 2," "Medical care: Level 4," "Communication: Level 3," "Experience in infectious disease response: 2 times," "Qualifications: Certified care worker," "Care history: Responsible for user C for 2 years," and "Daily work report: March 15, 2024, Led infectious disease control measures during influenza outbreak." For Staff C, the system records information such as "Dementia care: Level 3," "Medical care: Level 2," "Communication: Level 4," "Emergency response experience: 1 time," "Experience in infectious disease response: 2 times," "Qualifications: Certified care worker," and "Care history: Responsible for user D for 6 months." All staff members are comprehensively recorded with diverse information. This information can be entered directly by staff members or managers from their terminals, and document data such as daily work reports, care records, training attendance records, evaluation sheets, accident reports, family interview records, and user questionnaires can also be uploaded, supporting various formats such as PDF, Word, spreadsheet files, text files, and image files. Furthermore, it is possible to upload audio and video recordings, and AI can automatically extract the content using speech recognition and image recognition.

[0069] The analysis department uses generative AI to analyze the vast amount of staff information stored in the data storage department from multiple perspectives with high accuracy. For example, it utilizes natural language processing technology to extract keywords and context related to skills and experience from free-text fields and uploaded documents, quantifying staff skill sets and experience levels. For instance, from descriptions such as "performed emergency response twice when accepting new users," "led infectious disease control during infectious disease outbreaks," "responsible for gastrostomy management as medical care," "contributed to building trust with families through communication with dementia users," and "responded quickly to nighttime falls and led coordination with medical institutions," it extracts experience in emergency response, infectious disease response, medical care, communication skills, dementia care, and medical institution collaboration, automatically generating a skill map for each staff member. Furthermore, the AI ​​also extracts information from daily work reports and accident reports, such as "experience in nighttime accident response," "experience in simultaneously handling multiple users," "number of family interviews," and "number of high ratings in user surveys," quantifying the multifaceted capabilities of staff members.

[0070] Furthermore, machine learning algorithms are used to multidimensionally analyze each staff member's skill level, experience, qualification distribution, growth trends, and care history, and to visualize the organization's overall skill distribution, experience distribution, qualification distribution, and growth history as heatmaps and graphs. For example, the system automatically generates data such as "dementia care skill distribution," "medical care skill distribution," "emergency response experience distribution," "infectious disease response experience distribution," "percentage of certified care workers," "number of dementia care specialists," "percentage of staff with nighttime response experience," and "percentage of staff with family interview experience," allowing users to see at a glance which skills are strengths within the organization, which areas are weaknesses, which qualifications are lacking, and which experiences are unevenly distributed. In addition, the system visualizes each staff member's skill growth history and training history over time, and can display growth trends and accumulated experience in graphs and charts, such as "dementia care skills improved from level 2 to level 4 in the past year," "skills significantly improved after medical care training," "increasing infectious disease response experience," and "increasing nighttime accident response experience." In addition, generative AI has the ability to learn from past data and predict future skill development potential and aptitude. For example, it can determine that staff members who have participated in multiple training sessions in the past and whose skill levels have steadily improved are likely to continue growing and can recommend them as potential leaders or specialists. Conversely, it can also suggest individual follow-up or additional training for staff members whose growth has stagnated.

[0071] Based on the analysis results from the analysis department, the recommendation department accepts input from a terminal regarding the care content, skill requirements, qualifications, and experience requirements needed for each user. Using a generative AI, it automatically extracts staff members who meet all the relevant conditions from the database and generates an optimal staffing plan. For example, if multiple conditions are entered for user A, such as "dementia care level 3 or higher," "communication ability level 4 or higher," "medical care level 2 or higher," "certified care worker," "previous experience caring for dementia patients," "experience with night shifts," and "experience with family interviews," and there are multiple staff members who meet the conditions, the AI ​​will automatically propose an optimal team composition, taking into account factors such as the balance of skills and experience, past patient history, current number of patients and workload, growth trends, preference for night shifts, and experience in building trust with families. For example, it can propose a team composition that complements each other's strengths by pairing a staff member with high dementia care skills but little experience with night shifts with a staff member with extensive experience with night shifts but slightly lower dementia care skills. It also automatically extracts staff members whose skill levels are below a predetermined threshold and generates individually optimized training plans. For example, the AI ​​automatically assigns the most suitable training content to each staff member, such as "Recommend Medical Care Training A for staff with medical care skills below level 4," "Suggest Dementia Care Training B for staff with limited experience in dementia care," "Recommend Emergency Response Simulation Training C for staff with no experience in emergency response," and "Suggest Communication Training D for staff with little experience in family interviews." Furthermore, in the event of organizational restructuring, launch of new businesses, changes in the user base, or the establishment of emergency systems during infectious disease outbreaks, the necessary skill sets and qualifications can be redefined, and the generative AI can extract the most suitable personnel from all staff members to form new teams.

[0072] The interface section provides a user interface for staff and administrators to input information from their devices and view analysis results and recommendations. For example, it includes an input form for staff to self-report their skills and experience, a file upload function for administrators to upload existing documents such as daily work reports, evaluation sheets, training attendance records, accident reports, family interview records, and user questionnaires, a visual display function to show analysis results and recommendations in various formats such as graphs, lists, heatmaps, and dashboards, a search and filtering function for administrators to change conditions and perform additional filtering, a My Page function where staff can check their own skill evaluations, growth history, and recommended training content, and a management dashboard function where administrators can check staff growth trends and training effectiveness at a glance. Furthermore, it addresses diverse on-site needs with features such as voice input and output, optimization for tablet and smartphone devices, and accessibility features for visually impaired users.

[0073] The Security Management Department is responsible for information security and privacy protection, including encrypted storage of staff information, access rights management, encrypted communications, login authentication, and data backup. For example, staff information is encrypted and stored, access rights are strictly managed, and access control according to roles is implemented, such as allowing administrators to view only the staff information of their own department, while management can view company-wide data. Furthermore, all communications between terminals and servers are encrypted to prevent unauthorized access and information leaks. Login authentication is strengthened using multi-factor authentication and one-time passwords, and there is also a function to encourage periodic password changes. Data backups are performed automatically on a regular basis, and a system is in place to enable rapid recovery in the event of disasters or failures.

[0074] The log management department meticulously records and manages the entire system's operation history, access history, data update history, and error history. For example, it records in chronological order who viewed, edited, or deleted which staff information and when, what operations were performed from which terminal, when and how AI analysis and recommendation processes were executed, and detailed logs of errors and anomalies. This information is used for audits, troubleshooting, and security measures. Logs are backed up regularly and can be searched, extracted, and analyzed by administrators as needed.

[0075] The AI ​​prompt generation unit automatically generates optimal prompt statements for the generation AI, improving the accuracy of the AI's analysis and recommendation processes. For example, when extracting skills and experience from unstructured text data, it generates a prompt statement such as, "Extract the assigned clients, care performed, acquired skills, and results from the following staff members' daily work reports, and organize them by staff ID," and inputs this into the AI. When predicting staff growth, it generates a prompt statement such as, "Based on the following staff members' skill evaluation history and training history over the past three years, predict the skills that can be expected to improve in the next year and the reasons why." When generating optimal staff placement plans, it generates a prompt statement such as, "Extract staff members who meet all of the following conditions, and propose the optimal team composition considering the balance of skills and experience, past client history, current workload, and growth predictions." When extracting training candidates, it generates a prompt statement such as, "Extract staff members with medical care skills below level 4, and propose the optimal training content considering their past training history and growth trends." These prompt statements are automatically optimized according to the AI's learning progress and the content of the data being analyzed, continuously improving the accuracy of the AI's output.

[0076] As described above, embodiments of the present invention enable comprehensive and highly accurate management of all information in nursing care settings, including staff skills, experience, qualifications, care history, emergency response experience, infectious disease response experience, medical care implementation history, communication ability, dementia care experience, training attendance history, evaluation history, daily work reports, and free-response fields. Generative AI is used to automatically formulate optimal staff assignments and individually optimized training plans. For example, staff with high dementia care skills and communication abilities can be preferentially assigned to users requiring dementia care, while staff with medical care experience and qualifications can be assigned to users requiring medical care. Furthermore, by visualizing staff skill gaps and growth trends and automatically generating individually optimized training plans, it is possible to promote staff growth, improve service quality, enhance user satisfaction, improve operational efficiency, and optimize human resource development across the entire organization. Moreover, in emergencies such as accidents or infectious disease outbreaks, the AI ​​can quickly identify the most suitable staff to respond, increasing responsiveness on-site. In addition, communication history with families and user survey results are also analyzed, contributing to improved user and family satisfaction. This multi-layered and multifaceted information management, combined with AI analysis, creates a robust system that enables scientific and objective human resource management, free from the reliance on traditional, subjective human judgment and empirical rules.

[0077] (System Configuration)

[0078] The system according to this embodiment comprises a data storage unit, an analysis unit, a recommendation unit, an interface unit, a security management unit, a log management unit, and an AI prompt generation unit. The data storage unit has the function of centrally storing extremely diverse and detailed information as a database, including skill information, experience information, qualification information, user history, emergency response experience, infectious disease response experience, medical care implementation history, communication ability, dementia care experience, training attendance history, evaluation history, daily work reports, and free-text fields for each care staff member. For example, for Staff A, the system records detailed information such as "Dementia care: Level 4", "Medical care: Level 3", "Communication: Level 5", "Emergency response experience: 2 times", "Infection control experience: 1 time", "Qualifications: Certified care worker, Dementia care specialist", "Care history: Responsible for user A for 3 months, responsible for user B for 1 year", "Daily work report: April 1, 2024, responded to a fall incident at night", "Evaluation history: Supervisor evaluation A for FY2023", "Training history: May 2023, attended dementia care training". Skills, experience, qualifications, assignment history, daily work records, evaluations, and training history are recorded in detail using numbers and text. In addition to direct input by staff and managers from terminals, document data such as daily work reports, care records, training records, evaluation sheets, accident reports, family interview records, and user questionnaires can also be uploaded. The system supports a variety of formats including PDF, Word, spreadsheet files, text files, image files, audio recordings, and video recordings, and can automatically extract content using AI-powered speech recognition and image recognition.

[0079] The analysis department has the capability to analyze the vast amount of staff information stored in the data storage department from multiple perspectives with high accuracy using generative AI. For example, it utilizes natural language processing technology to extract keywords and context related to skills and experience from free-text fields and uploaded documents, quantifying staff skill sets and experience levels. For instance, from descriptions such as "performed emergency response twice when accepting new users," "led infectious disease control during infectious disease outbreaks," "responsible for gastrostomy management as medical care," "contributed to building trust with families through communication with dementia users," and "responded quickly to nighttime falls and led coordination with medical institutions," it extracts experience in emergency response, infectious disease response, medical care, communication skills, dementia care, and medical institution collaboration, automatically generating a skill map for each staff member. Furthermore, the AI ​​also extracts information such as "experience in nighttime accident response," "experience in simultaneously handling multiple users," "number of family interviews," and "number of high ratings in user surveys" from daily work reports and accident reports, quantifying the multifaceted capabilities of staff members. Using machine learning algorithms, the system analyzes each staff member's skill level, experience, qualification distribution, growth trends, and care history in multiple dimensions, visualizing the organization's overall skill distribution, experience distribution, qualification distribution, and growth history as heatmaps and graphs. For example, it automatically generates data such as "dementia care skill distribution," "medical care skill distribution," "emergency response experience distribution," "infectious disease response experience distribution," "percentage of certified care workers," "number of dementia care specialists," "percentage of staff with nighttime response experience," and "percentage of staff with family interview experience," allowing users to see at a glance which skills are strengths within the organization, which areas are weaknesses, which qualifications are lacking, and which experiences are unevenly distributed. It can also visualize each staff member's skill growth history and training history over time, displaying growth trends and accumulated experience in graphs and charts, such as "dementia care skills improved from level 2 to level 4 in the past year," "skills significantly improved after medical care training," "increasing infectious disease response experience," and "increasing nighttime accident response experience."Generative AI learns from past data and has the ability to predict future skill development potential and aptitude. For example, it can determine that staff members who have participated in multiple training sessions and whose skill levels have steadily improved are likely to continue growing and recommend them as potential leaders or specialists. Conversely, it can suggest individual follow-up or additional training for staff members whose growth has stagnated.

[0080] The recommendation department, based on the analysis results from the analysis department, accepts input from a terminal regarding the care content, skill requirements, qualifications, and experience requirements needed for each user. Using a generative AI, it automatically extracts staff members who meet all the relevant conditions from the database and generates an optimal staffing plan. For example, if multiple conditions are entered for user A, such as "dementia care level 3 or higher," "communication ability level 4 or higher," "medical care level 2 or higher," "holds a certified care worker qualification," "has experience caring for dementia patients in the past," "has experience with night shifts," and "has experience conducting family interviews," and there are multiple staff members who meet the conditions, the AI ​​will automatically propose an optimal team composition, taking into account factors such as the balance of skills and experience, past user history, current number of users and workload, growth trends, preference for night shifts, and experience in building trust with families. For example, it can propose a team composition that complements each other's strengths, such as pairing a staff member with high dementia care skills but little experience with night shifts with a staff member with extensive experience with night shifts but slightly lower dementia care skills. It also automatically extracts staff members whose skill levels are below a predetermined threshold and generates individually optimized training plans. For example, the AI ​​automatically assigns the most suitable training content to each staff member, such as "Recommend Medical Care Training A for staff with medical care skills below level 4," "Suggest Dementia Care Training B for staff with limited experience in dementia care," "Recommend Emergency Response Simulation Training C for staff with no experience in emergency response," and "Suggest Communication Training D for staff with little experience in family interviews." Furthermore, in the event of organizational restructuring, launch of new businesses, changes in the user base, or the establishment of emergency systems during infectious disease outbreaks, the necessary skill sets and qualifications can be redefined, and the generative AI can extract the most suitable personnel from all staff members to form new teams.

[0081] The interface section provides a user interface for staff and administrators to input information from their devices and view analysis results and recommendations. For example, it includes an input form for staff to self-report their skills and experience, a file upload function for administrators to upload existing documents such as daily work reports, evaluation sheets, training attendance records, accident reports, family interview records, and user questionnaires, a visual display function to show analysis results and recommendations in various formats such as graphs, lists, heatmaps, and dashboards, a search and filtering function for administrators to change conditions and perform additional filtering, a My Page function where staff can check their own skill evaluations, growth history, and recommended training content, and a management dashboard function where administrators can check staff growth trends and training effectiveness at a glance. Furthermore, it addresses diverse on-site needs with features such as voice input and output, optimization for tablet and smartphone devices, and accessibility features for visually impaired users.

[0082] The Security Management Department is responsible for information security and privacy protection, including encrypted storage of staff information, access rights management, encrypted communications, login authentication, and data backup. For example, staff information is encrypted and stored, access rights are strictly managed, and access control according to roles is implemented, such as allowing administrators to view only the staff information of their own department, while management can view company-wide data. Furthermore, all communications between terminals and servers are encrypted to prevent unauthorized access and information leaks. Login authentication is strengthened using multi-factor authentication and one-time passwords, and there is also a function to encourage periodic password changes. Data backups are performed automatically on a regular basis, and a system is in place to enable rapid recovery in the event of disasters or failures.

[0083] The log management department meticulously records and manages the entire system's operation history, access history, data update history, and error history. For example, it records in chronological order who viewed, edited, or deleted which staff information and when, what operations were performed from which terminal, when and how AI analysis and recommendation processes were executed, and detailed logs of errors and anomalies. This information is used for audits, troubleshooting, and security measures. Logs are backed up regularly and can be searched, extracted, and analyzed by administrators as needed.

[0084] The AI ​​prompt generation unit automatically generates optimal prompt statements for the generation AI, improving the accuracy of the AI's analysis and recommendation processes. For example, when extracting skills and experience from unstructured text data, it generates a prompt statement such as, "Extract the assigned clients, care performed, acquired skills, and results from the following staff members' daily work reports, and organize them by staff ID," and inputs this into the AI. When predicting staff growth, it generates a prompt statement such as, "Based on the following staff members' skill evaluation history and training history over the past three years, predict the skills that can be expected to improve in the next year and the reasons why." When generating optimal staff placement plans, it generates a prompt statement such as, "Extract staff members who meet all of the following conditions, and propose the optimal team composition considering the balance of skills and experience, past client history, current workload, and growth predictions." When extracting training candidates, it generates a prompt statement such as, "Extract staff members with medical care skills below level 4, and propose the optimal training content considering their past training history and growth trends." These prompt statements are automatically optimized according to the AI's learning progress and the content of the data being analyzed, continuously improving the accuracy of the AI's output.

[0085] As described above, the system according to this embodiment includes a data storage unit, an analysis unit, a recommendation unit, an interface unit, a security management unit, a log management unit, and an AI prompt generation unit, each working in cooperation to comprehensively and accurately manage all kinds of information in nursing care settings, such as staff skills and experience, qualifications, care history, emergency response experience, infectious disease response experience, medical care implementation history, communication ability, dementia care experience, training attendance history, evaluation history, daily work reports, and free-text fields. It also enables the automatic planning of optimal staff allocation and individually optimized training plans using generative AI.

[0086] (Implementation Steps)

[0087] Step 1: Collect and enter staff information Care staff or managers use terminals to input detailed information such as skills, experience, qualifications, client history, emergency response experience, infectious disease response experience, medical care implementation history, communication skills, dementia care experience, training attendance history, evaluation history, daily work reports, and free-text fields. For example, staff members may input "Dementia care: Level 4," "Medical care: Level 3," "Communication: Level 5," "Emergency response experience: 2 times," and "Qualifications held: Certified Care Worker," while managers upload document data such as daily work reports, accident reports, family interview records, and client questionnaires. Document data supports a variety of formats including PDF, Word, spreadsheet, text, images, audio, and video.

[0088] Step 2: Storage and management in the database Information entered and uploaded from the terminal is sent to the data storage unit on the server and centrally managed as a structured database with attributes such as skills, experience, qualifications, assignment history, daily work reports, evaluations, training history, and free-text fields for each staff ID. For example, the record for staff A would store information such as "Dementia care: Level 4," "Medical care: Level 3," "Assigned to user A for 3 months," and "Responded to a fall incident on the night of April 1, 2024."

[0089] Step 3: AI analysis of unstructured data Using a generation AI, keywords and context related to skills and experience are extracted from free-text fields and uploaded documents to quantify staff skill sets and experience levels. For example, from descriptions such as "Performed emergency response twice when accepting new users," "Leaded infection control during an infectious disease outbreak," and "Responsible for gastrostomy management as medical care," experience in emergency response, infectious disease response, and medical care can be extracted. A concrete example of a prompt to be fed into the generation AI is to input "Extract the user in charge, care performed, skills acquired, and results from the following staff member work reports, and organize them by staff ID."

[0090] Step 4: Visualization of skills, experience, and qualifications, and analysis of growth history. Using generative AI and machine learning algorithms, the system multidimensionally analyzes each staff member's skill level, experience, qualification distribution, growth trends, and care history, and visualizes the organization's overall skill distribution, experience distribution, qualification distribution, and growth history as heatmaps and graphs. It also visualizes each staff member's skill growth history and training history over time, displaying growth trends and accumulated experience in graphs and charts. A concrete example of a prompt to be fed into the generative AI is: "Based on the following staff members' skill evaluation history and training history over the past three years, please graph their skill growth trends over time."

[0091] Step 5: Future Forecasting and Aptitude Analysis Using a generative AI, past data is learned to predict future skill improvement potential and aptitude. For example, staff members who have participated in multiple training sessions in the past and whose skill levels have steadily improved are judged to have potential for further growth and are recommended as potential leaders or specialists. An example of a prompt to be fed into the generative AI is to input: "Based on the following staff member's past skill evaluation history and training participation history, predict the skills that can be expected to improve in the next year and the reasons why."

[0092] Step 6: Optimizing Staffing and Training Plans Based on the analysis results from the analysis department, the system inputs the required care content, skill requirements, qualification requirements, and experience requirements for each user via a terminal. Using a generation AI, it automatically extracts staff members who meet all the relevant conditions from the database and generates optimal staffing plans and individually optimized training plans. For example, by inputting conditions such as "dementia care level 3 or higher," "communication ability level 4 or higher," "medical care level 2 or higher," and "certified care worker qualification holder," the AI ​​proposes the optimal team composition. A specific example of a prompt message to be fed into the generation AI is: "Please extract staff members who meet all of the following conditions and propose the optimal team composition considering the balance of skills and experience, past user history, current workload, and growth forecast."

[0093] Step 7: Display of analysis and recommendation results and feedback The system sends analysis and recommendation results from the server to terminals, allowing administrators and staff to view them in various formats such as graphs, lists, heatmaps, and dashboards. Administrators can view dashboards showing "optimal staffing plans for each user," "overall skill distribution," "training target lists," and "staff growth predictions," while staff members can also check their own skill evaluations, growth history, and recommended training content. Administrators can re-obtain recommendation results in real time by changing conditions or applying additional filters.

[0094] (Specific use cases)

[0095] For example, consider a care facility that accepts new residents requiring dementia care, where it is necessary to select the most suitable staff member and improve the staff's skills. In this case, the administrator uses the terminal interface to input multiple conditions as care requirements for the resident, such as "dementia care level 3 or higher," "communication ability level 4 or higher," "medical care level 2 or higher," "certified care worker qualification," "experience with night shifts," and "experience with family interviews." These conditions can be flexibly set based on the resident's condition, the family's wishes, and the facility's policies. Furthermore, if the administrator wants to consider the workload of the assigned staff member, their past work history, and their growth trend, they can also input additional conditions such as "currently assigned to 3 or fewer residents" and "showing an improving trend in dementia care skills over the past year."

[0096] This input information is sent to the recommendation department on the server, which then accesses data stored in the data storage unit, including all staff members' skill information, experience information, qualifications, client history, emergency response experience, infectious disease response experience, medical care implementation history, communication ability, dementia care experience, training attendance history, evaluation history, daily work reports, and free-text fields. The recommendation department utilizes a generation AI to generate a prompt message, for example, "Extract staff members who meet all of the following conditions, and propose the optimal staffing plan considering the balance of skills and experience, past client history, current workload, and growth forecast," and inputs this into the AI. The generation AI automatically extracts staff members who meet all the conditions, such as "Staff ID 123: Dementia care level 4, communication level 5, medical care level 3, certified care worker qualification, 2 night shift experiences, 5 family interview experiences, currently assigned 2 clients, dementia care skills improved from level 3 to level 4 in the past year," and then automatically generates the optimal staffing plan by comprehensively considering the balance of skills and experience, past client history, current workload, and growth trends.

[0097] Furthermore, the analysis department uses generating AI to visualize the skill distribution, experience distribution, and growth history of each staff member, outputting data such as "dementia care skill distribution," "medical care skill distribution," "communication ability distribution," "night shift experience distribution," and "family interview experience distribution" as heatmaps and graphs. In addition, based on each staff member's growth trends and past training history, it predicts the potential for future skill improvement and suitability, outputting analysis results such as "Staff ID 123's dementia care skills improved from level 3 to level 4 in the past year, and further growth can be expected" and "Staff ID 456's skills significantly improved after taking medical care training." This allows managers to select the most suitable personnel, taking into account not only the presence or absence of skills and experience, but also growth trends and future suitability.

[0098] Furthermore, the recommendation system automatically identifies staff members who do not meet the user's care requirements and generates individually optimized training plans. For example, it might recommend "Dementia Care Training A for staff with dementia care level below 3," "Medical Care Training B for staff with medical care level below 2," "Nighttime Simulation Training C for staff without nighttime response experience," or "Communication Training D for staff with limited family interview experience." The AI ​​automatically assigns the most suitable training content to each staff member. An example of a prompt message to the generating AI is: "Based on the following staff skill evaluations and training history, please suggest the most suitable training content to meet the user's care requirements."

[0099] In such use cases, the system enables administrators to efficiently and objectively formulate optimal staff allocation and skill development plans for each user and staff member, without having to individually review vast amounts of staff data. This is achieved through a series of steps: collecting and inputting staff information, storing and managing it in a database, AI analysis of unstructured data, visualization of skills, experience, and qualifications and analysis of growth history, future prediction and aptitude analysis, optimization of staff allocation and training plans, and display and feedback of analysis and recommendation results. This leverages the advanced analytical capabilities of the generating AI. As a result, it is possible to improve the quality of service in care settings, promote staff growth, increase user satisfaction, improve operational efficiency, and optimize human resource development throughout the organization.

[0100] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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.

[0101] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0102] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0103] For example, the data collection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart device 14 and processes it with the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the output device 40 of the smart device 14 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0104] 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.

[0105] [Second Embodiment]

[0106] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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).

[0109] 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, camera 42, and communication interface 44 are also connected to the bus 52.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0116] 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. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the identification processing unit 290 using these models.

[0117] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is realized by the data processing device 12 and the smart glasses 214. 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".

[0118] (Example 1)

[0119] Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0120] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0121] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0122] Furthermore, the processing by the data processing system 10 described above is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0123] For example, the data collection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the smart glasses 214 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0124] 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.

[0125] [Third Embodiment]

[0126] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0127] 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.

[0128] 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).

[0129] 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, display 343, and communication interface 44 are also connected to the bus 52.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the headset terminal 314. 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".

[0138] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0139] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0140] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0141] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] For example, the data collection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the headset terminal 314 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using generation AI. For example, the serving unit is implemented by the speaker 240 and display 343 of the headset terminal 314 or the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0143] 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.

[0144] [Fourth Embodiment]

[0145] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0146] 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.

[0147] 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).

[0148] 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, controlled object 443, and communication interface 44 are also connected to the bus 52.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. Each part of the system described below is implemented by the data processing device 12 and the robot 414. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0158] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.

[0159] (Application Example 1) Since the process flow is the same as in Application Example 1 described in the first embodiment above, the explanation will be omitted.

[0160] The specific processing unit 290 transmits the result of the specific processing obtained in the embodiment 1 or application example 1 described above 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.

[0161] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or external devices, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or external devices.

[0162] For example, the data collection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the acquisition unit acquires step count data using the camera 42 and communication I / F 44 of the robot 414 and processes it using the specific processing unit 290 of the data processing device 12. For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12 and analyzes the data from the data collection unit and the acquisition unit. For example, the generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a cooking menu using a generation AI. For example, the serving unit is implemented by the speaker 240 and controlled object 443 of the robot 414 and the specific processing unit 290 of the data processing device 12 and provides the generated cooking menu to the user. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0163] 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 robot 414.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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."

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] Furthermore, the following additional information is disclosed regarding the above explanation.

[0183] (Claim 1)

[0184] A system for managing diverse information such as the skills, experience, qualifications, and care history of care staff, and automatically formulating optimal staff assignments and training plans for each user, comprising: a data storage unit that stores information such as skill information, experience information, qualification information, user history, emergency response experience, infectious disease response experience, medical care implementation history, communication ability, dementia care experience, training attendance history, evaluation history, daily work reports, and free-text fields for each care staff member as a database; an analysis unit that automatically collects and analyzes the diverse information for each care staff member stored in the data storage unit using generative AI, and analyzes each staff member's skill level, experience, qualification distribution, growth trend, and care history using analysis algorithms including natural language processing and machine learning, and visualizes the skill distribution, experience distribution, qualification distribution, and growth history; and a recommendation unit that accepts the care content and skill conditions required for each user as input based on the analysis results of the analysis unit, automatically extracts staff members who meet the conditions and recommends them as candidates for staff assignment, and further automatically extracts staff members whose skill level is below a predetermined threshold and recommends them as individuals for optimized training, wherein at least a part of the processing of the analysis unit and the recommendation unit is performed by generative AI. (Claim 2)

[0185] The system according to claim 1, characterized in that the recommendation department accepts a combination of multiple care contents, skill requirements, qualification requirements, and experience requirements required for each user as input, automatically extracts staff who simultaneously meet the relevant multiple conditions, and automatically generates an optimal staffing plan using a generative AI, taking into account each staff member's skill level, experience, qualifications, past user history, current workload, and growth trend, and presents the visualized recommendation results to the manager. (Claim 3)

[0186] The system according to claim 1, characterized in that the aforementioned analysis unit manages time-series data such as skills, experience, qualifications, care history, training history, and evaluation history for each care staff member, uses generative AI to analyze past skill improvement trends, accumulated experience, and training effectiveness, predicts future skill improvement potential and suitability, and then the aforementioned recommendation unit supports the planning of future staff placement and training plans, taking these prediction results into consideration. [Explanation of Symbols]

[0187] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A system for optimizing personnel placement and training plans based on employee skills and experience, comprising: a data storage unit that stores employee skill information and experience information as a database; an analysis unit that automatically collects employee skill information and experience information stored in the data storage unit using generative AI, analyzes each employee's skill level and years of experience using analytical algorithms including natural language processing and machine learning, and visualizes the skill distribution and experience distribution; and a recommendation unit that accepts the required skill and experience conditions for each project and job content as input based on the analysis results by the analysis unit, automatically extracts employees who meet the conditions and recommends them as personnel placement candidates, and further automatically extracts employees whose skill level is below a predetermined threshold and recommends them as training candidates, wherein at least a part of the processing of the analysis unit and the recommendation unit is performed by generative AI.

2. The system according to claim 1, characterized in that the recommendation department accepts a combination of multiple skills and experience requirements for each project as input, automatically extracts employees who simultaneously meet the relevant conditions, automatically generates an optimal personnel placement plan using a generative AI, taking into account the balance of each employee's skill level and years of experience, and presents the visualized recommendation results to the person in charge.

3. The system according to claim 1, characterized in that the analysis department manages the trends and growth history of each employee's skills and experience as time-series data, analyzes past skill improvement trends and accumulated experience using generative AI, predicts future skill improvement potential and aptitude, and then the recommendation department supports the formulation of future personnel placement and training plans, taking the prediction results into consideration.

Citation Information

Patent Citations

  • Persona chatbot control method and system

    JP2022180282A