system
A generative AI-based system addresses HR challenges by objectively evaluating employee competencies from diverse data sources, optimizing personnel allocation and enhancing organizational performance and employee satisfaction.
Patent Information
- Application Number
- JP2025070037
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-04-21
- Publication Date
- 2026-11-02
AI Technical Summary
Existing HR systems struggle to comprehensively evaluate employee performance and optimize personnel allocation across departments, leading to suboptimal team performance, friction, and talent drain due to subjective evaluations and lack of consideration for teamwork compatibility.
A system utilizing generative AI to analyze diverse communication data from sources like meeting records, emails, and social media to quantify employee competencies and generate objective personnel allocation and evaluation proposals, considering multiple indicators and organizational strategies.
Enables fair and data-driven personnel allocation and performance evaluations, maximizing organizational performance, improving employee motivation, and promoting cross-departmental talent mobility.
Smart Images

Figure 2026175247000001_ABST
Abstract
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 including 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 that this invention aims to solve are: in personnel allocation and performance evaluation within an organization, it has traditionally been difficult for HR personnel to fully grasp the company's overall operations, the details of each department, and the characteristics, communication style, teamwork, leadership, and contributions of each individual employee. As a result, optimal personnel transfers and allocations across departments cannot be achieved, and it is difficult to formulate common evaluation criteria across the entire company, making it impossible to conduct fair and objective performance evaluations. Consequently, the overall performance of the organization and the output of teams are not maximized. Furthermore, the compatibility between employees and aspects of teamwork are not sufficiently considered, leading to friction and decreased performance in collaborative work. In addition, there is a risk of decreased motivation and talent drain due to the inappropriate evaluation of employee abilities and contributions. To solve these problems, this invention comprehensively collects diverse communication data such as meeting minutes, emails, chats, daily work reports, task management systems, and internal social media. It then uses generative AI to analyze and evaluate each employee's abilities, contributions, communication style, etc., using company-wide common criteria, and enables the automatic proposal and implementation of optimal personnel allocation and fair performance evaluations based on the analysis results. [Means for solving the problem]
[0005] The means for solving the problems according to the present invention comprises a system comprising a communication data collection unit, a capability analysis unit, and a human resources support unit. The communication data collection unit has the function of automatically and comprehensively collecting various internal communication data such as meeting records, emails, chats, daily work reports, task management systems, and internal social networking services, and centrally storing it including attribute information such as speaker, content of statement, time, related projects, and involved members. The capability analysis unit analyzes the communication data using generative AI and analyzes each employee's contribution level, cooperativeness, leadership, communication style, expertise, problem-solving ability, proposal ability, The system has the functionality to quantify multiple competency indicators, such as stress tolerance, influence within and outside the team, frequency of gratitude and apologies, tendencies in questioning and giving instructions, assertiveness and passivity in speech, and degree of cross-project involvement, using natural language processing and machine learning, and to statistically aggregate them based on company-wide common evaluation criteria. The Human Resources Support Department will use generative AI to automatically generate optimal personnel placement and personnel transfer proposals across departments based on each employee's competency indicators and communication style obtained by the Competency Analysis Department, and will also calculate evaluation scores and rankings to ensure fairness across the entire company, and will be configured to present specific transfer proposals and evaluation results to managers. [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 the data processing device and 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 storage with a reference sign is one or a plurality of non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include a flash memory (SSD (Solid State Drive)), a magnetic disk (for example, a hard disk), a magnetic tape, or the like.
[0012] In the following embodiments, the communication I / F (Interface) with a reference sign is an interface including a communication processor, an antenna, and the like. The communication I / F governs communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), and the like.
[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, may be only B, or may be a combination of A and B. Further, in the present specification, even when three or more matters are expressed in association with each other using "and / or", the same concept as that for "A and / or B" is applied.
[0014] [First Embodiment]
[0015] FIG. 1 illustrates 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 apparatus 12 and a smart device 14. An example of the data processing apparatus 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, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network), and the like.
[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, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, the camera 42, and the 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 detects contact of an indicator (for example, a pen, a finger, or the like), thereby receiving a user input by the contact of the indicator. The microphone 38B detects a user's voice, thereby receiving a voice-based user input. A 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, a specific processing unit 290 acquires the data indicating the user input.
[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.
[0021] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.
[0022] Figure 2 shows 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 detail. The system of the present invention consists of a server and a terminal. The server side is equipped with a communication data collection unit, a capability analysis unit, a personnel support unit, a database management unit, a security management unit, and the like. The terminal side is equipped with a user interface unit, a data input support unit, a notification management unit, and the like.
[0031] First, the communication data collection unit operates on a server and automatically collects data from various sources within the organization. For example, for meeting records, it transcribes meeting audio data using a speech recognition engine and extracts metadata such as the content of the speech, the time of the speech, the meeting name, the participant list, and the purpose and agenda of the meeting for each speaker. For email, it works in conjunction with the mail server to obtain information such as the sender, recipient, CC, BCC, date and time of sending, subject, body, attachment file name, and reply / forward history. For chat, it uses the internal chat system's API to collect user IDs, message content, sending time, stamps and reactions, thread information, and the relationship between quotes and replies. For daily work reports and task management systems, it uses APIs and data export functions to obtain information such as the person in charge, work content, progress status, report comments, task priority, deadline, related projects, and task dependencies. For internal social networking services, it collects information such as the poster, post content, comments, number of likes and shares, tags, and group information. Furthermore, data such as internal surveys, employee satisfaction surveys, 1-on-1 meeting records, internal awards history, training history, qualification acquisition information, and external seminar participation history can also be collected. This data is normalized by the database management department on the server, categorized by employee ID, project ID, time-series information, and data type, and access rights and privacy protection are strictly managed by the security management department.
[0032] Next, the capability analysis unit operates on a server and uses generative AI to analyze the collected data from multiple perspectives. The generative AI is composed of a combination of multiple AI engines, including large-scale language models, natural language processing models, sentiment analysis models, clustering models, and time series analysis models. For example, for text data of meeting records, the content of statements is divided according to context and classified into speech behaviors such as the gist and intent of the statements, emotional expressions, suggestions and instructions, problem raising, consensus building, counterarguments and agreements. For emails and chats, the frequency of exchanges, response speed, network structure of exchanges (who is exchanging with whom and to what extent), expressions of gratitude and apologies, number of questions and instructions, content of advice and support, frequency of collaboration with other departments, and presence or absence of business improvement suggestions are extracted. For daily work reports and task management data, the task completion rate, on-time delivery rate, response to delays, frequency and quality of progress reports, content of problem identification and solution proposals, and degree of cross-project involvement are analyzed. For internal social media and survey data, we extract information such as employee motivation, engagement, organizational contribution, influence on others, and the level of internal communication from the content of posts and comments.
[0033] Generative AI combines technologies such as natural language processing for key phrase extraction, topic modeling, sentiment analysis, contextual understanding, speech behavior classification, network analysis, clustering, anomaly detection, and time series forecasting to quantify multidimensional competency indicators for each employee, including contribution, collaborativeness, leadership, communication style, expertise, problem-solving ability, proposal ability, stress tolerance, influence within and outside the team, frequency of gratitude and apologies, tendencies in questions and instructions, assertiveness and passivity in speech, degree of cross-project involvement, innovation orientation, risk management ability, willingness to learn independently, and ability to mentor others. For example, an employee who says "I want to propose a new workflow" in a meeting is evaluated as having high proposal ability and leadership, while an employee who says "Please feel free to talk to me anytime if you have any problems" in a chat is evaluated as having high collaborativeness and support ability. An employee who handles tasks across multiple projects in the task management system and has a high on-time delivery rate is evaluated as having high cross-project contribution and reliability. An employee who actively comments on and advises others' posts on the company's internal social networking service is evaluated as having high influence and communication activity within the organization.
[0034] Furthermore, the generative AI comprehensively analyzes information such as employees' past transfer history, departments they work in, assigned projects, workload, team compatibility, overall organizational personnel structure, future business plans, and employees' career aspirations and self-reported information. For example, it analyzes performance changes of employees who have transferred in the past, performance trends under specific team configurations, and the gap between employees' career aspirations and actual work content, and uses this information to generate optimal personnel placement and transfer proposals. In addition, the generative AI can learn from feedback data from managers and employees, and continuously update its analysis models and evaluation criteria.
[0035] The HR Support Department operates on a server and uses generative AI to automatically generate optimal personnel placement and personnel transfer proposals across departments, based on each employee's competency indicators, communication style, work history, team composition, workload, and organizational strategy obtained from the Capability Analysis Department. For example, it may recommend an employee with strong leadership and collaboration skills, as well as experience working in multiple departments, as a candidate for a new project leader, or generate proposals to transfer an employee with strong expertise and problem-solving skills to a specific department. Furthermore, the generative AI automatically generates multiple transfer scenarios and presents the expected organizational performance, risk assessment, impact on employee satisfaction, and cost and resource allocation for each scenario. For example, it can perform scenario analysis such as determining that a particular transfer proposal would accelerate the progress of Project A, while simultaneously creating a risk of resource shortages for Project B.
[0036] Furthermore, to ensure fairness across the entire company, the Human Resources Support Department calculates evaluation scores and rankings based on competency indicators, assigning ranks such as S, A, B, and C, and presenting the evaluation results to managers. Evaluation scores are calculated comprehensively by weighting multiple competency indicators, not just a single indicator. For example, contribution might be 40%, teamwork 20%, leadership 20%, expertise 10%, and problem-solving ability 10%, and the weights can be adjusted according to organizational policies and job types.
[0037] The terminal unit is equipped with a user interface, allowing administrators, HR personnel, and employees to access the server to view transfer proposals and evaluation results, and to input feedback and self-reported information. For example, administrators can view a list of each employee's performance indicators, transfer proposals, and evaluation ranks through a dashboard screen on their terminal, and approve or revise transfer proposals and input feedback. Employees themselves can also check their own performance indicators and evaluation details, and input self-reported or supplementary information as needed. The notification management unit has the function of notifying terminals in real time of transfer proposals, evaluation results, and new feedback requests.
[0038] Generative AI plays an essential role in core system processing, for example, in semantic analysis of speech content using natural language processing, evaluation of stress tolerance and cooperativeness through sentiment analysis, determination of expertise and problem-solving ability through topic extraction, estimation of leadership and influence within and outside the team from the flow of conversation and frequency and content of interactions, comprehensive ability evaluation through integrated analysis of multiple data sources, automatic generation of transfer scenarios and automation of risk assessment, prediction of optimized future personnel placement by learning from past transfer patterns and historical data of organizational performance, and continuous improvement of analysis and proposal accuracy by learning from feedback from managers and employees. For example, generative AI can visualize employee speech patterns and communication networks, and identify key people and bottlenecks within the organization. Furthermore, it can propose future career paths and transfers / placements for skill development based on employees' career aspirations and self-reported information.
[0039] As described above, in the embodiments of the present invention, the server side performs key processes such as collection, storage, analysis, personnel support, and security management of communication data, while the terminal side provides a user interface, notifications, and data input support. This makes it possible to automatically optimize the personnel allocation and performance evaluation of the entire organization based on objective and fair criteria centered on generative AI. For example, decision-making regarding transfers and evaluations, which previously depended on the experience and subjectivity of HR personnel, can be realized in a data-driven and AI-led manner. This can yield a wide range of benefits, including maximizing organizational performance, improving employee motivation, utilizing the right people in the right places, promoting cross-departmental talent mobility, establishing a fair evaluation system, supporting employee career development, promoting organizational innovation, and early detection and response to risks.
[0040] (System Configuration)
[0041] The system according to this embodiment comprises a communication data collection unit, a capability analysis unit, a personnel support unit, a database management unit, a security management unit, a user interface unit, a data entry support unit, and a notification management unit. The communication data collection unit has the function of automatically collecting various communication and business-related data that occurs inside and outside the organization, such as meeting records, emails, chats, daily work reports, task management systems, internal SNS, survey systems, 1-on-1 meeting records, internal award history, training history, qualification acquisition information, and external seminar participation history. For example, for meeting records, the system converts the meeting recording data into text using a speech recognition engine and extracts metadata such as the content of the speech, the time of speech, the meeting name, the participant list, and the purpose and agenda of the meeting for each speaker. For emails, the system works in conjunction with the mail server to obtain the sender, recipient, CC, BCC, date and time of sending, subject, body, attachment file name, reply / forward history, etc. For chats, the system uses the API of the internal chat system to collect user IDs, message content, sending time, stamps and reactions, thread information, and the relationship between quotes and replies. For daily work reports and task management systems, APIs and data export functions are used to retrieve information such as assigned personnel, work content, progress status, report comments, task priority, deadline, related projects, and task dependencies. Furthermore, for internal social media, information such as posters, post content, comments, number of likes and shares, tags, and group information is collected. From survey systems and 1-on-1 meeting records, information such as employee satisfaction, awareness of issues, career aspirations, and feedback content is obtained.
[0042] The Capability Analysis Department utilizes generative AI to comprehensively analyze the diverse data collected by the Communication Data Collection Department. For example, for text data from meeting records, it divides the content of statements according to context and classifies speech behaviors such as the gist and intent of the statements, emotional expressions, suggestions and instructions, problem raising, consensus building, counterarguments and agreements. For emails and chats, it extracts information such as the frequency of exchanges, response speed, network structure of the exchanges, expressions of gratitude and apologies, the number of questions and instructions, the content of advice and support, the frequency of collaboration with other departments, and whether or not business improvement suggestions were made. For daily work reports and task management data, it analyzes the task completion rate, on-time delivery rate, response to delays, frequency and quality of progress reports, content of problem identification and solution proposals, and the degree of cross-project involvement. For internal social media and survey data, it extracts information such as employee motivation, engagement, organizational contribution, influence on others, and the activity level of internal communication from the content of posts and comments. Generative AI combines technologies such as natural language processing for key phrase extraction, topic modeling, sentiment analysis, contextual understanding, speech behavior classification, network analysis, clustering, anomaly detection, and time series forecasting to quantify multidimensional competency indicators for each employee, including contribution, collaborativeness, leadership, communication style, expertise, problem-solving ability, proposal ability, stress tolerance, influence within and outside the team, frequency of gratitude and apologies, tendencies in questions and instructions, assertiveness and passivity in speech, degree of cross-project involvement, innovation orientation, risk management ability, willingness to learn independently, and ability to mentor others. For example, an employee who says "I'd like to propose a new workflow" in a meeting is evaluated as having high proposal ability and leadership, while an employee who says "Please feel free to talk to me anytime if you have any problems" in a chat is evaluated as having high collaborativeness and support ability. An employee who handles tasks across multiple projects in the task management system and has a high on-time delivery rate is evaluated as having high cross-project contribution and reliability. An employee who actively comments on and advises others' posts on the company's internal social networking service is evaluated as having high influence and communication activity within the organization.
[0043] The Human Resources Support Department has the capability to automatically generate optimal personnel placement and personnel transfer proposals across departments using generative AI, based on each employee's competency indicators, communication style, work history, team composition, workload, and organizational strategy obtained from the Competency Analysis Department. For example, it can recommend employees with strong leadership and collaboration skills, as well as experience working in multiple departments, as candidates for new project leaders, or generate proposals to transfer employees with strong expertise and problem-solving abilities to specific departments. Furthermore, the generative AI automatically generates multiple transfer scenarios and presents the expected organizational performance, risk assessment, impact on employee satisfaction, and cost and resource allocation for each scenario. For example, it can perform scenario analysis to determine that in one transfer proposal, the progress of Project A would accelerate, while there is a risk of insufficient resources for Project B. In addition, to ensure fairness across the entire company, the Human Resources Support Department calculates evaluation scores and rankings based on competency indicators, assigning ranks such as S, A, B, and C, and presents the evaluation results to managers. The evaluation score is calculated comprehensively by weighting multiple competency indicators, not just a single indicator. For example, it is possible to adjust the weights according to organizational policies and job roles, such as 40% contribution, 20% teamwork, 20% leadership, 10% expertise, and 10% problem-solving ability.
[0044] The Database Management Department centrally stores and manages all data generated and acquired by the aforementioned departments, normalizes it by employee ID, project ID, time-series information, and data type, and performs high-speed searching, aggregation, backup, restore, and archiving as needed. For example, it can extract the meeting participation history of all employees for the past five years, analyze the communication patterns of employees involved in a specific project over time, and investigate the correlation between transfer history and performance changes.
[0045] The Security Management Department strictly controls access rights to various types of data, implementing measures such as encryption to protect privacy and prevent information leaks, access log recording, unauthorized access detection, data masking, anonymization of personal information, and storage of audit trails. For example, it can restrict access to detailed employee performance data to only HR personnel, control access so that employees can only view their own performance metrics, and restrict the removal of data outside the company.
[0046] The user interface unit operates on the terminal and provides screens and operational functions for administrators, HR personnel, and employees to access the server, view transfer proposals and evaluation results, and input feedback and self-reported information. For example, administrators can view a list of each employee's performance indicators, transfer proposals, and evaluation ranks on the dashboard screen, and approve or revise transfer proposals and input feedback. Employees themselves can also check their own performance indicators and evaluation details, and input self-reported or supplementary information as needed.
[0047] The Data Entry Support Department improves the efficiency and accuracy of data entry by automatically correcting input errors, automatically classifying input content, dynamically generating input forms, and automatically suggesting past input history for information entered by employees and managers from terminals. For example, in a self-declaration form, it can automatically display past input examples and related keywords for questions such as "Please describe any improvements you have made in your recent work."
[0048] The notification management unit has the function to notify terminals in real time of transfer proposals, evaluation results, new feedback requests, etc. For example, it can notify administrators with messages such as "A new transfer proposal has been generated" or "Feedback has been added to employee A's evaluation," and send reminders to employees such as "Your evaluation has been updated" or "The deadline for submitting your self-report is approaching."
[0049] Specific examples of prompts to be fed into the generative AI when implementing the present invention include, for example, "Analyze the following meeting record data and quantify each speaker's leadership, cooperativeness, proposal ability, problem-solving ability, and frequency of expressions of gratitude. Meeting record: Speaker A: 'I propose a new workflow,' Speaker B: 'I agree with that proposal,' Speaker C: 'One issue is that the deadline needs to be adjusted,'" or, "Classify each employee's communication style (proactive, passive, questioning, supportive, etc.) from the following chat history and aggregate the frequency. Chat history: Employee X: 'Please feel free to consult me anytime if you have any problems,' Employee Y: 'I have a question about this matter,' Employee Z: 'Thank you,'" or, "Evaluate each employee's on-times rate, degree of cross-project involvement, and problem-finding ability based on the following task management data. Task data: Employee M was in charge of tasks in both projects A and B, and completed all on time, Employee N proposed solutions when delays occurred in project C." Furthermore, prompts such as, "Based on the following employee transfer history, work history, performance indicators, team structure, workload, and organizational strategy, generate multiple optimal staffing plans and present the expected organizational performance and risk assessment for each scenario," can also be used.
[0050] (Implementation Steps)
[0051] Step 1: Automatic collection of communication data In this step, the communication data collection unit operates on the server and automatically and comprehensively collects a variety of communication and business-related data generated both inside and outside the organization, such as meeting records, emails, chats, daily work reports, task management systems, internal social networking services, survey systems, 1-on-1 meeting records, internal award history, training history, qualification acquisition information, and external seminar participation history. For example, meeting records are transcribed into text using a speech recognition engine, and metadata such as the content of the speech, time of speech, meeting name, participant list, and meeting purpose and agenda are extracted for each speaker. For emails, sender, recipient, CC, BCC, date and time of sending, subject, body, attachment file name, and reply / forward history are obtained. For chats, user ID, message content, time of sending, stamps and reactions, thread information, and the relationship between quotes and replies are collected. From daily work reports and task management systems, information such as the person in charge, work content, progress status, report comments, task priority, deadline, related projects, and task dependencies is obtained. From internal social networking services and survey systems, information such as the poster, post content, comments, number of likes and shares, tags, group information, satisfaction level and problem recognition, career aspirations, and feedback content is obtained.
[0052] Step 2: Accumulation and normalization into the database In this step, the database management department normalizes the various data mentioned above by employee ID, project ID, time-series information, and data type, and centrally stores them in a database on the server. For example, meeting record data is organized by meeting, speaker, and time-series; email and chat data are linked by conversation thread; and daily work reports and task management data are organized by project and task. This allows subsequent analysis, searching, aggregation, backup, restore, and archiving processes to be carried out efficiently.
[0053] Step 3: Security Management and Access Control In this step, the security management department strictly controls access permissions to various types of data, implementing measures such as encryption to protect privacy and prevent information leaks, access log recording, unauthorized access detection, data masking, anonymization of personal information, and storage of audit trails. For example, it is possible to restrict access to detailed employee evaluation data to only HR personnel, control access so that employees can only view their own evaluation metrics, and restrict the export of data to external parties.
[0054] Step 4: Ability and characteristic analysis by generated AI In this step, the Capability Analysis Department utilizes generative AI to analyze the collected data from multiple perspectives. The generative AI is composed of a combination of multiple AI engines, including large-scale language models, natural language processing models, sentiment analysis models, clustering models, and time series analysis models. For example, for text data from meeting records, the content of statements is divided according to context, and speech behaviors such as the gist and intent of the statements, emotional expressions, suggestions and instructions, problem raising, consensus building, counterarguments and agreements are classified. For emails and chats, the frequency of exchanges, response speed, network structure of exchanges, expressions of gratitude and apologies, number of questions and instructions, content of advice and support, frequency of collaboration with other departments, and presence or absence of business improvement suggestions are extracted. For daily work reports and task management data, the completion rate of tasks, on-time delivery rate, response to delays, frequency and quality of progress reports, content of problem identification and solution proposals, and degree of cross-project involvement are analyzed. For internal SNS and survey data, employee motivation, engagement, organizational contribution, influence on others, and the activity level of internal communication are extracted from the content of posts and comments. Generative AI combines technologies such as natural language processing for key phrase extraction, topic modeling, sentiment analysis, contextual understanding, speech behavior classification, network analysis, clustering, anomaly detection, and time series forecasting to quantify multidimensional competency indicators for each employee, including contribution, collaborativeness, leadership, communication style, expertise, problem-solving ability, proposal ability, stress tolerance, influence within and outside the team, frequency of gratitude and apologies, tendencies in questioning and giving instructions, assertiveness and passivity in speech, degree of cross-project involvement, innovation orientation, risk management ability, willingness to learn independently, and ability to mentor others. Specific examples of prompt texts to be fed into the generating AI include: "Analyze the following meeting record data and quantify each speaker's leadership, collaborativeness, proposal ability, problem-solving ability, and frequency of expressions of gratitude. Meeting record: Speaker A: 'I propose a new workflow,' Speaker B: 'I agree with that plan,' Speaker C: 'The issue is that the deadline needs to be adjusted.'" and "Classify each employee's communication style (proactive, passive, questioning, supportive, etc.) from the following chat history and compile the frequency."Examples of chat history include: "Employee X: 'Please feel free to talk to me anytime if you have any problems,' Employee Y: 'I have a question about this matter,' Employee Z: 'Thank you,'" and "Based on the following task management data, please evaluate each employee's on-time delivery rate, degree of cross-project involvement, and problem-solving ability. Task data: Employee M was in charge of tasks in both Project A and B, and completed all on time; Employee N proposed solutions when delays occurred in Project C."
[0055] Step 5: Generation of transfer and evaluation proposals using HR support AI In this step, the Human Resources Support Department uses generative AI to automatically generate optimal personnel placement and personnel transfer proposals across departments, based on each employee's competency indicators, communication style, work history, team composition, workload, and organizational strategy obtained from the Competency Analysis Department. For example, it might recommend an employee with strong leadership and collaborative skills, as well as experience working in multiple departments, as a candidate for a new project leader, or generate proposals to transfer an employee with strong expertise and problem-solving skills to a specific department. Furthermore, the generative AI automatically generates multiple transfer scenarios, along with the expected organizational performance, risk assessment, impact on employee satisfaction, and cost and resource allocation for each scenario. A specific example of a prompt to be fed into the generative AI would be: "Based on the following employee transfer history, work history, competency indicators, team composition, workload, and organizational strategy, generate multiple optimal personnel placement proposals, and present the expected organizational performance and risk assessment for each scenario."
[0056] Step 6: Presenting results and obtaining feedback through the user interface. In this step, the user interface operates on the terminal, providing administrators, HR personnel, and employees with screens and operational functions to access the server, view transfer proposals and evaluation results, and input feedback and self-reported information. For example, administrators can view each employee's performance indicators, transfer proposals, and evaluation ranks in a list on the dashboard screen, and approve or revise transfer proposals and input feedback. Employees themselves can also check their own performance indicators and evaluation details, and input self-reported or supplementary information as needed.
[0057] Step 7: Operational support through notifications and reminders In this step, the notification management unit has the function to notify terminals in real time of transfer proposals, evaluation results, new feedback requests, etc. For example, it can notify administrators with messages such as "A new transfer proposal has been generated" or "Feedback has been added to employee A's evaluation," and send reminders to employees such as "Your evaluation has been updated" or "The deadline for submitting your self-report is approaching."
[0058] (Specific use cases)
[0059] For example, consider a use case where the optimal project members and leaders are selected when launching a new business project within an organization. In this case, the communication data collection department automatically collects all relevant employee communication and work data from the past year, including meeting records, emails, chats, daily work reports, task management systems, internal social networking services, survey systems, 1-on-1 meeting records, training history, and qualification acquisition information. For meeting records, metadata such as the content of the speech transcribed into text by a speech recognition engine, the speaker, the time of the speech, the meeting name, participant list, and agenda are extracted. For emails, sender, recipient, date and time of sending, subject, body, attachment file name, and reply / forward history are obtained. For chats, user ID, message content, time of sending, stamps and reactions, thread information, and the relationship between quotes and replies are collected. The task management system retrieves information such as the person in charge, the work content, progress status, report comments, task priority, deadline, related projects, and task dependencies. The internal social networking service and survey system retrieve information such as the poster, post content, comments, number of likes and shares, tags, group information, satisfaction level and awareness of issues, career aspirations, and feedback content.
[0060] Next, the Capability Analysis Department uses generative AI to analyze the collected data from multiple perspectives. The generative AI classifies speech behaviors such as the gist and intent of statements, emotional expressions, suggestions and instructions, problem raising, consensus building, counterarguments and agreements from the text data of meeting records. From email and chat exchanges, it extracts frequency, response speed, network structure, expressions of gratitude and apologies, number of questions and instructions, content of advice and support, frequency of collaboration with other departments, and presence or absence of business improvement suggestions. From task management data, it analyzes task completion rates, on-time delivery rates, responses when delays occur, frequency and quality of progress reports, content of problem identification and solution proposals, and degree of cross-project involvement. From internal SNS and survey data, it extracts motivation, engagement, organizational contribution, influence on others, and the activity level of internal communication based on the content of posts and comments. Based on these analysis results, we quantify multidimensional competency indicators for each employee, including contribution, teamwork, leadership, communication style, expertise, problem-solving ability, proposal ability, stress tolerance, influence within and outside the team, frequency of expressing gratitude and apologies, tendencies in asking questions and giving instructions, proactiveness and passivity in speaking, degree of cross-project involvement, innovation orientation, risk management ability, willingness to learn independently, and ability to develop others.
[0061] The Human Resources Support Department uses generative AI to automatically generate optimal staffing plans and leader candidates for new business projects, based on each employee's competency indicators, communication style, work history, team structure, workload, and organizational strategy obtained from the Competency Analysis Department. For example, it recommends employees with strong leadership and collaboration skills, experience in multiple departments, and a history of high performance as project leaders as leader candidates, and selects employees with strong expertise and problem-solving abilities as project members. The generative AI also automatically generates multiple staffing scenarios, presenting expected organizational performance, risk assessments, impact on employee satisfaction, and cost and resource allocation for each scenario. For example, in one scenario, it analyzes that while the progress of Project A will accelerate, there is a risk of insufficient resources for existing operations.
[0062] The user interface section allows administrators and HR personnel to access the server and view a dashboard displaying generated personnel placement proposals, leader candidates, each employee's performance indicators, and evaluation ranks, enabling them to approve or revise transfer proposals and input feedback. Employees themselves can also check their own performance indicators and evaluation details and input self-reports and supplementary information as needed. The notification management section notifies terminals in real time of transfer proposals, evaluation results, and new feedback requests, sending notifications to administrators such as "A personnel placement proposal has been generated for a new project" and "Feedback has been added to employee A's evaluation," and sending reminders to employees such as "Your evaluation has been updated" and "The deadline for submitting your self-report is approaching."
[0063] Specific examples of prompt text to be fed into the generating AI include: "Analyze the following meeting records, email history, chat history, task management data, internal SNS posts, and survey responses to quantify each employee's leadership, collaborativeness, expertise, problem-solving ability, degree of cross-project involvement, and communication style. Furthermore, generate multiple candidate leader and optimal member configurations for new business projects, and present the expected organizational performance and risk assessment for each proposal. Meeting records: Speaker A: 'I propose a new workflow,' Speaker B: 'I agree with that proposal,' Speaker C: 'The issue is that the deadline needs to be adjusted.' Chat history: Employee X: 'Please feel free to talk to me anytime if you have any problems,' Employee Y: 'I have a question about this matter,' Employee Z: 'Thank you.' Task data: Employee M is in charge of tasks in both projects A and B, and has completed all on time, Employee N has proposed solutions when delays occur in project C."
[0064] Thus, by using the system of the present invention, it is possible to comprehensively and automatically collect and analyze diverse communication and business data within an organization, evaluate the abilities and characteristics of employees using generative AI based on objective and fair criteria, and achieve optimal personnel allocation, project member selection, leader candidate recommendation, transfer proposal generation, improved organizational performance, risk reduction, and increased employee satisfaction.
[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 with greater specificity. The system of the present invention consists of multiple functional units, such as a care data collection unit, a capability analysis unit, a personnel allocation support unit, a database management unit, a security management unit, a user interface unit, and a notification management unit, and each unit operates in cooperation with the server and terminal.
[0068] First, the care data collection department automatically and comprehensively collects all data generated in care facilities and home care settings using a variety of means. For example, regarding care records, it collects detailed information such as meal assistance, toileting assistance, bathing assistance, medication management, rehabilitation support, monitoring, recreational activities, transfer / mobility assistance, repositioning, oral care, changes in toileting patterns, pressure ulcer care, infection control, changes in the user's condition, vital signs, presence or absence of abnormalities, care innovations, user reactions, requests and complaints from family members, the user's life history and hobbies / preferences, and the implementation status of individual care plans, all of which are entered by staff using tablet devices or voice input systems. Regarding handover records, it collects information such as the status of nighttime monitoring shared among staff during shift changes, precautions for users at high risk of falls, special notes to prevent medication errors, emergency response history, individual considerations for each user, the status of coordination among staff, the occurrence of communication omissions and misunderstandings during handovers, the quality and quantity of handover content, and the emotional expressions and tone during handovers. Communication logs with users include recording daily conversations, greetings, encouragement, explanations, consultations, interactions during visits with family, requests and complaints from users, words of gratitude, changes in the user's psychology, how to handle users with dementia, how to address feelings of loneliness and anxiety, and interactions related to supporting the user's independence. Emergency response records include detailed information on falls, sudden changes in condition, aspiration, fever, ambulance transport, coordination with medical institutions, emergency contact with family, initial response to the incident, follow-up observations after the incident, implementation of preventative measures, coordination among staff at the time of the incident, and explanations given to the user and family at the time of the incident. Family communication records include regular contacts, interview records, care plan explanations, requests and complaints from family, messages of gratitude, family participation in care, psychological support for family, coordination between family wishes and on-site care policies, and efforts to build trust with family. The staff chat system is used to collect information regarding work-related matters, shift adjustments, sudden absence notifications, suggestions for work improvements, daily consultations and encouragement, rapid information sharing in the event of problems, emotional support among staff, resolution of disagreements among staff, and knowledge sharing and expertise transfer among staff.For shift management data, we collect information such as each staff member's working days, working hours, assigned clients, night / day shift assignments, history of sudden shift changes, staff's preferred shifts, overtime status, fairness of shifts, discrepancies between preferred and actual assignments, and the level of cooperation among staff during shift adjustments. For training history, we collect information on dementia care training, infectious disease control training, medical care training, leadership training, participation in external seminars, qualification acquisition history, self-study history, e-learning completion history, impressions and feedback from training participants, and the practical application of training content in the field. For accident and near-miss reports, we record information such as falls, medication errors, aspiration, pica, violent behavior, complaints, attempted incidents, circumstances at the time of the accident, post-accident response, accident cause analysis, proposed and implemented measures to prevent recurrence, quality of the accident report, and the level of cooperation among staff at the time of the accident. User feedback is collected from users and their families through questionnaires, satisfaction surveys, free-response evaluations, expressions of gratitude and dissatisfaction, requests regarding care content, evaluations of the user's quality of life (QOL), the user's psychological satisfaction, evaluations of improvements in the user's independence, and the user's satisfaction with social participation and recreational activities. Care plan creation history is recorded through care managers and multidisciplinary collaboration, including the history of care plan creation and revision, goal setting, achievement status, identification of issues, improvement suggestions, individuality of the care plan, implementation status of the care plan, and opinions of staff and family members regarding the care plan.
[0069] The capability analysis unit has the function of analyzing the aforementioned caregiving-related data from multiple perspectives and in a sophisticated manner using generative AI. For example, from text data such as care records and handover records, we can gather information on each staff member's care quality (careful assistance, awareness of changes in the user's condition, practice of individual consideration, contribution to improving the user's QOL), teamwork (cooperation with other staff, thoroughness of handovers, teamwork, building trust among staff), responsiveness (quick judgment and action in emergencies, calm response in times of trouble, flexible response to unexpected situations), expertise (utilization of knowledge of dementia care and medical care, reflection of training history, professional assessment ability), stress tolerance (stable response during busy periods and times of trouble, emotional control, maintaining performance during long working hours), user satisfaction (gratitude and high praise from users and their families, contribution to the user's psychological stability), emergency response ability (appropriate initial response in the event of an accident, cooperation with medical institutions, demonstrating leadership in emergencies), communication style (encouraging, explanatory, standard, passive, proactive, listening, directing, empathetic, etc.), and education / training history (content of courses taken, qualifications obtained, motivation for self-learning, training content) Multidimensional competency indicators such as the degree of practical application of skills in the field, accident response history (degree of implementation of recurrence prevention measures, calm response at the time of the accident, follow-up after the accident), ability to deal with families (building trust with families, responding to requests, providing psychological support to families, dealing with disputes with families), influence inside and outside the team (advising and supporting other staff, demonstrating leadership, contributing to improving the morale of the entire team), frequency of gratitude and apologies (expressions of gratitude and apologies to users, families, and colleagues, sincere response in the event of a dispute), tendency in asking questions and giving instructions (proactive suggestions and instructions, passive responses, frequency of suggesting improvements to the field), assertiveness and passivity of speech (frequency and content of speeches in meetings and chats, assertiveness in suggesting improvements to the field), and degree of cross-project involvement (participation in collaboration with multiple units and multidisciplinary teams, degree of involvement in facility-wide events and committee activities) are quantified by combining multiple AI technologies such as natural language processing, sentiment analysis, topic extraction, network analysis, clustering, anomaly detection, and time series analysis, and statistically compiled based on evaluation criteria common to all facilities. For example, if the handover record states, "Staff member A calmly handled multiple sudden changes in the condition of several residents during the night shift," then their stress tolerance and emergency response ability scores will be higher.If user feedback includes a comment like, "Staff B's words were encouraging," then the communication style will be counted as supportive. Accident and near-miss reports allow for evaluation of the degree to which recurrence prevention measures are implemented and risk management capabilities. Training history and qualification acquisition information allow for evaluation of expertise and motivation for self-learning. Records of communication with family members allow for evaluation of family support skills and trust-building abilities. Staff chats can also be used to evaluate the level of cooperation among staff, the activity level of knowledge sharing, the speed of information sharing in the event of trouble, and the degree to which psychological support is provided among staff.
[0070] The Staffing Support Department integrates information obtained from the Competency Analysis Department, including each staff member's competency indicators and communication style, the level of care required and medical care needs of users, the overall staffing situation of the facility, shift balance, the condition and needs of users, past placement history, workload, team compatibility information, facility management policies, and staff members' career aspirations and self-reported information. Using generative AI, it automatically generates optimal staff placement plans, assignment plans, team formation plans, leader candidate recommendations, evaluation scores, and rankings, and presents concrete placement proposals and evaluation results to managers. For example, staff members with high care quality and user satisfaction are assigned to users with high care needs, while staff members with high cooperativeness and leadership skills are assigned as team leaders or new employee trainers. Staff members with high expertise and emergency response capabilities are assigned to users requiring medical care or to night shifts. Considering staff members' career aspirations and self-reported information, it also generates placement plans that reflect their wishes and growth opportunities. It automatically generates multiple transfer and placement scenarios, and for each scenario, it also presents the expected care quality, risk assessment, and impact on staff satisfaction and work efficiency. For example, in one scenario, distributing highly leadership-oriented staff across multiple units can improve overall performance, while in another scenario, concentrating highly specialized staff in specific units can enhance the quality of medical care. Furthermore, analysis of staff's past transfer history, performance changes, performance trends in team formations, and the gap between staff's career aspirations and actual job responsibilities can be used to generate optimal staffing and transfer plans.
[0071] The Database Management Department centrally stores and manages all data generated and acquired by the aforementioned departments, normalizing it by staff ID, user ID, project ID, time-series information, and data type, and performing high-speed searches, aggregations, backups, restores, and archiving processes as needed. For example, it can extract care records and handover histories of all staff over the past few years, analyze communication patterns of staff involved with specific users over time, and investigate the correlation between staffing history and changes in care quality.
[0072] The Security Management Department strictly controls access rights to various types of data, implementing measures such as encryption to protect privacy and prevent information leaks, access log recording, unauthorized access detection, data masking, anonymization of personal information, and storage of audit trails. For example, it can restrict access to detailed evaluation data for all staff members to administrators only, control staff members so they can only view their own evaluation metrics, and restrict the removal of data outside the company.
[0073] The user interface section provides screens and operational functions for administrators, team leaders, and staff members to access the server, view placement proposals and evaluation results, and input feedback and self-reported information. For example, administrators can view a list of each staff member's competency indicators, placement proposals, and evaluation ranks on the dashboard screen, and approve or revise placement proposals and input feedback. Staff members themselves can also check their own competency indicators and evaluation details, and input self-reported or supplementary information as needed. Furthermore, it is possible to propose future career paths and transfers / placements for skill development based on staff members' career aspirations and self-reported information.
[0074] The notification management unit has the function of notifying terminals in real time of placement proposals, evaluation results, and new feedback requests. For example, it can notify administrators with messages such as "A new placement proposal has been generated" or "Feedback has been added to Staff A's evaluation," and send reminders to staff members such as "Your evaluation has been updated" or "The deadline for submitting your self-report is approaching."
[0075] Thus, in the embodiments of the present invention, all operational and communication data generated in nursing care settings are comprehensively collected and analyzed, and the characteristics and strengths of each staff member are objectively visualized by utilizing the capabilities of generative AI. This enables the automatic proposal and implementation of optimal staffing and evaluation according to the user's condition and the facility's operational status. This can bring about multifaceted and sustainable effects, such as improving the quality of services in nursing care settings, ensuring staff are placed in appropriate positions, increasing operational efficiency, establishing a fair evaluation system, improving user satisfaction, supporting staff career development, enabling early detection and response to risks, optimizing facility operations, increasing staff motivation, reducing turnover rates, promoting innovation in the field, strengthening trust with families, and strengthening regional cooperation.
[0076] (System Configuration)
[0077] The system according to this embodiment comprises a care data collection unit, a capability analysis unit, a staffing support unit, a database management unit, a security management unit, a user interface unit, and a notification management unit. The care data collection unit has the function of automatically and comprehensively collecting various data generated in care facilities and home care settings. For example, it collects detailed information such as meal assistance, excretion assistance, bathing assistance, medication management, rehabilitation support, monitoring, recreational activities, transfer / mobility assistance, position changes, oral care, changes in excretion patterns, pressure ulcer care, infection control measures, changes in the user's condition, vital signs, presence or absence of abnormalities, points of care innovation, user reactions, requests and complaints from family members, the user's life history and hobbies / preferences, and the implementation status of individual care plans, which are entered by staff using tablet terminals or voice input systems. Furthermore, as part of the shift change handover records, we collect information on nighttime monitoring status, precautions for users at high risk of falling, special notes to prevent medication errors, emergency response history, individual considerations for each user, the status of coordination among staff, instances of communication omissions or misunderstandings during handovers, the quality and quantity of handover content, and the emotional expressions and tone during handovers. In addition, as a communication log with users, we record daily conversations, greetings, encouragement, explanations, consultations, interactions during visits with family members, requests and complaints from users, words of gratitude, changes in the user's psychology, how we dealt with users with dementia, how we addressed users' feelings of loneliness and anxiety, and interactions related to supporting users' independence. In addition, we collect detailed emergency response records, including falls, sudden changes in condition, aspiration, fever, ambulance transport, coordination with medical institutions, emergency contact with family, initial response to accidents, follow-up observations after accidents, implementation status of recurrence prevention measures, the status of coordination among staff during accidents, and the content of explanations given to users and their families during accidents. Family communication records include regular contacts, meeting records, care plan explanations, requests and complaints from family members, messages of gratitude, family participation in caregiving, family psychological support, adjustments between family wishes and on-site care policies, and efforts to build trust with family members. Staff chat records include work-related communication, shift adjustments, sudden absence notifications, suggestions for work improvement, daily consultations and encouragement, rapid information sharing in case of trouble, emotional support among staff, resolution of conflicts and disagreements among staff, and knowledge sharing and know-how transfer among staff.Shift management data includes each staff member's working days, working hours, assigned clients, night / day shift assignments, history of sudden shift changes, staff's preferred shifts, overtime status, fairness of shifts, discrepancies between preferred and actual assignments, and the level of cooperation among staff during shift adjustments. Training history includes dementia care training, infectious disease control training, medical care training, leadership training, external seminar participation history, qualification acquisition history, self-study history, e-learning completion history, impressions and feedback from training participants, and the practical application of training content in the field. Accident and near-miss reports record falls, medication errors, aspiration, pica, violent behavior, complaints, attempted incidents, circumstances at the time of the accident, post-accident response, accident cause analysis, proposed and implemented recurrence prevention measures, quality of accident report content, and the level of cooperation among staff at the time of the accident. User feedback is collected from users and their families through questionnaires, satisfaction surveys, free-response evaluations, expressions of gratitude and dissatisfaction, requests regarding care content, evaluations of the user's quality of life, the user's psychological satisfaction, evaluations of improvements in the user's independence, and the user's satisfaction with social participation and recreational activities. Care plan creation history is recorded through care managers and multidisciplinary collaboration, including the history of care plan creation and revision, goal setting, achievement status, identification of issues, improvement suggestions, individuality of the care plan, implementation status of the care plan, and opinions of staff and family members regarding the care plan.
[0078] The Capability Analysis Department has the function of using generative AI to analyze the aforementioned care-related data from multiple perspectives and with high precision. For example, from text data of care records and handover records, it analyzes the care quality of each staff member (careful assistance, awareness of changes in the user's condition, practice of individual consideration, contribution to improving the user's QOL), teamwork (cooperation with other staff, thoroughness of handover, teamwork, building trust among staff), responsiveness (quick judgment and action in emergencies, calm response in times of trouble, flexible response to unexpected situations), and expertise (dementia care, etc.). Utilization of medical care knowledge, reflection of training history, professional assessment ability), stress tolerance (stable response during busy periods and troubles, emotional control, maintaining performance during long working hours), user satisfaction (gratitude and high praise from users and their families, contribution to the psychological stability of users), emergency response ability (appropriate initial response in the event of an accident, collaboration with medical institutions, demonstrating leadership in emergencies), communication style (encouraging, explanatory, standard, passive, proactive, listening, directing, empathetic, etc.), education and training history ( Multidimensional competency indicators such as course content, qualification acquisition status, motivation for self-learning, degree of practical application of training content, accident response history (degree of implementation of recurrence prevention measures, calm response at the time of the accident, follow-up after the accident), ability to deal with families (building trust with families, responding to requests, providing psychological support to families, handling disputes with families), influence inside and outside the team (advising and supporting other staff, demonstrating leadership, contributing to improving the morale of the entire team), frequency of gratitude and apologies (expressions of gratitude and apologies to users, families, and colleagues, sincere response in the event of a problem), tendency in asking questions and giving instructions (proactive suggestions and instructions, passive responses, frequency of suggesting improvements to the workplace), assertiveness and passivity of speech (frequency and content of speeches in meetings and chats, assertiveness of suggesting improvements to the workplace), and degree of cross-project involvement (participation in collaboration with multiple units and multidisciplinary teams, degree of involvement in facility-wide events and committee activities) are quantified by combining multiple AI technologies such as natural language processing, sentiment analysis, topic extraction, network analysis, clustering, anomaly detection, and time series analysis, and statistically compiled based on evaluation criteria common to all facilities. For example, if the handover record states, "Staff member A calmly handled multiple sudden changes in the condition of several residents during the night shift," then their stress tolerance and emergency response ability scores will be higher.If user feedback includes a comment like, "Staff B's words were encouraging," then the communication style will be counted as supportive. Accident and near-miss reports allow for evaluation of the degree to which recurrence prevention measures are implemented and risk management capabilities. Training history and qualification acquisition information allow for evaluation of expertise and motivation for self-learning. Records of communication with family members allow for evaluation of family support skills and trust-building abilities. Staff chats can also be used to evaluate the level of cooperation among staff, the activity level of knowledge sharing, the speed of information sharing in the event of trouble, and the degree to which psychological support is provided among staff. Specific examples of prompts to be fed into the generating AI include: "Analyze the following care records, handover records, user feedback, emergency response records, family communication records, staff chats, training history, and accident / near-miss reports, and quantify each staff member's care quality, teamwork, responsiveness, expertise, stress tolerance, user satisfaction, emergency response ability, communication style, education / training history, accident response history, family support ability, influence inside and outside the team, frequency of gratitude and apologies, tendency to ask questions and give instructions, proactiveness or passivity in speech, and degree of cross-project involvement."
[0079] The Staffing Support Department integrates information obtained from the Competency Analysis Department, including each staff member's competency indicators and communication style, the level of care required and medical care needs of users, the overall staffing situation of the facility, shift balance, the condition and needs of users, past placement history, workload, team compatibility information, facility management policies, and staff members' career aspirations and self-reported information. Using generative AI, it automatically generates optimal staff placement plans, assignment plans, team formation plans, leader candidate recommendations, evaluation scores, and rankings, and presents concrete placement proposals and evaluation results to managers. For example, staff members with high care quality and user satisfaction are assigned to users with high care needs, while staff members with high cooperativeness and leadership skills are assigned as team leaders or new employee trainers. Staff members with high expertise and emergency response capabilities are assigned to users requiring medical care or to night shifts. Considering staff members' career aspirations and self-reported information, it also generates placement plans that reflect their wishes and growth opportunities. It automatically generates multiple transfer and placement scenarios, and for each scenario, it also presents the expected care quality, risk assessment, and impact on staff satisfaction and work efficiency. For example, in one scenario, it might be possible to improve overall performance by distributing highly skilled leadership staff across multiple units, while in another scenario, it might be possible to improve the quality of medical care by concentrating highly specialized staff in specific units.
[0080] The Database Management Department centrally stores and manages all data generated and acquired by the aforementioned departments, normalizing it by staff ID, user ID, project ID, time-series information, and data type, and performing high-speed searches, aggregations, backups, restores, and archiving processes as needed. For example, it can extract care records and handover histories of all staff over the past few years, analyze communication patterns of staff involved with specific users over time, and investigate the correlation between staffing history and changes in care quality.
[0081] The Security Management Department strictly controls access rights to various types of data, implementing measures such as encryption to protect privacy and prevent information leaks, access log recording, unauthorized access detection, data masking, anonymization of personal information, and storage of audit trails. For example, it can restrict access to detailed evaluation data for all staff members to administrators only, control staff members so they can only view their own evaluation metrics, and restrict the removal of data outside the company.
[0082] The user interface section provides screens and operational functions for administrators, team leaders, and staff members to access the server, view placement proposals and evaluation results, and input feedback and self-reported information. For example, administrators can view a list of each staff member's competency indicators, placement proposals, and evaluation ranks on the dashboard screen, and approve or revise placement proposals and input feedback. Staff members themselves can also check their own competency indicators and evaluation details, and input self-reported or supplementary information as needed. Furthermore, it is possible to propose future career paths and transfers / placements for skill development based on staff members' career aspirations and self-reported information.
[0083] The notification management unit has the function of notifying terminals in real time of placement proposals, evaluation results, and new feedback requests. For example, it can notify administrators with messages such as "A new placement proposal has been generated" or "Feedback has been added to Staff A's evaluation," and send reminders to staff members such as "Your evaluation has been updated" or "The deadline for submitting your self-report is approaching."
[0084] (Implementation Steps)
[0085] Step 1: Comprehensive automated collection of care-related data In this step, the care data collection department automatically and comprehensively collects diverse data generated in care facilities and home care settings. Specifically, it collects detailed information such as meal assistance, toileting assistance, bathing assistance, medication management, rehabilitation support, monitoring, recreational activities, transfer / mobility assistance, repositioning, oral care, changes in toileting patterns, pressure ulcer care, infection control, changes in the user's condition, vital signs, presence or absence of abnormalities, care innovations, user reactions, requests and complaints from family members, the user's life history and hobbies / preferences, and the implementation status of individual care plans, all entered by staff using tablet devices or voice input systems. In addition, handover records during shift changes, communication logs with users, emergency response records, contact records with family members, staff chats, shift management data, training history, accident / near-miss reports, user feedback, and care plan creation history are collected in various formats and centrally stored in the database management department.
[0086] Step 2: Data normalization, storage, and security management In this step, the database management department normalizes the various data according to staff ID, user ID, time series, and data type, and centrally stores it in a database on the server. This includes data duplication, data completion, formatting standardization, timestamping, and linking related data. The security management department implements access control, encryption for privacy protection, access log recording, unauthorized access detection, data masking, personal information anonymization, and audit trail storage, ensuring that only administrators can access detailed evaluation data and that staff members can view only their own evaluation metrics.
[0087] Step 3: Multidimensional capability analysis using generative AI In this step, the competency analysis department uses generative AI to comprehensively analyze diverse data such as care records, handover records, user feedback, emergency response records, communication records with families, staff chats, training history, and accident / near-miss reports. The generative AI combines multiple AI technologies, including natural language processing, sentiment analysis, topic extraction, network analysis, clustering, anomaly detection, and time series analysis, to quantify multidimensional competency indicators such as care quality, teamwork, responsiveness, expertise, stress tolerance, user satisfaction, emergency response ability, communication style, education / training history, accident response history, family interaction ability, influence within and outside the team, frequency of gratitude and apologies, tendencies in questions and instructions, assertiveness and passivity in speech, and degree of cross-project involvement. These indicators are then statistically aggregated based on evaluation criteria common to all facilities. Specific examples of prompts to be fed into the generating AI include: "Analyze the following care records, handover records, user feedback, emergency response records, family communication records, staff chats, training history, and accident / near-miss reports, and quantify each staff member's care quality, teamwork, responsiveness, expertise, stress tolerance, user satisfaction, emergency response ability, communication style, education / training history, accident response history, family support ability, influence inside and outside the team, frequency of gratitude and apologies, tendency to ask questions and give instructions, proactiveness or passivity in speech, and degree of cross-project involvement."
[0088] Step 4: Automatic generation of optimal placement and evaluation proposals using AI. In this step, the Staffing Support Department integrates information obtained from the Competency Analysis Department, including each staff member's competency indicators and communication style, the level of care required and medical care needs of users, the overall staffing situation of the facility, shift balance, the condition and needs of users, past staffing history, workload, team compatibility information, facility management policies, and staff career aspirations and self-reported information. Using a generative AI, it automatically generates optimal staffing plans, assignment plans, team formation plans, leader candidate recommendations, evaluation scores, and rankings, presenting concrete staffing proposals and evaluation results to managers. An example of a prompt message to be fed into the generative AI is: "Based on the following staff competency indicators, user information, shift status, workload, past staffing history, team compatibility, and career aspirations, generate optimal staffing plans and multiple scenarios, and also present the impact on care quality, risk assessment, staff satisfaction, and work efficiency for each."
[0089] Step 5: Presenting results and obtaining feedback through the user interface. In this step, the user interface unit presents placement proposals and evaluation results to administrators, team leaders, and staff members themselves via dashboards and individual screens, enabling them to approve and revise placement plans, provide feedback, and input self-reported information. Administrators can view a list of each staff member's competency indicators, placement proposals, and evaluation ranks, while staff members can also review their own competency indicators and evaluation details, and input self-reported or supplementary information as needed.
[0090] Step 6: Operational support through notifications and reminders In this step, the notification management department notifies terminals in real time of placement proposals, evaluation results, new feedback requests, and self-reporting deadlines. Administrators receive notifications such as "A new placement proposal has been generated" and "Feedback has been added to Staff A's evaluation," while staff receive reminders such as "Your evaluation has been updated" and "The deadline for submitting your self-report is approaching."
[0091] (Specific use cases)
[0092] For example, when a nursing care facility accepts multiple new residents, it is assumed that the care level of each resident, medical care needs, presence or absence of dementia, requests from family members, life history, hobbies and preferences, and psychological tendencies are known in advance. In this case, the care data collection department comprehensively collects past care records of existing staff, handover records, user feedback, emergency response records, communication records with family members, staff chats, shift management data, training history, accident / near-miss reports, care plan creation history, etc., and stores diverse data such as each staff member's work content, response history, communication tendencies, expertise, accident response experience, ability to deal with families, influence within and outside the team, stress tolerance, and motivation for self-learning in a database. The competency analysis department uses generative AI to quantify each staff member's competency indicators in multiple dimensions, generating competency profiles for all staff members. For example, it might say, "Staff member X has attended dementia care training multiple times and has many records of practicing how to speak to and alleviate the anxiety of dementia patients," "Staff member Y has many records of calm judgment and swift initial response in emergency response records," "Staff member Z has many comments of gratitude and trust from family members in their communication records," or "Staff member W frequently provides advice and support to other staff members in handover records, demonstrating high teamwork."
[0093] The Staffing Support Department integrates information obtained from the Competency Analysis Department, including each staff member's competency indicators and communication style, the level of care required and medical care needs of users, the overall staffing situation of the facility, shift balance, the condition and needs of users, past staffing history, workload, team compatibility information, facility management policies, and staff members' career aspirations and self-reported information. Using generative AI, it automatically generates optimal staffing plans, assignment plans, team formation plans, and leader candidate recommendations. For example, it can generate multiple specific staffing plans such as, "Staff member X, with high experience and expertise in dementia care, will be primarily responsible for user A with dementia, and staff member Y, with high emergency response capabilities and stress tolerance, will be assigned to user B, who is at high risk of sudden changes in condition at night," or "Staff member Z, with high family support capabilities, will be responsible for user C, where collaboration with family is important, and staff member W, with high cooperativeness and leadership skills, is recommended as the team leader." For each plan, it can also present the impact on care quality, risk assessment, staff satisfaction, and operational efficiency.
[0094] The user interface section displays a dashboard screen for administrators and team leaders, showing each staff member's competency indicators, placement plans, evaluation rank, scenario comparisons for each placement plan, risk assessments, career aspirations, and self-reported information. This allows for the approval and modification of placement plans and the input of feedback. Staff members themselves can also access screens to input their own competency indicators, evaluations, placement plans, self-reports, and career aspirations. The notification management section sends notifications to administrators such as "An optimal placement plan has been generated for the admission of a new resident" and "Feedback has been added to Staff X's evaluation," and reminders to staff members such as "Your assigned clients have changed" and "The deadline for submitting your self-report is approaching."
[0095] Specific examples of prompts to be fed into the generating AI include: "Analyze the following care records, handover records, user feedback, emergency response records, family communication records, staff chats, shift management data, training history, accident / near-miss reports, and care plan creation history, and quantify each staff member's care quality, teamwork, responsiveness, expertise, stress tolerance, user satisfaction, emergency response ability, communication style, education / training history, accident response history, family support ability, influence within and outside the team, frequency of gratitude and apologies, tendency in questions and instructions, proactiveness or passivity in speech, and degree of cross-project involvement. Furthermore, based on user information such as resident A (dementia, care level 4), resident B (high risk of sudden changes at night), and resident C (emphasis on family collaboration), along with staff competency indicators, shift status, workload, past placement history, team compatibility, and career aspirations, generate multiple optimal staff placement plans, and present the impact of each plan on care quality, risk assessment, staff satisfaction, and operational efficiency."
[0096] In this way, by using the system of the present invention, diverse work and communication data in nursing care settings can be comprehensively collected and analyzed, and the characteristics and strengths of each staff member can be objectively visualized by utilizing the capabilities of generative AI. This enables the automatic proposal and implementation of optimal staffing and evaluation according to the condition of the users and the operational status of the facility. This can bring about multifaceted effects, such as improving the quality of services in nursing care settings, ensuring that staff are placed in the right positions, improving operational efficiency, establishing a fair evaluation system, increasing user satisfaction, supporting staff career development, early detection and response to risks, and optimizing facility operations.
[0097] 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.
[0098] 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.
[0099] 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.
[0100] 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.
[0101] 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.
[0102] [Second Embodiment]
[0103] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.
[0104] 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.
[0105] 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).
[0106] 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.
[0107] 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.
[0108] 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).
[0109] 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.
[0110] 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.
[0111] 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.
[0112] 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.
[0113] 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.
[0114] 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".
[0115] (Example 1)
[0116] Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.
[0117] (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.
[0118] 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.
[0119] 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.
[0120] 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.
[0121] 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.
[0122] [Third Embodiment]
[0123] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.
[0124] 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.
[0125] 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).
[0126] 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.
[0127] 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.
[0128] 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).
[0129] 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.
[0130] 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.
[0131] 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.
[0132] 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.
[0133] 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.
[0134] 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".
[0135] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.
[0136] (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.
[0137] 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.
[0138] 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.
[0139] 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.
[0140] 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.
[0141] [Fourth Embodiment]
[0142] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.
[0143] 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.
[0144] 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).
[0145] 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.
[0146] 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.
[0147] 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).
[0148] 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.
[0149] 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.
[0150] 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.
[0151] 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.
[0152] 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.
[0153] 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.
[0154] 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".
[0155] (Example 1) Since the process flow is the same as in Example 1 described in the First Embodiment above, the explanation will be omitted.
[0156] (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.
[0157] 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.
[0158] 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.
[0159] 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.
[0160] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.
[0161] 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.
[0162] 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.
[0163] 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.
[0164] 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.
[0165] 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.
[0166] 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."
[0167] 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.
[0168] 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.
[0169] 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.
[0170] 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.
[0171] 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.
[0172] 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.
[0173] 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 this memory.
[0174] 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.
[0175] 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.
[0176] 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.
[0177] 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.
[0178] 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.
[0179] Furthermore, the following additional information is disclosed regarding the above explanation.
[0180] (Claim 1)
[0181] The system comprises a care data collection unit, a competency analysis unit, and a staffing support unit. The care data collection unit automatically and comprehensively collects diverse care-related data from care facilities and home care settings, including care records, handover records, communication logs with users, emergency response records, communication records with families, staff chats, shift management data, training history, accident / near-miss reports, user feedback, and care plan creation history. It also has the function of centrally storing attribute information such as staff ID, user ID, date and time, work content, related events, emotional expression, and evaluation comments. The competency analysis unit analyzes the aforementioned care-related data using generative AI and analyzes each staff member's care quality, teamwork, responsiveness, expertise, stress tolerance, user satisfaction, emergency response ability, communication style, education / training history, accident response history, family support ability, etc. The system has the function of quantifying multiple competency indicators, such as influence within and outside the team, frequency of expressions of gratitude and apologies, tendencies in asking questions and giving instructions, proactiveness and passivity in speaking, and degree of involvement across projects, using natural language processing and machine learning, and statistically aggregating them based on evaluation criteria common to all facilities. The personnel placement support department integrates the competency indicators and communication style of each staff member obtained from the competency analysis department, as well as additional information such as the level of care required and medical care needs of users, the overall staffing situation of the facility, shift balance, the condition and needs of users, past placement history, workload, team compatibility information, and facility management policies, and uses generative AI to automatically generate optimal staff placement plans, assignment plans, team formation plans, leader candidate recommendations, evaluation scores and rankings, and presents concrete placement proposals and evaluation results to managers. (Claim 2)
[0182] The system according to claim 1, wherein the competency analysis unit uses generative AI to analyze competency indicators such as care quality, teamwork, responsiveness, expertise, stress tolerance, user satisfaction, emergency response ability, communication style, education and training history, accident response history, family support ability, influence inside and outside the team, frequency of gratitude and apologies, tendency in asking questions and giving instructions, assertiveness and passivity in speech, and degree of cross-project involvement, in a multidimensional and dynamic manner by combining multiple AI technologies such as natural language processing, sentiment analysis, topic extraction, network analysis, clustering, anomaly detection, and time series analysis, and has a function to continuously update competency indicators. (Claim 3)
[0183] The system according to claim 1, wherein the personnel placement support department uses generative AI to comprehensively consider the ability indicators and communication styles of each staff member obtained from the ability analysis department, the level of care required and medical care needs of users, the overall staffing situation of the facility, shift balance, the condition and needs of users, past placement history, workload, team compatibility information, facility management policies, and staff career aspirations and self-reported information, and automatically generates multiple scenarios for optimal staff placement plans, assignment plans, team formation plans, and leader candidate recommendations, and also presents the expected care quality, risk assessment, staff satisfaction, and impact on work efficiency for each scenario. [Explanation of symbols]
[0184] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots
Claims
1. The system comprises a communication data collection unit, a competency analysis unit, and a human resources support unit. The communication data collection unit automatically collects multiple types of internal communication data, such as meeting records, emails, chats, daily work reports, task management systems, and internal social networking services, and centrally stores this data, including attribute information such as speaker, content of speech, time, related projects, and involved members. The competency analysis unit uses generative AI to analyze the communication data and analyzes each employee's contribution level, teamwork, leadership, communication style, expertise, problem-solving ability, proposal ability, stress tolerance, and performance both within and outside the team. The system has the function of quantifying multiple competency indicators, such as influence, frequency of gratitude and apologies, tendencies in questioning and giving instructions, assertiveness and passivity in speech, and degree of cross-project involvement, using natural language processing and machine learning, and statistically aggregating them based on company-wide common evaluation criteria. The Human Resources Support Department, based on the competency indicators and communication styles of each employee obtained by the Competency Analysis Department, uses generative AI to automatically generate optimal personnel placement and personnel transfer proposals that transcend departmental boundaries. Furthermore, it has the function of calculating evaluation scores and rankings to ensure fairness across the entire company, and presenting specific transfer proposals and evaluation results to managers.
2. The system according to claim 1, wherein the competence analysis unit uses generative AI to analyze the context and emotional expressions of statements, the content of requests for cooperation and feedback, whether or not the employee made proactive statements as a project leader, the frequency of advice and support to others, the extent of cross-departmental communication, and the content of business improvement suggestions and problem identifications from each employee's communication history, and has a function to continuously update each employee's competence indicators in a multidimensional and dynamic manner based on these analysis results.
3. The system according to claim 1, wherein the Human Resources Support Department uses generative AI to integrate and consider additional information such as each employee's ability indicators and communication style obtained by the Ability Analysis Department, as well as the employee's past transfer history, department, assigned projects, workload, team compatibility information, and the overall organizational personnel structure and future business plans, to automatically generate optimal personnel placement and personnel transfer plans as multiple scenarios, and also presents the expected organizational performance and risk assessment for each scenario.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A
