System

Abstract

A system is provided.SOLUTION: The system includes a means for analyzing the behavior characteristics, tone, failure contents, and work problems of employees by using generated AI, a means for generating an improvement plan and a motivation improvement plan, and a means for transmitting the generated improvement plan and motivation improvement plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With traditional work styles, each employee has different goals, perceptions, ways of thinking, and motivations, making it difficult to provide individually optimized work guidance and motivation management. Furthermore, it was not possible to provide appropriate support to employees with disabilities in particular, resulting in problems with productivity and employment retention. There was a need to resolve these issues and provide effective and efficient solutions for each employee. [Means for solving the problem]

[0005] This invention is a system that uses generative AI to analyze employee behavioral characteristics, speech patterns, obstacles, and work challenges. Specifically, it includes a means for generating improvement plans and motivational measures based on the generated characteristic data and challenge data and sending them to a manager's terminal. Additionally, the system includes a means for continuously updating specialized data for each employee and regenerating new improvement plans and motivational measures based on previous feedback data, as well as a means for storing each employee's data in a database and preprocessing the data before analysis. This enables work styles and motivation management optimized for each employee, improving productivity and employee retention.

[0006] "Generative AI" refers to artificial intelligence that uses advanced technologies such as machine learning and natural language processing to analyze data and generate new information and improvement measures.

[0007] "Employee" refers to an individual worker employed by a company or organization and engaged in work.

[0008] "Behavioral characteristics" refer to the specific behavioral patterns and habits that employees exhibit in their daily work.

[0009] "Tone of voice" refers to the characteristics of the way one speaks and the tone of the words used in conversation or communication.

[0010] "Disability" refers to the type and description of the specific physical, mental, or cognitive challenge or impairment an employee has.

[0011] "Work challenges" refer to the specific problems or difficulties employees face in carrying out their work.

[0012] "Characteristic data" refers to information that compiles data on an employee's behavioral characteristics, tone of voice, disability details, etc.

[0013] "Issue data" refers to information that compiles data about specific work-related issues that employees have.

[0014] "Improvement Suggestions" refer to specific action plans or measures suggested by generative AI to mitigate or resolve challenges faced by employees.

[0015] "Motivational measures" refer to specific approaches and measures proposed to increase employees' motivation and enthusiasm for their work.

[0016] "Administrator's device" refers to a computer or mobile device used by a manager or leader who manages employees.

[0017] "Feedback data" refers to data on the effectiveness of improvement proposals and motivational measures implemented by managers and employees, as well as data on new issues that have arisen. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple 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), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] 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 a "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).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention relates to a system that uses generative AI to analyze employees' behavioral characteristics, tone of voice, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system is designed to provide a work environment and measures suited to each employee, thereby improving their productivity and motivation.

[0040] System Overview

[0041] The system includes the following major components:

[0042] 1. Data Collection Device (hereinafter referred to as "Device")

[0043] 2. Central Database (hereinafter referred to as "Server")

[0044] 3. Generation AI

[0045] 4. Management Interface (hereinafter "Terminal")

[0046] Operational Overview

[0047] The system begins by entering data on an employee's behavioral characteristics, tone of voice, obstacles, and work challenges on a terminal and sending it to a server. The server stores this data in a central database and passes it to a generation AI for analysis. The generation AI generates improvement and motivational measures based on the individual employee's characteristics and sends them back to the management terminal. Based on these results, the manager can implement the optimal response for the employee.

[0048] Program processing

[0049] Data collection

[0050] The user inputs employee information (behavioral characteristics, tone of voice, obstacles, work issues) into the terminal. Each piece of information is collected in detail through specific forms and checklists.

[0051] Example input items:

[0052] Employee ID

[0053] Behavioral characteristics: Poor time management

[0054] Tone: Calm and polite

[0055] Disability: Attention Deficit Disorder (ADHD)

[0056] Work Challenge: Slow task completion speed

[0057] Data transmission and storage

[0058] The device sends the collected information to a server, which stores the received data in a central database for later analysis by the generative AI.

[0059] Characteristics analysis and problem analysis

[0060] The server preprocesses the stored data before passing it to the generation AI. This preprocessing ensures data integrity by filling in missing values ​​and detecting outliers.

[0061] The server then launches the generative AI, which analyzes employee characteristics and issues based on the preprocessed data. The generative AI then generates optimal improvement plans and motivational measures for each employee.

[0062] Generate improvement proposals

[0063] Generative AI generates specific improvement proposals and motivation-boosting measures tailored to each employee's characteristics and challenges.

[0064] This example generates:

[0065] Employee A's improvement suggestion:

[0066] Conducting time management training

[0067] Setting short-term goals and providing feedback

[0068] Motivate with positive praise

[0069] Employee B's improvement suggestion:

[0070] Organize your work environment and provide a space where you can focus

[0071] Incorporating a routine with short breaks

[0072] Introduction of an error checklist and confirmation before work begins

[0073] Output and action taken

[0074] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to the terminal. The user (administrator) receives this and takes specific measures for employees based on the report.

[0075] This example does the following:

[0076] Set goals for the day at your morning meeting

[0077] Providing feedback after completing a task

[0078] If they complete the task more quickly, they are given an extra break.

[0079] Feedback and Continuous Improvement

[0080] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends it back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generation AI. This allows for continuous optimal work styles and motivation management.

[0081] This system is a powerful tool for providing optimized support to each employee, improving their productivity and satisfaction. By utilizing generative AI, it is possible to respond to each individual employee and quickly implement approaches tailored to the characteristics of each employee.

[0082] The processing flow will be explained below.

[0083] Step 1:

[0084] Users enter data about employee behavioral traits, tone, obstacles, and work challenges into a terminal, using specific forms and checklists.

[0085] Step 2:

[0086] The terminal transmits the input data to the server.

[0087] Step 3:

[0088] The server stores the received data in a central database.

[0089] Step 4:

[0090] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[0091] Step 5:

[0092] The server passes the preprocessed data to the generation AI, which then launches it and analyzes the employee's behavioral characteristics and issues.

[0093] Step 6:

[0094] The generative AI generates improvement proposals and motivation-boosting measures based on each employee's characteristic data and issue data.

[0095] Step 7:

[0096] The server formats the generated improvement and motivational measures and creates a report for the management interface.

[0097] Step 8:

[0098] The server sends the report to the terminal.

[0099] Step 9:

[0100] The user (manager) receives the report and takes specific action against the employee based on it.

[0101] Step 10:

[0102] The user (administrator) inputs the effectiveness of the countermeasures and any new issues that have arisen into the terminal.

[0103] Step 11:

[0104] The terminal transmits the feedback data to the server.

[0105] Step 12:

[0106] The server stores the feedback data in a database and reanalyzes it using the generative AI, which then generates new improvement proposals and motivation-boosting strategies.

[0107] Step 13:

[0108] By repeating the process from step 6 onwards, optimal working styles and motivation management can be continuously achieved.

[0109] Example 1

[0110] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0111] As the working environment becomes more diverse, it is becoming increasingly important to provide optimal improvement plans and motivational measures for each employee, taking into account their behavioral characteristics, speech patterns, disabilities, and work challenges. However, collecting, analyzing, and continuously updating detailed data for individual responses makes it difficult to propose and implement effective improvement measures. For this reason, there is a need to develop a system that can quickly generate specific countermeasures tailored to each employee's characteristics and challenges, and continuously improve them based on feedback.

[0112] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0113] In this invention, the server includes means for collecting employee behavioral characteristics, tone of voice, details of obstacles, and work issues, means for sending the collected data to the server and storing it in a central database, means for preprocessing the stored data and filling in missing values ​​and detecting outliers, means for analyzing characteristics and issues using a generation AI based on the preprocessed data, means for generating improvement plans and motivation improvement measures tailored to each employee, means for sending the generated improvement plans and motivation improvement measures to a management terminal, means for re-collecting the effects of measures implemented by the manager and newly arising issues, and means for re-analyzing based on feedback data and making continuous improvements. This allows for the rapid provision of specific improvement plans and motivation improvement measures tailored to each employee's characteristics, enabling continuously optimized work styles and motivation management.

[0114] "Employee" refers to an individual who works for an organization or company.

[0115] "Behavioral characteristics" are elements that indicate an employee's behavioral patterns, habits, and characteristics in their work.

[0116] "Tone" refers to the way an employee speaks and the expressions they use when speaking.

[0117] "Disability details" refers to information including the employee's disability or special needs.

[0118] "Work challenges" refer to specific problems or difficulties that employees face in their work.

[0119] "Collection means" refers to the methods and devices used to aggregate information about employees.

[0120] A "server" is a computer system for storing, managing, and analyzing data.

[0121] A "central database" is a database system for centrally storing and managing collected data.

[0122] "Preprocessing" refers to processes such as filling in missing values ​​and detecting outliers before data analysis.

[0123] "Generative AI" refers to a system that uses artificial intelligence to analyze data, analyze characteristics and issues, and generate improvement proposals.

[0124] "Characteristic analysis" refers to analyzing employee characteristics based on collected data.

[0125] "Problem analysis" refers to identifying the specific challenges employees face through data analysis.

[0126] "Improvement proposals" refer to specific means or methods proposed to improve employees' work and increase efficiency.

[0127] "Motivation improvement measures" refer to specific proposals to increase employee motivation and morale.

[0128] "Administrative terminal" refers to a terminal used by an administrator to check data and implement countermeasures through the system.

[0129] "Feedback data" refers to data on the effectiveness of implemented countermeasures and new issues that have arisen.

[0130] "Continuous improvement" refers to repeatedly conducting new analyses and proposals based on feedback, rather than conducting a single analysis and proposal.

[0131] This invention relates to a system that analyzes employees' behavioral characteristics, tone, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system utilizes generative AI to provide a work environment and measures suited to each employee, and is designed to improve their productivity and motivation.

[0132] Hardware and software used

[0133] Hardware: Data collection terminal, central server, management terminal

[0134] Software: Generative AI (e.g., GPT-4), Database Management Systems (e.g., MySQL)

[0135] System Operation Overview

[0136] The user operates the data collection terminal to input detailed information about the employee. This information includes behavioral characteristics, tone of voice, obstacles, and work challenges. The data collection terminal encrypts the collected data and sends it to the server. The server stores the received data in a central database.

[0137] After the data is saved, the server performs preprocessing, which includes filling in missing values, detecting outliers, and normalizing the data. The preprocessed data is then passed to a generative AI that analyzes the characteristics and challenges of each employee. This analysis generates optimal improvement and motivational measures for each employee.

[0138] The improvement proposals and motivation-boosting measures generated by the generative AI are sent to a management terminal via a server. Based on this information, managers implement specific countermeasures for employees. Managers also re-enter the effectiveness of the countermeasures and any new issues that arise into a data collection terminal and send it to the server. The server stores this data in a database and re-analyzes it using the generative AI. This allows for continuous optimization.

[0139] Prompt Sentence Examples

[0140] Provide optimal improvement and motivational strategies based on employee details, such as:

[0141] Behavioral trait: Poor time management

[0142] Tone: Calm and polite

[0143] Disability: ADHD

[0144] Work Challenge: Slow task completion rate

[0145] Specific examples

[0146] The user inputs detailed information about Employee A into the data collection terminal. For example, information such as Employee A's behavioral characteristics as "poor time management," his tone of voice as "calm and polite," his disability as "ADHD," and his work challenges as "slow task completion speed" is collected. This information is sent to the server and stored in a central database.

[0147] The server preprocesses the data and passes the preprocessed data to the generation AI. The generation AI analyzes this data and generates specific improvement proposals, such as "conduct time management training" and "set short-term goals and provide feedback." The generated improvement proposals are sent to a management terminal, and the manager uses them to implement specific measures for employee A.

[0148] In this way, this system provides specific improvement measures tailored to the characteristics and needs of employees, aiming to increase productivity and satisfaction. The use of generative AI enables quick and individual responses, making it easier to implement approaches tailored to characteristics.

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Step 1: Data collection

[0151] The user operates the terminal to input detailed information about the employee. Specifically, data on the employee's behavioral characteristics, tone of voice, obstacles, and work issues is collected using forms and checklists. The input information includes specific data such as "Employee A's ID, behavioral characteristics: poor time management, tone of voice: calm and polite, obstacles: ADHD, work issues: slow task completion speed." This input data is collected by the terminal.

[0152] Step 2: Send data

[0153] The device encrypts the collected information and sends it to the server. During the transmission process, the device sends data to the server in real time via the Internet, and the server receives the data. This transmitted data is in preparation for being stored in a database in the next step.

[0154] Step 3: Save data

[0155] The server stores the received data in a central database. Specifically, a database management system (e.g., MySQL) is used to store the data while maintaining its integrity and consistency. This stored data serves as the basis for analysis by the generative AI. Once the input data has been stored, it is passed on to the next preprocessing step.

[0156] Step 4: Data Preprocessing

[0157] The server preprocesses the data stored in the central database. Preprocessing involves filling in missing values, detecting outliers, and normalizing the data. For example, if missing values ​​exist, they are filled in with the mean or median, and if outliers are detected, appropriate corrections are made. Once preprocessing is complete, the data is ready to be passed to the generative AI.

[0158] Step 5: Characteristics analysis and problem analysis

[0159] The server passes the preprocessed data to the generation AI, which analyzes the characteristics and issues. The generation AI (e.g., GPT-4) uses a deep learning algorithm to analyze the employee's characteristics and issues. Based on the input data, it identifies and analyzes Employee A's characteristic of "poor time management" and his issue of "slow task completion speed." The results of this analysis are used to generate improvement measures in the next step.

[0160] Step 6: Generate improvement ideas and motivational strategies

[0161] Based on the results of the characteristic analysis and issue analysis, the generative AI generates improvement proposals and motivational measures tailored to each employee. For example, for employee A, it generates specific improvement proposals such as "implementing training on time management" and "setting short-term goals and providing feedback." The generated improvement proposals are compiled in report format.

[0162] Step 7: Output and action taken

[0163] The server sends a report of the generated improvement proposals and motivational measures to the management terminal. The user (administrator) receives the report and implements specific countermeasures. For example, specific countermeasures such as "setting the day's goals in a morning meeting" and "providing feedback after completing tasks" are implemented based on the report.

[0164] Step 8: Feedback and continuous improvement

[0165] The user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues they have encountered into their device and sends it back to the server. This new feedback data is stored in a central database, and the server re-analyzes it using the AI ​​generation system, achieving continuous optimization. By continuously collecting and analyzing feedback data, the cycle of providing optimal countermeasures for each employee is maintained.

[0166] (Application example 1)

[0167] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0168] In recent years, there has been a demand for improved operational efficiency and accuracy for factory robots. However, there is still a lack of effective systems that can grasp the operational status of robots on-site in real time and provide optimal improvement proposals and maintenance measures. In particular, robot operation errors and reduced operational efficiency have a negative impact on productivity, which is a problem. Conventional systems rely on manual monitoring and judgment by operators and managers, and often make it difficult to respond quickly. For this reason, there is a need for the development of a new system that can monitor the operational status of factory robots in real time and use generative AI to provide optimal improvement proposals.

[0169] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0170] In this invention, the server includes means for using a generating AI to analyze employee behavioral characteristics, tone of voice, details of obstacles, and work issues, means for generating improvement plans and motivation improvement measures based on the resulting characteristic data and issue data, means for transmitting the generated improvement plans and motivation improvement measures to a manager's terminal, and means for monitoring the robot's operation status in real time with smart glasses and using that data to provide optimal improvement plans and maintenance measures. This makes it possible to reduce operation errors and improve operation efficiency by monitoring the operation status of factory robots in real time and having the generating AI provide optimal improvement plans and maintenance measures.

[0171] "Generative AI" is an artificial intelligence technology that analyzes data and automatically generates improvement plans and suggestions based on human behavior and characteristics.

[0172] "Behavioral characteristics" are patterns of performance and behavior of employees or robots in work situations.

[0173] "Tone" refers to the style of speaking and expression in audio data.

[0174] "Disability" refers to physical or mental handicaps or limitations that arise in the course of work.

[0175] "Job challenges" are the job-related problems and challenges that employees face.

[0176] "Characteristic data" is detailed information about the behavior and status of the employee or robot being analyzed.

[0177] "Challenge data" is information about a specific problem an employee or robot is facing.

[0178] "Improvement proposals" are specific action plans proposed to improve the performance of employees or robots.

[0179] "Motivation improvement measures" are specific proposals and measures to increase employee motivation and efficiency.

[0180] The "administrator's terminal" refers to a computer or smart device used by the administrator for operation.

[0181] "Robot operation status" refers to information about the progress of the work being performed by the factory robot and the accuracy of its movements.

[0182] "Smart glasses" are wearable devices that display real-time information and record on-site conditions.

[0183] "Maintenance measures" are specific management procedures and repair proposals to maintain the normal operation of robots and equipment.

[0184] This invention relates to a system that uses generative AI to analyze employee behavioral characteristics, speech patterns, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system is particularly useful for improving the operational efficiency and accuracy of factory robots. Specific embodiments of the system are described below.

[0185] Hardware and Software Configuration

[0186] 1. Hardware:

[0187] Smart glasses (e.g., Google Glass): Used to monitor the operation status of factory robots in real time.

[0188] Administrator's device: A device such as a PC or smartphone used to receive generated improvement proposals and motivational measures.

[0189] 2. Software:

[0190] Data collection application: Runs on the smart glasses and collects and transmits robot operation data.

[0191] Generative AI model: Runs on the server and analyzes and processes collected data.

[0192] System execution procedures and operations

[0193] 1. Data Collection:

[0194] The smart glasses monitor the operating status of factory robots (operating efficiency, error frequency, accuracy, etc.) in real time and periodically send this data to a server.

[0195] 2. Data transmission and storage:

[0196] The server stores the received data in a central database, which is then used for analysis by the generative AI.

[0197] 3. Characteristics and Issues Analysis:

[0198] The server preprocesses the stored data before passing it to the generation AI, which performs missing value imputation and outlier detection to maintain data integrity.

[0199] Next, the server launches the generative AI, which uses the preprocessed data to perform characteristic analysis and problem analysis related to the operational efficiency and accuracy of the factory robot.

[0200] 4. Generate improvement proposals:

[0201] The generative AI generates optimal improvement and maintenance plans based on the robot's characteristic data and problem data.

[0202] 5. Output and action taken:

[0203] The server compiles the generated improvement proposals and maintenance measures into a report format and sends it to the administrator's terminal.

[0204] The user (administrator) receives this report and takes specific countermeasures on-site based on the report.

[0205] Specific examples

[0206] For example, if a factory robot has an operating efficiency of 85%, an error frequency of 2, and an accuracy of 90%, the data collected by the smart glasses will be converted into the following prompt sentence:

[0207] "Analyze the operational activity data of a factory robot and generate optimal improvement and maintenance plans to improve efficiency. The following data was collected: operational efficiency: 85%, error frequency: 2 times, accuracy: 90%."

[0208] If you feed this prompt to a generative AI model, you'll get the following response:

[0209] To improve the efficiency of your robot's operation, we recommend the following steps:

[0210] 1. Standardizing operating procedures and providing training

[0211] 2. Shorter maintenance intervals

[0212] 3. Software updates to improve operation accuracy

[0213] By generating specific improvement plans in this way, it is possible to effectively improve the operating conditions of factory robots and increase productivity.

[0214] This system can be applied not only to factory robots, but also to managing other employees and improving their performance. It also includes a function that continuously updates data specific to each employee and regenerates new improvement proposals and motivational measures based on previous feedback data. This allows for continuous optimal work styles and motivation management.

[0215] Finally, by utilizing generative AI, this invention enables rapid implementation of approaches tailored to the characteristics of employees and robots, making it easier to respond to individual needs.

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] Data collection

[0219] Input: The robot's operation status (operation efficiency, error frequency, accuracy, etc.) is obtained in real time from the smart glasses.

[0220] How it works: The smart glasses use sensors to collect data on the robot's operations and record it digitally.

[0221] Output: The collected operation data is sent from the terminal (smart glasses) to the server.

[0222] Step 2:

[0223] Data transmission and storage

[0224] Input: Robot operation data sent from the terminal.

[0225] Specific operation: The server receives the received data in real time and stores it in a central database.

[0226] Output: The saved operational data is used for the next analysis step.

[0227] Step 3:

[0228] Characteristics analysis and problem analysis

[0229] Input: Robot operation data stored in a central database.

[0230] Specific operation: The server performs preprocessing, imputes missing values ​​in the data, detects outliers, and maintains data integrity. The preprocessed data is then passed to the generation AI.

[0231] Output: Preprocessed data passed to the generative AI.

[0232] Step 4:

[0233] Generative AI startup and analysis

[0234] Input: Preprocessed operational data.

[0235] Specific operation: The generative AI analyzes the robot's characteristics and issues based on the input data. For example, it analyzes based on data such as 85% operational efficiency, 2 error frequencies, and 90% accuracy.

[0236] Output: Analysis results based on characteristic data and problem data regarding the robot's operating situation.

[0237] Step 5:

[0238] Generate improvement proposals

[0239] Input: Analysis results (characteristic data and problem data).

[0240] Specific actions: The generative AI generates optimal improvement and maintenance plans from the analysis results, such as standardizing operating procedures, shortening maintenance intervals, and proposing software updates.

[0241] Output: Generated improvement and maintenance recommendations.

[0242] Step 6:

[0243] Output and action taken

[0244] Input: Generated improvement and maintenance measures.

[0245] Specific operation: The server compiles the generated improvement proposals and maintenance measures into a report format and sends it to the administrator's terminal.

[0246] Output: Report received on administrator's terminal.

[0247] Step 7:

[0248] Feedback and Continuous Improvement

[0249] Input: Feedback data on the effectiveness of measures taken by administrators and new issues that have arisen.

[0250] Specific operation: The user (administrator) inputs feedback data into the terminal and sends it to the server, which stores it in a database and reanalyzes it as feedback data using the generation AI.

[0251] Output: Continuous improvement recommendations based on new feedback data.

[0252] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0253] This invention relates to a system that uses generative AI to analyze employees' behavioral characteristics, tone of voice, obstacles, and work challenges, and also to a system that uses an emotion engine to analyze employees' emotional data and provide optimal improvement proposals and motivational measures. This system is designed to provide a work environment and measures that are suited to each individual employee, thereby improving their productivity and motivation.

[0254] System Overview

[0255] The system includes the following major components:

[0256] 1. Data Collection Device (hereinafter referred to as "Device")

[0257] 2. Central Database (hereinafter referred to as "Server")

[0258] 3. Generation AI

[0259] 4. Emotion Engine

[0260] 5. Management Interface (hereinafter "Terminal")

[0261] Operational Overview

[0262] The system begins by entering an employee's behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data into a terminal and sending it to a server. The server stores this data in a central database and passes it to a generative AI and emotion engine for analysis. The generative AI generates improvement and motivational measures based on the employee's individual characteristics and emotions and sends them back to the management terminal. Based on these results, the manager can implement the optimal response for the employee.

[0263] Program processing

[0264] Data collection

[0265] Users input employee information (behavioral characteristics, tone of voice, obstacles, work challenges) and emotional data into the terminal. Each piece of information is collected in detail using specific forms and checklists, as well as emotion recognition technology.

[0266] Example input items:

[0267] Employee ID

[0268] Behavioral characteristics: Poor time management

[0269] Tone: Calm and polite

[0270] Disability: Attention Deficit Disorder (ADHD)

[0271] Work Challenge: Slow task completion speed

[0272] Emotional data: Stress levels based on facial expressions and voice analysis

[0273] Data transmission and storage

[0274] The device sends the input data to a server, which stores it in a central database for later analysis by the generative AI and emotion engine.

[0275] Characteristics analysis and problem analysis

[0276] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[0277] The server then passes the preprocessed data to the generation AI and emotion engine for analysis. The generation AI analyzes the employee's behavioral characteristics and issues, while the emotion engine analyzes the employee's emotional data.

[0278] Generate improvement proposals

[0279] Generative AI and an emotion engine generate specific improvement proposals and motivational measures based on each employee's individual characteristics, challenges, and emotions.

[0280] This example generates:

[0281] Employee A's improvement suggestion:

[0282] Conducting time management training

[0283] Setting short-term goals and providing feedback

[0284] Motivate with positive praise

[0285] Introducing relaxation techniques based on emotional data

[0286] Employee B's improvement suggestion:

[0287] Organize your work environment and provide a space where you can focus

[0288] Incorporating a routine with short breaks

[0289] Introduction of an error checklist and confirmation before work begins

[0290] Introducing stress management methods based on emotional data

[0291] Output and action taken

[0292] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to the terminal. The user (administrator) receives this and takes specific measures for employees based on the report.

[0293] This example does the following:

[0294] Set goals for the day at your morning meeting

[0295] Providing feedback after completing a task

[0296] If they complete the task more quickly, they are given an extra break.

[0297] Implement relaxation and stress management techniques based on emotional data

[0298] Feedback and Continuous Improvement

[0299] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[0300] This system is a powerful tool for providing optimized support to each employee, improving their productivity and satisfaction. Utilizing generative AI and an emotion engine, it enables personalized responses and quickly implements approaches tailored to the employee's characteristics and emotions.

[0301] The processing flow will be explained below.

[0302] Step 1:

[0303] Users input employee behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data into a terminal using specific forms and checklists, as well as emotion recognition technology (e.g., facial expression analysis cameras and voice recognition microphones).

[0304] Step 2:

[0305] The device sends the entered data to the server, where it is encrypted and transmitted using a secure protocol.

[0306] Step 3:

[0307] The server stores the received data in a central database, which stores each employee's behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data.

[0308] Step 4:

[0309] The server preprocesses the stored data. This preprocessing includes filling in missing data, detecting outliers, and standardizing data formats. Data preprocessing is essential to improve the accuracy of analysis.

[0310] Step 5:

[0311] The server passes the preprocessed data to the generation AI and emotion engine. The generation AI analyzes the employee's behavioral characteristics and issues, and the emotion engine analyzes the employee's emotional data.

[0312] Step 6:

[0313] The generative AI analyzes the characteristic data and issue data for each employee, and the emotion engine analyzes the emotional data. Based on the results of this analysis, it generates optimal improvement plans and motivation-boosting measures.

[0314] Step 7:

[0315] The server formats the generated improvement and motivational measures and creates a report for the management interface, which includes the analysis results and specific countermeasures.

[0316] Step 8:

[0317] The server sends the report to the terminal, which is provided in a format that is easy for the administrator to understand.

[0318] Step 9:

[0319] The user (manager) receives the report and takes specific action based on it, including suggestions for improvement and motivation provided by the generative AI and emotion engine.

[0320] Step 10:

[0321] The user (administrator) evaluates the effectiveness of the countermeasures and any new issues that arise, and enters the evaluation results and feedback data into the terminal.

[0322] Step 11:

[0323] The terminal sends feedback data to the server, which is stored in a central database in the same way as the initial data.

[0324] Step 12:

[0325] The server reanalyzes the feedback data using the generative AI and emotion engine, which is used as important input data for the next improvement plan.

[0326] Step 13:

[0327] The server then formats the new improvement proposals and motivation-boosting measures into a report and sends it to the device. This process is repeated to continuously optimize work styles and motivation management.

[0328] In this way, the system can continuously analyze employees' characteristics and emotions and provide optimal improvement and motivational strategies.

[0329] Example 2

[0330] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0331] In today's workplace, improving employee productivity and motivation is a key challenge. However, accurately understanding the behavioral characteristics and emotional state of each employee and responding to them individually can be difficult. It is also not easy to quickly provide appropriate improvement proposals and motivation-boosting measures based on employees' characteristics and challenges. A system that effectively utilizes employee emotional data to achieve specific behavioral improvements and motivational improvements is needed.

[0332] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0333] In this invention, the server includes: means for analyzing employee behavioral characteristics, tone of voice, obstacles, and work issues using a generation AI; means for generating improvement plans and motivation-boosting measures based on the resulting characteristic data and issue data; means including an emotion analysis engine for analyzing the collected emotion data and proposing appropriate measures based on the employee's emotions; and means for sending the generated improvement plans and motivation-boosting measures to a manager's terminal in report format. This enables the rapid provision of optimized support for each employee, improving productivity and motivation.

[0334] "Generative AI" is a system that uses artificial intelligence techniques to analyze data and generate outputs or results suitable for specific purposes.

[0335] "Behavioral characteristics" are characteristics related to employee behavior patterns, habits, and actions.

[0336] "Tone" refers to the characteristics of the language and communication style used by employees.

[0337] "Disability details" is information about an employee's specific disability and its impact.

[0338] "Work challenges" are work-related problems employees face or areas that need improvement.

[0339] "Characteristic data" refers to information regarding the behavioral characteristics, tone of voice, and disability details of the employee being analyzed.

[0340] "Issue data" refers to information regarding business issues and areas requiring improvement.

[0341] An "improvement proposal" is a specific improvement measure proposed based on the employee's behavioral characteristics and challenges.

[0342] "Motivation improvement measures" are specific measures to increase employee motivation and enthusiasm.

[0343] "Emotional data" is data that indicates an employee's emotional state and is typically collected through facial and voice analysis.

[0344] An "emotion analysis engine" is a system that analyzes emotional data, evaluates employees' emotional state, and generates countermeasures based on that.

[0345] "Administrator's terminal" refers to a computer or device used by the system administrator to receive generated reports and improvement proposals.

[0346] This invention is a system that utilizes generative AI and an emotion analysis engine to analyze employees' behavioral characteristics, tone of voice, obstacles, work issues, and emotional data, and provides optimal improvement plans and motivational measures for each employee. This system consists of a data collection terminal, a server, generative AI, an emotion analysis engine, and a management terminal.

[0347] Hardware and Software Use

[0348] Data collection device: A computer or mobile device used to collect employee behavioral characteristics, tone, obstacles, work challenges, and emotional data. This device is equipped with sensors such as a camera and microphone and is also used to collect emotional data.

[0349] Server: A computer that stores collected data in a central database and passes it to the generation AI and emotion analysis engine. It also transmits generated improvement proposals and motivational measures to the management terminal.

[0350] Generative AI: An artificial intelligence model used to analyze employee behavioral characteristics and challenges. This AI generates optimal improvement plans and motivational measures based on data for each employee.

[0351] Sentiment Analysis Engine: Software that analyzes emotional data and assesses the emotional state of employees, allowing it to suggest countermeasures based on their emotions.

[0352] Management terminal: A computer or device where a manager receives generated reports and takes action against employees.

[0353] Explanation of program processing

[0354] Users enter employee behavioral characteristics, tone, obstacles, work challenges, and emotional data into data collection devices. This data is collected through forms, checklists, cameras, and microphones.

[0355] Specifically, the following data is entered:

[0356] Employee ID

[0357] Behavioral characteristics: Poor time management

[0358] Tone: Calm and polite

[0359] Disability: Attention Deficit Disorder (ADHD)

[0360] Work Challenge: Slow task completion speed

[0361] Emotional data collected using a camera and microphone: stress levels through facial and voice analysis

[0362] The terminal encrypts the input data and transmits it in real time to the server, which stores the received data in a central database and performs pre-processing on the data, including missing value imputation, outlier detection, and data format standardization.

[0363] The server then passes the preprocessed data to the generation AI and emotion analysis engine for analysis. The generation AI analyzes employees' behavioral characteristics and issues, and generates optimal improvement proposals and motivation-boosting measures. At the same time, the emotion analysis engine analyzes the emotional data and proposes countermeasures based on the employee's emotional state.

[0364] The generated improvement proposals and motivation-boosting measures are compiled into a report and sent to a management terminal. The user (manager) then implements specific measures for the employees based on this report.

[0365] for example:

[0366] Set goals for the day at your morning meeting

[0367] Providing feedback after completing a task

[0368] Offer additional breaks if the task can be completed more quickly

[0369] Implement relaxation and stress management techniques based on emotional data

[0370] Finally, the user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues that have arisen into the terminal and sends it back to the server, allowing the system to continuously update the data and continue to provide optimal improvement proposals and motivation-boosting measures.

[0371] Example prompts for generative AI models

[0372] Below are some example prompts to be input to the generative AI model:

[0373] Prompt statement:

[0374] Employee ID: 12345

[0375] Behavioral trait: Poor time management

[0376] Tone: Calm and polite

[0377] Disability: ADHD

[0378] Work Challenge: Slow task completion rate

[0379] Emotion data: High stress level based on facial expression analysis

[0380] Generate optimal improvement and motivational strategies.

[0381] This makes it possible to provide each employee with quick, optimized support, improving productivity and motivation.

[0382] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0383] Step 1:

[0384] Data collection

[0385] Users input employee behavioral characteristics, tone of voice, obstacles, work tasks, and emotional data into a terminal. This input data is collected through forms, checklists, cameras, and microphones.

[0386] Input: Employee ID, behavioral characteristics, tone of voice, obstacle details, work issues, emotional data

[0387] Specific behavior:

[0388] The user enters an employee ID into a form.

[0389] Select a behavioral trait from the selection list.

[0390] Enter the tone.

[0391] Check the fault details.

[0392] Enter work assignments.

[0393] Emotional data (facial expression analysis, voice analysis) is collected using a camera and microphone.

[0394] Step 2:

[0395] Data transmission

[0396] The device encrypts the entered data and sends it to the server. The data is sent in real time to prevent data leakage during transmission.

[0397] Input: Employee data entered into the terminal

[0398] Output: The encrypted data is sent to the server

[0399] Specific behavior:

[0400] The device encrypts all input data at once.

[0401] The encrypted data is sent to the server.

[0402] Step 3:

[0403] Data storage

[0404] The server deserializes the received data and stores it in a central database, where the storage is performed transactionally to ensure consistency and integrity.

[0405] Input: Encrypted data sent to the server

[0406] Output: Employee data deserialized and saved to the database

[0407] Specific behavior:

[0408] The server decrypts the received data.

[0409] The data is deserialized and stored in a central database.

[0410] Step 4:

[0411] Data Preprocessing

[0412] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[0413] Input: Stored raw data

[0414] Output: Preprocessed data

[0415] Specific behavior:

[0416] The server detects and completes missing values ​​in the stored data.

[0417] Correct any abnormal values.

[0418] Transform data into a unified format.

[0419] Step 5:

[0420] Characteristics analysis and problem analysis

[0421] The server passes the preprocessed data to the generation AI and sentiment analysis engine for analysis. The generation AI analyzes employee behavioral characteristics and issues, while the sentiment analysis engine analyzes the emotional data.

[0422] Input: Preprocessed data

[0423] Output: Analysis results (behavioral characteristics, tasks, emotional state)

[0424] Specific behavior:

[0425] The server converts the data into an input format for the generative AI model.

[0426] The generative AI analyzes behavioral characteristics and challenges and outputs the results.

[0427] The emotion analysis engine analyzes the emotion data and outputs the emotional state.

[0428] Step 6:

[0429] Generate improvement proposals

[0430] Generative AI and an emotion analysis engine generate specific improvement proposals and motivational measures based on each employee's characteristics, challenges, and emotions.

[0431] Input: Analysis results (behavioral characteristics, tasks, emotional state)

[0432] Output: Improvement proposals and motivational measures

[0433] Specific behavior:

[0434] The server receives the analysis results from the generation AI and the sentiment analysis engine.

[0435] Generate optimal improvement plans and motivation measures for each employee.

[0436] Step 7:

[0437] Output of improvement proposals

[0438] The server compiles the generated improvement proposals and motivation-boosting measures into a report format and sends it to the management terminal.

[0439] Input: Generated improvement ideas and motivational measures

[0440] Output: Report format data. Send to management terminal.

[0441] Specific behavior:

[0442] The server formats the data using a report template.

[0443] The formatted report is sent to the management terminal.

[0444] Step 8:

[0445] Implementing countermeasures

[0446] The user (manager) takes specific measures for the employee based on the report.

[0447] Input: Report sent to management terminal

[0448] Output: Implementing action against employee

[0449] Specific behavior:

[0450] The user (administrator) sets the day's goals at a morning meeting.

[0451] Provide feedback after completing a task.

[0452] If they can complete the task more quickly, they are given an extra break.

[0453] Relaxation and stress management techniques are implemented based on emotional data.

[0454] Step 9:

[0455] Feedback and Continuous Improvement

[0456] The user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues they have encountered into the terminal and sends it back to the server. This updates the database, and the new feedback data is reanalyzed by the generation AI and emotion analysis engine.

[0457] Input: Feedback data, effectiveness of countermeasures, new issues

[0458] Output: Updated data, continuous improvement ideas and motivational measures

[0459] Specific behavior:

[0460] The user (administrator) inputs the feedback data into the terminal.

[0461] The device sends this to the server, where it is stored in a database.

[0462] The server reanalyzes the feedback data and generates new improvement suggestions.

[0463] (Application example 2)

[0464] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0465] When workers and robots work together in factories, optimal work instructions and support that take into account the behavioral characteristics and emotional data of workers are not being provided, which is a problem that leads to reduced productivity and increased stress among workers. Furthermore, there is a lack of individualized measures for each worker, making it difficult to respond quickly and accurately, which makes it difficult to improve worker motivation and provide an efficient work environment.

[0466] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing an employee's behavioral characteristics, tone of voice, obstacle details, and work issues using a generation AI, means for generating improvement plans and motivation improvement measures based on the resulting characteristic data and issue data, means for sending the generated improvement plans and motivation improvement measures to a manager's terminal, means for analyzing employee emotion data and optimizing robot work instructions based on the analysis results, and means for detecting an employee's stress level and suggesting appropriate rest. This allows work instructions and support optimized for each employee to be automatically provided, improving productivity and reducing employee stress.

[0467] "Generative AI" is an artificial intelligence that uses artificial intelligence technology to analyze employees' behavioral characteristics and work challenges, and automatically generates appropriate improvement proposals and motivation-boosting measures.

[0468] "Behavioral characteristics" refer to an employee's working style and behavioral patterns, such as strengths and weaknesses in time management and the speed at which tasks are completed.

[0469] "Tone of speech" refers to the characteristics of an employee's language and speaking style, such as a calm and polite manner of speaking or a strong tone of voice.

[0470] "Disability" means information about an employee's disability, such as attention deficit disorder or physical limitations.

[0471] "Work challenges" refer to problems or difficulties an employee faces in performing their job, such as slow task completion.

[0472] "Characteristic data" refers to data obtained as a result of analysis, such as employee behavioral characteristics and the nature of obstacles.

[0473] "Issue data" refers to data related to the work issues of employees obtained as a result of the analysis.

[0474] "Emotional data" is data that indicates an employee's emotional state and is collected through voice analysis and facial expression recognition.

[0475] "Improvement proposals" are specific improvement measures created based on an employee's behavioral characteristics and work challenges, and include, for example, training on time management.

[0476] "Motivation measures" are specific means to increase employees' motivation to work, and include setting short-term goals and motivating employees through praise.

[0477] "Administrator's device" refers to a computer or smart device used by a supervisor or manager, and is a device used to view and manage employee characteristic data and improvement proposals.

[0478] "Robot work instructions" refers to automatically giving instructions to robots in factories to optimize their collaborative work with employees.

[0479] "Break suggestion" means sensing an employee's stress level and suggesting a break at the appropriate time if necessary.

[0480] This invention realizes a system that analyzes employee behavioral characteristics, speech patterns, obstacles, work challenges, and emotional data to provide optimal improvement plans and motivational measures in order to optimize collaboration between employees and robots in a factory. A specific embodiment of this system will be described below.

[0481] System Overview

[0482] The system includes the following major components:

[0483] 1. Data Collection Device (hereinafter referred to as "Device")

[0484] 2. Central Database (hereinafter referred to as "Server")

[0485] 3. Generation AI

[0486] 4. Emotion Engine

[0487] 5. Robot Operation Interface (hereinafter "Robot Interface")

[0488] 6. Management terminal (hereinafter referred to as "Management terminal")

[0489] Operational Overview

[0490] The user inputs the employee's behavioral characteristics, tone of voice, details of the obstacles, work issues, and emotional data into the terminal and sends it to the server. The server stores this data in a central database and passes it to the generation AI and emotion engine for analysis. The generation AI generates improvement proposals and motivational measures based on the employee's individual characteristics and emotions and sends them back to the management terminal. It also provides the robot with optimal work instructions through the robot interface. Based on these results, the manager can implement the optimal response for the employee.

[0491] Program processing

[0492] Data collection

[0493] Users input employee information (behavioral characteristics, tone of voice, obstacles, work challenges) and emotional data into the terminal. Each piece of information is collected in detail using specific forms and checklists, as well as emotion recognition technology.

[0494] Example input items:

[0495] Employee ID

[0496] Behavioral characteristics: Poor time management

[0497] Tone: Calm and polite

[0498] Disability: Attention Deficit Disorder (ADHD)

[0499] Work Challenge: Slow task completion speed

[0500] Emotional data: Stress levels based on facial expressions and voice analysis

[0501] Data transmission and storage

[0502] The device sends the input data to a server, which stores it in a central database for later analysis by the generative AI and emotion engine.

[0503] Characteristics analysis and problem analysis

[0504] The server preprocesses the stored data. This preprocessing includes filling in missing values, detecting outliers, and standardizing data formats. The server then passes the preprocessed data to the generative AI and emotion engine for analysis. The generative AI analyzes employee behavioral characteristics and issues, while the emotion engine analyzes employee emotional data.

[0505] Generate improvement proposals and motivational measures

[0506] Generative AI and an emotion engine generate specific improvement proposals and motivational measures based on each employee's individual characteristics, challenges, and emotions.

[0507] This example generates:

[0508] Employee A's improvement suggestion:

[0509] Conducting time management training

[0510] Setting short-term goals and providing feedback

[0511] Motivate with positive praise

[0512] Introducing relaxation techniques based on emotional data

[0513] Employee B's improvement suggestion:

[0514] Organize your work environment and provide a space where you can focus

[0515] Incorporating a routine with short breaks

[0516] Introduction of an error checklist and confirmation before work begins

[0517] Introducing stress management methods based on emotional data

[0518] Output and action taken

[0519] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to a management terminal. The user (manager) receives this report and implements specific measures for employees based on the report. The server also provides the robot with optimal work instructions based on the employee's emotional data through the robot interface.

[0520] This example does the following:

[0521] Set goals for the day at your morning meeting

[0522] Providing feedback after completing a task

[0523] If they complete the task more quickly, they are given an extra break.

[0524] Implement relaxation and stress management techniques based on emotional data

[0525] Feedback and Continuous Improvement

[0526] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[0527] Example prompts to input to a generative AI model:

[0528] Prompt: Based on Employee A's behavioral and emotional data, please suggest the best improvement and motivational measures for him.

[0529] Behavioral data: Poor time management, slow task completion

[0530] Emotional data: high stress level, tired facial expression

[0531] As described above, this invention is a powerful tool for providing optimized support to each employee and improving their productivity and satisfaction. By utilizing generative AI and an emotion engine, personalized responses are possible, and approaches tailored to the employee's characteristics and emotions can be quickly implemented.

[0532] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0533] Step 1:

[0534] The user inputs employee information (behavioral characteristics, tone of voice, obstacles, and work challenges) and emotional data into the terminal. Specific forms and checklists are used to collect detailed data, which is then analyzed using emotion recognition technology. For example, the user inputs the employee's ID, behavioral characteristics (poor time management), tone of voice (calm and polite), obstacles (attention deficit disorder), work challenges (slow task completion speed), and emotional data (stress level determined by facial and voice analysis).

[0535] Input: Employee behavioral characteristics, tone of voice, obstacles, work issues, emotional data

[0536] Output: A set of input data

[0537] Step 2:

[0538] The device sends the input data to the server, which then stores it in a central database for later analysis by the generative AI and emotion engine.

[0539] Input: Employee data sent from the terminal

[0540] Output: Data stored in a central database

[0541] Step 3:

[0542] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats. For example, it imputes missing data and detects and corrects outliers.

[0543] Input: Raw data in a central database

[0544] Output: Preprocessed dataset

[0545] Step 4:

[0546] The server passes the preprocessed data to the generation AI and emotion engine for analysis. The generation AI analyzes employees' behavioral characteristics and issues, while the emotion engine analyzes their emotional data. Specifically, for example, GPT-4 is used to analyze the characteristic data and issue data, and the Emotion API is used to analyze the emotional data.

[0547] Input: Preprocessed data

[0548] Output: Analysis results (characteristic data, issue data, emotion data)

[0549] Step 5:

[0550] The generative AI and emotion engine generate specific improvement and motivational measures based on each employee's characteristics, challenges, and emotions. These improvement measures are optimized for each employee. For example, for employee A, time management training and short-term goal setting are suggested.

[0551] Input: Analysis results

[0552] Output: Improvement proposals and motivational measures

[0553] Step 6:

[0554] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to a management terminal. Furthermore, the server provides the robot with optimal work instructions based on the employee's emotional data via the robot interface.

[0555] Input: Improvement ideas and motivational measures

[0556] Output: Report sent to the management terminal, work instructions to the robot

[0557] Step 7:

[0558] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[0559] Input: Effects of implemented countermeasures, new issues

[0560] Output: Save feedback data to database, reanalysis results

[0561] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0562] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0563] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0564] [Second embodiment]

[0565] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0566] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0567] 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 a "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).

[0568] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0569] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0570] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0571] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0572] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0573] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0574] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0575] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0576] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0577] This invention relates to a system that uses generative AI to analyze employees' behavioral characteristics, tone of voice, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system is designed to provide a work environment and measures suited to each employee, thereby improving their productivity and motivation.

[0578] System Overview

[0579] The system includes the following major components:

[0580] 1. Data Collection Device (hereinafter referred to as "Device")

[0581] 2. Central Database (hereinafter referred to as "Server")

[0582] 3. Generation AI

[0583] 4. Management Interface (hereinafter "Terminal")

[0584] Operational Overview

[0585] The system begins by entering data on an employee's behavioral characteristics, tone of voice, obstacles, and work challenges on a terminal and sending it to a server. The server stores this data in a central database and passes it to a generation AI for analysis. The generation AI generates improvement and motivational measures based on the individual employee's characteristics and sends them back to the management terminal. Based on these results, the manager can implement the optimal response for the employee.

[0586] Program processing

[0587] Data collection

[0588] The user inputs employee information (behavioral characteristics, tone of voice, obstacles, work issues) into the terminal. Each piece of information is collected in detail through specific forms and checklists.

[0589] Example input items:

[0590] Employee ID

[0591] Behavioral characteristics: Poor time management

[0592] Tone: Calm and polite

[0593] Disability: Attention Deficit Disorder (ADHD)

[0594] Work Challenge: Slow task completion speed

[0595] Data transmission and storage

[0596] The device sends the collected information to a server, which stores the received data in a central database for later analysis by the generative AI.

[0597] Characteristics analysis and problem analysis

[0598] The server preprocesses the stored data before passing it to the generation AI. This preprocessing ensures data integrity by filling in missing values ​​and detecting outliers.

[0599] The server then launches the generative AI, which analyzes employee characteristics and issues based on the preprocessed data. The generative AI then generates optimal improvement plans and motivational measures for each employee.

[0600] Generate improvement proposals

[0601] Generative AI generates specific improvement proposals and motivation-boosting measures tailored to each employee's characteristics and challenges.

[0602] This example generates:

[0603] Employee A's improvement suggestion:

[0604] Conducting time management training

[0605] Setting short-term goals and providing feedback

[0606] Motivate with positive praise

[0607] Employee B's improvement suggestion:

[0608] Organize your work environment and provide a space where you can focus

[0609] Incorporating a routine with short breaks

[0610] Introduction of an error checklist and confirmation before work begins

[0611] Output and action taken

[0612] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to the terminal. The user (administrator) receives this and takes specific measures for employees based on the report.

[0613] This example does the following:

[0614] Set goals for the day at your morning meeting

[0615] Providing feedback after completing a task

[0616] If they complete the task more quickly, they are given an extra break.

[0617] Feedback and Continuous Improvement

[0618] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends it back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generation AI. This allows for continuous optimal work styles and motivation management.

[0619] This system is a powerful tool for providing optimized support to each employee, improving their productivity and satisfaction. By utilizing generative AI, it is possible to respond to each individual employee and quickly implement approaches tailored to the characteristics of each employee.

[0620] The processing flow will be explained below.

[0621] Step 1:

[0622] Users enter data about employee behavioral traits, tone, obstacles, and work challenges into a terminal, using specific forms and checklists.

[0623] Step 2:

[0624] The terminal transmits the input data to the server.

[0625] Step 3:

[0626] The server stores the received data in a central database.

[0627] Step 4:

[0628] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[0629] Step 5:

[0630] The server passes the preprocessed data to the generation AI, which then launches it and analyzes the employee's behavioral characteristics and issues.

[0631] Step 6:

[0632] The generative AI generates improvement proposals and motivation-boosting measures based on each employee's characteristic data and issue data.

[0633] Step 7:

[0634] The server formats the generated improvement and motivational measures and creates a report for the management interface.

[0635] Step 8:

[0636] The server sends the report to the terminal.

[0637] Step 9:

[0638] The user (manager) receives the report and takes specific action against the employee based on it.

[0639] Step 10:

[0640] The user (administrator) inputs the effectiveness of the countermeasures and any new issues that have arisen into the terminal.

[0641] Step 11:

[0642] The terminal transmits the feedback data to the server.

[0643] Step 12:

[0644] The server stores the feedback data in a database and reanalyzes it using the generative AI, which then generates new improvement proposals and motivation-boosting strategies.

[0645] Step 13:

[0646] By repeating the process from step 6 onwards, optimal working styles and motivation management can be continuously achieved.

[0647] Example 1

[0648] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0649] As the working environment becomes more diverse, it is becoming increasingly important to provide optimal improvement plans and motivational measures for each employee, taking into account their behavioral characteristics, speech patterns, disabilities, and work challenges. However, collecting, analyzing, and continuously updating detailed data for individual responses makes it difficult to propose and implement effective improvement measures. For this reason, there is a need to develop a system that can quickly generate specific countermeasures tailored to each employee's characteristics and challenges, and continuously improve them based on feedback.

[0650] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0651] In this invention, the server includes means for collecting employee behavioral characteristics, tone of voice, details of obstacles, and work issues, means for sending the collected data to the server and storing it in a central database, means for preprocessing the stored data and filling in missing values ​​and detecting outliers, means for analyzing characteristics and issues using a generation AI based on the preprocessed data, means for generating improvement plans and motivation improvement measures tailored to each employee, means for sending the generated improvement plans and motivation improvement measures to a management terminal, means for re-collecting the effects of measures implemented by the manager and newly arising issues, and means for re-analyzing based on feedback data and making continuous improvements. This allows for the rapid provision of specific improvement plans and motivation improvement measures tailored to each employee's characteristics, enabling continuously optimized work styles and motivation management.

[0652] "Employee" refers to an individual who works for an organization or company.

[0653] "Behavioral characteristics" are elements that indicate an employee's behavioral patterns, habits, and characteristics in their work.

[0654] "Tone" refers to the way an employee speaks and the expressions they use when speaking.

[0655] "Disability details" refers to information including the employee's disability or special needs.

[0656] "Work challenges" refer to specific problems or difficulties that employees face in their work.

[0657] "Collection means" refers to the methods and devices used to aggregate information about employees.

[0658] A "server" is a computer system for storing, managing, and analyzing data.

[0659] A "central database" is a database system for centrally storing and managing collected data.

[0660] "Preprocessing" refers to processes such as filling in missing values ​​and detecting outliers before data analysis.

[0661] "Generative AI" refers to a system that uses artificial intelligence to analyze data, analyze characteristics and issues, and generate improvement proposals.

[0662] "Characteristic analysis" refers to analyzing employee characteristics based on collected data.

[0663] "Problem analysis" refers to identifying the specific challenges employees face through data analysis.

[0664] "Improvement proposals" refer to specific means or methods proposed to improve employees' work and increase efficiency.

[0665] "Motivation improvement measures" refer to specific proposals to increase employee motivation and morale.

[0666] "Administrative terminal" refers to a terminal used by an administrator to check data and implement countermeasures through the system.

[0667] "Feedback data" refers to data on the effectiveness of implemented countermeasures and new issues that have arisen.

[0668] "Continuous improvement" refers to repeatedly conducting new analyses and proposals based on feedback, rather than conducting a single analysis and proposal.

[0669] This invention relates to a system that analyzes employees' behavioral characteristics, tone, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system utilizes generative AI to provide a work environment and measures suited to each employee, and is designed to improve their productivity and motivation.

[0670] Hardware and software used

[0671] Hardware: Data collection terminal, central server, management terminal

[0672] Software: Generative AI (e.g., GPT-4), Database Management Systems (e.g., MySQL)

[0673] System Operation Overview

[0674] The user operates the data collection terminal to input detailed information about the employee. This information includes behavioral characteristics, tone of voice, obstacles, and work challenges. The data collection terminal encrypts the collected data and sends it to the server. The server stores the received data in a central database.

[0675] After the data is saved, the server performs preprocessing, which includes filling in missing values, detecting outliers, and normalizing the data. The preprocessed data is then passed to a generative AI that analyzes the characteristics and challenges of each employee. This analysis generates optimal improvement and motivational measures for each employee.

[0676] The improvement proposals and motivation-boosting measures generated by the generative AI are sent to a management terminal via a server. Based on this information, managers implement specific countermeasures for employees. Managers also re-enter the effectiveness of the countermeasures and any new issues that arise into a data collection terminal and send it to the server. The server stores this data in a database and re-analyzes it using the generative AI. This allows for continuous optimization.

[0677] Prompt Sentence Examples

[0678] Provide optimal improvement and motivational strategies based on employee details, such as:

[0679] Behavioral trait: Poor time management

[0680] Tone: Calm and polite

[0681] Disability: ADHD

[0682] Work Challenge: Slow task completion rate

[0683] Specific examples

[0684] The user inputs detailed information about Employee A into the data collection terminal. For example, information such as Employee A's behavioral characteristics as "poor time management," his tone of voice as "calm and polite," his disability as "ADHD," and his work challenges as "slow task completion speed" is collected. This information is sent to the server and stored in a central database.

[0685] The server preprocesses the data and passes the preprocessed data to the generation AI. The generation AI analyzes this data and generates specific improvement proposals, such as "conduct time management training" and "set short-term goals and provide feedback." The generated improvement proposals are sent to a management terminal, and the manager uses them to implement specific measures for employee A.

[0686] In this way, this system provides specific improvement measures tailored to the characteristics and needs of employees, aiming to increase productivity and satisfaction. The use of generative AI enables quick and individual responses, making it easier to implement approaches tailored to characteristics.

[0687] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0688] Step 1: Data collection

[0689] The user operates the terminal to input detailed information about the employee. Specifically, data on the employee's behavioral characteristics, tone of voice, obstacles, and work issues is collected using forms and checklists. The input information includes specific data such as "Employee A's ID, behavioral characteristics: poor time management, tone of voice: calm and polite, obstacles: ADHD, work issues: slow task completion speed." This input data is collected by the terminal.

[0690] Step 2: Send data

[0691] The device encrypts the collected information and sends it to the server. During the transmission process, the device sends data to the server in real time via the Internet, and the server receives the data. This transmitted data is in preparation for being stored in a database in the next step.

[0692] Step 3: Save Data

[0693] The server stores the received data in a central database. Specifically, a database management system (e.g., MySQL) is used to store the data while maintaining its integrity and consistency. This stored data serves as the basis for analysis by the generative AI. Once the input data has been stored, it is passed on to the next preprocessing step.

[0694] Step 4: Data Preprocessing

[0695] The server preprocesses the data stored in the central database. Preprocessing involves filling in missing values, detecting outliers, and normalizing the data. For example, if missing values ​​exist, they are filled in with the mean or median, and if outliers are detected, appropriate corrections are made. Once preprocessing is complete, the data is ready to be passed to the generative AI.

[0696] Step 5: Characteristics analysis and problem analysis

[0697] The server passes the preprocessed data to the generation AI, which analyzes the characteristics and issues. The generation AI (e.g., GPT-4) uses a deep learning algorithm to analyze the employee's characteristics and issues. Based on the input data, it identifies and analyzes Employee A's characteristic of "poor time management" and his issue of "slow task completion speed." The results of this analysis are used to generate improvement measures in the next step.

[0698] Step 6: Generate improvement ideas and motivational strategies

[0699] Based on the results of the characteristic analysis and issue analysis, the generative AI generates improvement proposals and motivational measures tailored to each employee. For example, for employee A, it generates specific improvement proposals such as "implementing training on time management" and "setting short-term goals and providing feedback." The generated improvement proposals are compiled in report format.

[0700] Step 7: Output and action taken

[0701] The server sends a report of the generated improvement proposals and motivational measures to the management terminal. The user (administrator) receives the report and implements specific countermeasures. For example, specific countermeasures such as "setting the day's goals in a morning meeting" and "providing feedback after completing tasks" are implemented based on the report.

[0702] Step 8: Feedback and continuous improvement

[0703] The user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues they have encountered into their device and sends it back to the server. This new feedback data is stored in a central database, and the server re-analyzes it using the AI ​​generation system, achieving continuous optimization. By continuously collecting and analyzing feedback data, the cycle of providing optimal countermeasures for each employee is maintained.

[0704] (Application example 1)

[0705] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0706] In recent years, there has been a demand for improved operational efficiency and accuracy for factory robots. However, there is still a lack of effective systems that can grasp the operational status of robots on-site in real time and provide optimal improvement proposals and maintenance measures. In particular, robot operation errors and reduced operational efficiency have a negative impact on productivity, which is a problem. Conventional systems rely on manual monitoring and judgment by operators and managers, and often make it difficult to respond quickly. For this reason, there is a need for the development of a new system that can monitor the operational status of factory robots in real time and use generative AI to provide optimal improvement proposals.

[0707] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0708] In this invention, the server includes means for using a generating AI to analyze employee behavioral characteristics, tone of voice, details of obstacles, and work issues, means for generating improvement plans and motivation improvement measures based on the resulting characteristic data and issue data, means for transmitting the generated improvement plans and motivation improvement measures to a manager's terminal, and means for monitoring the robot's operation status in real time with smart glasses and using that data to provide optimal improvement plans and maintenance measures. This makes it possible to reduce operation errors and improve operation efficiency by monitoring the operation status of factory robots in real time and having the generating AI provide optimal improvement plans and maintenance measures.

[0709] "Generative AI" is an artificial intelligence technology that analyzes data and automatically generates improvement plans and suggestions based on human behavior and characteristics.

[0710] "Behavioral characteristics" are patterns of performance and behavior of employees or robots in work situations.

[0711] "Tone" refers to the style of speaking and expression in audio data.

[0712] "Disability" refers to physical or mental handicaps or limitations that arise in the course of work.

[0713] "Job challenges" are the job-related problems and challenges that employees face.

[0714] "Characteristic data" is detailed information about the behavior and status of the employee or robot being analyzed.

[0715] "Challenge data" is information about a specific problem an employee or robot is facing.

[0716] "Improvement proposals" are specific action plans proposed to improve the performance of employees or robots.

[0717] "Motivation improvement measures" are specific proposals and measures to increase employee motivation and efficiency.

[0718] The "administrator's terminal" refers to a computer or smart device used by the administrator for operation.

[0719] "Robot operation status" refers to information about the progress of the work being performed by the factory robot and the accuracy of its movements.

[0720] "Smart glasses" are wearable devices that display real-time information and record on-site conditions.

[0721] "Maintenance measures" are specific management procedures and repair proposals to maintain the normal operation of robots and equipment.

[0722] This invention relates to a system that uses generative AI to analyze employee behavioral characteristics, speech patterns, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system is particularly useful for improving the operational efficiency and accuracy of factory robots. Specific embodiments of the system are described below.

[0723] Hardware and Software Configuration

[0724] 1. Hardware:

[0725] Smart glasses (e.g., Google Glass): Used to monitor the operation status of factory robots in real time.

[0726] Administrator's device: A device such as a PC or smartphone used to receive generated improvement proposals and motivational measures.

[0727] 2. Software:

[0728] Data collection application: Runs on the smart glasses and collects and transmits robot operation data.

[0729] Generative AI model: Runs on the server and analyzes and processes collected data.

[0730] System execution procedures and operations

[0731] 1. Data Collection:

[0732] The smart glasses monitor the operating status of factory robots (operating efficiency, error frequency, accuracy, etc.) in real time and periodically send this data to a server.

[0733] 2. Data transmission and storage:

[0734] The server stores the received data in a central database, which is then used for analysis by the generative AI.

[0735] 3. Characteristics and Issues Analysis:

[0736] The server preprocesses the stored data before passing it to the generation AI, which performs missing value imputation and outlier detection to maintain data integrity.

[0737] Next, the server launches the generative AI, which uses the preprocessed data to perform characteristic analysis and problem analysis related to the operational efficiency and accuracy of the factory robot.

[0738] 4. Generate improvement proposals:

[0739] The generative AI generates optimal improvement and maintenance plans based on the robot's characteristic data and problem data.

[0740] 5. Output and action taken:

[0741] The server compiles the generated improvement proposals and maintenance measures into a report format and sends it to the administrator's terminal.

[0742] The user (administrator) receives this report and takes specific countermeasures on-site based on the report.

[0743] Specific examples

[0744] For example, if a factory robot has an operating efficiency of 85%, an error frequency of 2, and an accuracy of 90%, the data collected by the smart glasses will be converted into the following prompt sentence:

[0745] "Analyze the operational activity data of a factory robot and generate optimal improvement and maintenance plans to improve efficiency. The following data was collected: operational efficiency: 85%, error frequency: 2 times, accuracy: 90%."

[0746] If you feed this prompt to a generative AI model, you'll get the following response:

[0747] To improve the efficiency of your robot's operation, we recommend the following steps:

[0748] 1. Standardizing operating procedures and providing training

[0749] 2. Shorter maintenance intervals

[0750] 3. Software updates to improve operation accuracy

[0751] By generating specific improvement plans in this way, it is possible to effectively improve the operating conditions of factory robots and increase productivity.

[0752] This system can be applied not only to factory robots, but also to managing other employees and improving their performance. It also includes a function that continuously updates data specific to each employee and regenerates new improvement proposals and motivational measures based on previous feedback data. This allows for continuous optimal work styles and motivation management.

[0753] Finally, by utilizing generative AI, this invention enables rapid implementation of approaches tailored to the characteristics of employees and robots, making it easier to respond to individual needs.

[0754] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0755] Step 1:

[0756] Data collection

[0757] Input: The robot's operation status (operation efficiency, error frequency, accuracy, etc.) is obtained in real time from the smart glasses.

[0758] How it works: The smart glasses use sensors to collect data on the robot's operations and record it digitally.

[0759] Output: The collected operation data is sent from the terminal (smart glasses) to the server.

[0760] Step 2:

[0761] Data transmission and storage

[0762] Input: Robot operation data sent from the terminal.

[0763] Specific operation: The server receives the received data in real time and stores it in a central database.

[0764] Output: The saved operational data is used for the next analysis step.

[0765] Step 3:

[0766] Characteristics analysis and problem analysis

[0767] Input: Robot operation data stored in a central database.

[0768] Specific operation: The server performs preprocessing, imputes missing values ​​in the data, detects outliers, and maintains data integrity. The preprocessed data is then passed to the generation AI.

[0769] Output: Preprocessed data passed to the generative AI.

[0770] Step 4:

[0771] Generative AI startup and analysis

[0772] Input: Preprocessed operational data.

[0773] Specific operation: The generative AI analyzes the robot's characteristics and issues based on the input data. For example, it analyzes based on data such as 85% operational efficiency, 2 error frequencies, and 90% accuracy.

[0774] Output: Analysis results based on characteristic data and problem data regarding the robot's operating situation.

[0775] Step 5:

[0776] Generate improvement proposals

[0777] Input: Analysis results (characteristic data and problem data).

[0778] Specific actions: The generative AI generates optimal improvement and maintenance plans from the analysis results, such as standardizing operating procedures, shortening maintenance intervals, and proposing software updates.

[0779] Output: Generated improvement and maintenance recommendations.

[0780] Step 6:

[0781] Output and action taken

[0782] Input: Generated improvement and maintenance measures.

[0783] Specific operation: The server compiles the generated improvement proposals and maintenance measures into a report format and sends it to the administrator's terminal.

[0784] Output: Report received on administrator's terminal.

[0785] Step 7:

[0786] Feedback and Continuous Improvement

[0787] Input: Feedback data on the effectiveness of measures taken by administrators and new issues that have arisen.

[0788] Specific operation: The user (administrator) inputs feedback data into the terminal and sends it to the server, which stores it in a database and reanalyzes it as feedback data using the generation AI.

[0789] Output: Continuous improvement recommendations based on new feedback data.

[0790] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0791] This invention relates to a system that uses generative AI to analyze employees' behavioral characteristics, tone of voice, obstacles, and work challenges, and also to a system that uses an emotion engine to analyze employees' emotional data and provide optimal improvement proposals and motivational measures. This system is designed to provide a work environment and measures that are suited to each individual employee, thereby improving their productivity and motivation.

[0792] System Overview

[0793] The system includes the following major components:

[0794] 1. Data Collection Device (hereinafter referred to as "Device")

[0795] 2. Central Database (hereinafter referred to as "Server")

[0796] 3. Generation AI

[0797] 4. Emotion Engine

[0798] 5. Management Interface (hereinafter "Terminal")

[0799] Operational Overview

[0800] The system begins by entering an employee's behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data into a terminal and sending it to a server. The server stores this data in a central database and passes it to a generative AI and emotion engine for analysis. The generative AI generates improvement and motivational measures based on the employee's individual characteristics and emotions and sends them back to the management terminal. Based on these results, the manager can implement the optimal response for the employee.

[0801] Program processing

[0802] Data collection

[0803] Users input employee information (behavioral characteristics, tone of voice, obstacles, work challenges) and emotional data into the terminal. Each piece of information is collected in detail using specific forms and checklists, as well as emotion recognition technology.

[0804] Example input items:

[0805] Employee ID

[0806] Behavioral characteristics: Poor time management

[0807] Tone: Calm and polite

[0808] Disability: Attention Deficit Disorder (ADHD)

[0809] Work Challenge: Slow task completion speed

[0810] Emotional data: Stress levels based on facial expressions and voice analysis

[0811] Data transmission and storage

[0812] The device sends the input data to a server, which stores it in a central database for later analysis by the generative AI and emotion engine.

[0813] Characteristics analysis and problem analysis

[0814] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[0815] The server then passes the preprocessed data to the generation AI and emotion engine for analysis. The generation AI analyzes the employee's behavioral characteristics and issues, while the emotion engine analyzes the employee's emotional data.

[0816] Generate improvement proposals

[0817] Generative AI and an emotion engine generate specific improvement proposals and motivational measures based on each employee's individual characteristics, challenges, and emotions.

[0818] This example generates:

[0819] Employee A's improvement suggestion:

[0820] Conducting time management training

[0821] Setting short-term goals and providing feedback

[0822] Motivate with positive praise

[0823] Introducing relaxation techniques based on emotional data

[0824] Employee B's improvement suggestion:

[0825] Organize your work environment and provide a space where you can focus

[0826] Incorporating a routine with short breaks

[0827] Introduction of an error checklist and confirmation before work begins

[0828] Introducing stress management methods based on emotional data

[0829] Output and action taken

[0830] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to the terminal. The user (administrator) receives this and takes specific measures for employees based on the report.

[0831] This example does the following:

[0832] Set goals for the day at your morning meeting

[0833] Providing feedback after completing a task

[0834] If they complete the task more quickly, they are given an extra break.

[0835] Implement relaxation and stress management techniques based on emotional data

[0836] Feedback and Continuous Improvement

[0837] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[0838] This system is a powerful tool for providing optimized support to each employee, improving their productivity and satisfaction. Utilizing generative AI and an emotion engine, it enables personalized responses and quickly implements approaches tailored to the employee's characteristics and emotions.

[0839] The processing flow will be explained below.

[0840] Step 1:

[0841] Users input employee behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data into a terminal using specific forms and checklists, as well as emotion recognition technology (e.g., facial expression analysis cameras and voice recognition microphones).

[0842] Step 2:

[0843] The device sends the entered data to the server, where it is encrypted and transmitted using a secure protocol.

[0844] Step 3:

[0845] The server stores the received data in a central database, which stores each employee's behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data.

[0846] Step 4:

[0847] The server preprocesses the stored data. This preprocessing includes filling in missing data, detecting outliers, and standardizing data formats. Data preprocessing is essential to improve the accuracy of analysis.

[0848] Step 5:

[0849] The server passes the preprocessed data to the generation AI and emotion engine. The generation AI analyzes the employee's behavioral characteristics and issues, and the emotion engine analyzes the employee's emotional data.

[0850] Step 6:

[0851] The generative AI analyzes the characteristic data and issue data for each employee, and the emotion engine analyzes the emotional data. Based on the results of this analysis, it generates optimal improvement plans and motivation-boosting measures.

[0852] Step 7:

[0853] The server formats the generated improvement and motivational measures and creates a report for the management interface, which includes the analysis results and specific countermeasures.

[0854] Step 8:

[0855] The server sends the report to the terminal, which is provided in a format that is easy for the administrator to understand.

[0856] Step 9:

[0857] The user (manager) receives the report and takes specific action based on it, including suggestions for improvement and motivation provided by the generative AI and emotion engine.

[0858] Step 10:

[0859] The user (administrator) evaluates the effectiveness of the countermeasures and any new issues that arise, and enters the evaluation results and feedback data into the terminal.

[0860] Step 11:

[0861] The terminal sends feedback data to the server, which is stored in a central database in the same way as the initial data.

[0862] Step 12:

[0863] The server reanalyzes the feedback data using the generative AI and emotion engine, which is used as important input data for the next improvement plan.

[0864] Step 13:

[0865] The server then formats the new improvement proposals and motivation-boosting measures into a report and sends it to the device. This process is repeated to continuously optimize work styles and motivation management.

[0866] In this way, the system can continuously analyze employees' characteristics and emotions and provide optimal improvement and motivational strategies.

[0867] Example 2

[0868] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0869] In today's workplace, improving employee productivity and motivation is a key challenge. However, accurately understanding the behavioral characteristics and emotional state of each employee and responding to them individually can be difficult. It is also not easy to quickly provide appropriate improvement proposals and motivation-boosting measures based on employees' characteristics and challenges. A system that effectively utilizes employee emotional data to achieve specific behavioral improvements and motivational improvements is needed.

[0870] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0871] In this invention, the server includes: means for analyzing employee behavioral characteristics, tone of voice, obstacles, and work issues using a generation AI; means for generating improvement plans and motivation-boosting measures based on the resulting characteristic data and issue data; means including an emotion analysis engine for analyzing the collected emotion data and proposing appropriate measures based on the employee's emotions; and means for sending the generated improvement plans and motivation-boosting measures to a manager's terminal in report format. This enables the rapid provision of optimized support for each employee, improving productivity and motivation.

[0872] "Generative AI" is a system that uses artificial intelligence techniques to analyze data and generate outputs or results suitable for specific purposes.

[0873] "Behavioral characteristics" are characteristics related to employee behavior patterns, habits, and actions.

[0874] "Tone" refers to the characteristics of the language and communication style used by employees.

[0875] "Disability details" is information about an employee's specific disability and its impact.

[0876] "Work challenges" are work-related problems employees face or areas that need improvement.

[0877] "Characteristic data" refers to information regarding the behavioral characteristics, tone of voice, and disability details of the employee being analyzed.

[0878] "Issue data" refers to information regarding business issues and areas requiring improvement.

[0879] An "improvement proposal" is a specific improvement measure proposed based on the employee's behavioral characteristics and challenges.

[0880] "Motivation improvement measures" are specific measures to increase employee motivation and enthusiasm.

[0881] "Emotional data" is data that indicates an employee's emotional state and is typically collected through facial and voice analysis.

[0882] An "emotion analysis engine" is a system that analyzes emotional data, evaluates employees' emotional state, and generates countermeasures based on that.

[0883] "Administrator's terminal" refers to a computer or device used by the system administrator to receive generated reports and improvement proposals.

[0884] This invention is a system that utilizes generative AI and an emotion analysis engine to analyze employees' behavioral characteristics, tone of voice, obstacles, work issues, and emotional data, and provides optimal improvement plans and motivational measures for each employee. This system consists of a data collection terminal, a server, generative AI, an emotion analysis engine, and a management terminal.

[0885] Hardware and Software Use

[0886] Data collection device: A computer or mobile device used to collect employee behavioral characteristics, tone, obstacles, work challenges, and emotional data. This device is equipped with sensors such as a camera and microphone and is also used to collect emotional data.

[0887] Server: A computer that stores collected data in a central database and passes it to the generation AI and emotion analysis engine. It also transmits generated improvement proposals and motivational measures to the management terminal.

[0888] Generative AI: An artificial intelligence model used to analyze employee behavioral characteristics and challenges. This AI generates optimal improvement plans and motivational measures based on data for each employee.

[0889] Sentiment Analysis Engine: Software that analyzes emotional data and assesses the emotional state of employees, allowing it to suggest countermeasures based on their emotions.

[0890] Management terminal: A computer or device where a manager receives generated reports and takes action against employees.

[0891] Explanation of program processing

[0892] Users enter employee behavioral characteristics, tone, obstacles, work challenges, and emotional data into data collection devices. This data is collected through forms, checklists, cameras, and microphones.

[0893] Specifically, the following data is entered:

[0894] Employee ID

[0895] Behavioral characteristics: Poor time management

[0896] Tone: Calm and polite

[0897] Disability: Attention Deficit Disorder (ADHD)

[0898] Work Challenge: Slow task completion speed

[0899] Emotional data collected using a camera and microphone: stress levels through facial and voice analysis

[0900] The terminal encrypts the input data and transmits it in real time to the server, which stores the received data in a central database and performs pre-processing on the data, including missing value imputation, outlier detection, and data format standardization.

[0901] The server then passes the preprocessed data to the generation AI and emotion analysis engine for analysis. The generation AI analyzes employees' behavioral characteristics and issues, and generates optimal improvement proposals and motivation-boosting measures. At the same time, the emotion analysis engine analyzes the emotional data and proposes countermeasures based on the employee's emotional state.

[0902] The generated improvement proposals and motivation-boosting measures are compiled into a report and sent to a management terminal. The user (manager) then implements specific measures for the employees based on this report.

[0903] for example:

[0904] Set goals for the day at your morning meeting

[0905] Providing feedback after completing a task

[0906] Offer additional breaks if the task can be completed more quickly

[0907] Implement relaxation and stress management techniques based on emotional data

[0908] Finally, the user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues that have arisen into the terminal and sends it back to the server, allowing the system to continuously update the data and continue to provide optimal improvement proposals and motivation-boosting measures.

[0909] Example prompts for generative AI models

[0910] Below are some example prompts to be input to the generative AI model:

[0911] Prompt statement:

[0912] Employee ID: 12345

[0913] Behavioral trait: Poor time management

[0914] Tone: Calm and polite

[0915] Disability: ADHD

[0916] Work Challenge: Slow task completion rate

[0917] Emotion data: High stress level based on facial expression analysis

[0918] Generate optimal improvement and motivational strategies.

[0919] This makes it possible to provide each employee with quick, optimized support, improving productivity and motivation.

[0920] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0921] Step 1:

[0922] Data collection

[0923] Users input employee behavioral characteristics, tone of voice, obstacles, work tasks, and emotional data into a terminal. This input data is collected through forms, checklists, cameras, and microphones.

[0924] Input: Employee ID, behavioral characteristics, tone of voice, obstacle details, work issues, emotional data

[0925] Specific behavior:

[0926] The user enters an employee ID into a form.

[0927] Select a behavioral trait from the selection list.

[0928] Enter the tone.

[0929] Check the fault details.

[0930] Enter work assignments.

[0931] Emotional data (facial expression analysis, voice analysis) is collected using a camera and microphone.

[0932] Step 2:

[0933] Data transmission

[0934] The device encrypts the entered data and sends it to the server. The data is sent in real time to prevent data leakage during transmission.

[0935] Input: Employee data entered into the terminal

[0936] Output: The encrypted data is sent to the server

[0937] Specific behavior:

[0938] The device encrypts all input data at once.

[0939] The encrypted data is sent to the server.

[0940] Step 3:

[0941] Data storage

[0942] The server deserializes the received data and stores it in a central database, where the storage is performed transactionally to ensure consistency and integrity.

[0943] Input: Encrypted data sent to the server

[0944] Output: Employee data deserialized and saved to the database

[0945] Specific behavior:

[0946] The server decrypts the received data.

[0947] The data is deserialized and stored in a central database.

[0948] Step 4:

[0949] Data Preprocessing

[0950] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[0951] Input: Stored raw data

[0952] Output: Preprocessed data

[0953] Specific behavior:

[0954] The server detects and completes missing values ​​in the stored data.

[0955] Correct any abnormal values.

[0956] Transform data into a unified format.

[0957] Step 5:

[0958] Characteristics analysis and problem analysis

[0959] The server passes the preprocessed data to the generation AI and sentiment analysis engine for analysis. The generation AI analyzes employee behavioral characteristics and issues, while the sentiment analysis engine analyzes the emotional data.

[0960] Input: Preprocessed data

[0961] Output: Analysis results (behavioral characteristics, tasks, emotional state)

[0962] Specific behavior:

[0963] The server converts the data into an input format for the generative AI model.

[0964] The generative AI analyzes behavioral characteristics and challenges and outputs the results.

[0965] The emotion analysis engine analyzes the emotion data and outputs the emotional state.

[0966] Step 6:

[0967] Generate improvement proposals

[0968] Generative AI and an emotion analysis engine generate specific improvement proposals and motivational measures based on each employee's characteristics, challenges, and emotions.

[0969] Input: Analysis results (behavioral characteristics, tasks, emotional state)

[0970] Output: Improvement proposals and motivational measures

[0971] Specific behavior:

[0972] The server receives the analysis results from the generation AI and the sentiment analysis engine.

[0973] Generate optimal improvement plans and motivation measures for each employee.

[0974] Step 7:

[0975] Output of improvement proposals

[0976] The server compiles the generated improvement proposals and motivation-boosting measures into a report format and sends it to the management terminal.

[0977] Input: Generated improvement ideas and motivational measures

[0978] Output: Report format data. Send to management terminal.

[0979] Specific behavior:

[0980] The server formats the data using a report template.

[0981] The formatted report is sent to the management terminal.

[0982] Step 8:

[0983] Implementing countermeasures

[0984] The user (manager) takes specific measures for the employee based on the report.

[0985] Input: Report sent to management terminal

[0986] Output: Implementing action against employee

[0987] Specific behavior:

[0988] The user (administrator) sets the day's goals at a morning meeting.

[0989] Provide feedback after completing a task.

[0990] If they can complete the task more quickly, they are given an extra break.

[0991] Relaxation and stress management techniques are implemented based on emotional data.

[0992] Step 9:

[0993] Feedback and Continuous Improvement

[0994] The user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues they have encountered into the terminal and sends it back to the server. This updates the database, and the new feedback data is reanalyzed by the generation AI and emotion analysis engine.

[0995] Input: Feedback data, effectiveness of countermeasures, new issues

[0996] Output: Updated data, continuous improvement ideas and motivational measures

[0997] Specific behavior:

[0998] The user (administrator) inputs the feedback data into the terminal.

[0999] The device sends this to the server, where it is stored in a database.

[1000] The server reanalyzes the feedback data and generates new improvement suggestions.

[1001] (Application example 2)

[1002] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1003] When workers and robots work together in factories, optimal work instructions and support that take into account the behavioral characteristics and emotional data of workers are not being provided, which is a problem that leads to reduced productivity and increased stress among workers. Furthermore, there is a lack of individualized measures for each worker, making it difficult to respond quickly and accurately, which makes it difficult to improve worker motivation and provide an efficient work environment.

[1004] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing an employee's behavioral characteristics, tone of voice, obstacle details, and work issues using a generation AI, means for generating improvement plans and motivation improvement measures based on the resulting characteristic data and issue data, means for sending the generated improvement plans and motivation improvement measures to a manager's terminal, means for analyzing employee emotion data and optimizing robot work instructions based on the analysis results, and means for detecting an employee's stress level and suggesting appropriate rest. This allows work instructions and support optimized for each employee to be automatically provided, improving productivity and reducing employee stress.

[1005] "Generative AI" is an artificial intelligence that uses artificial intelligence technology to analyze employees' behavioral characteristics and work challenges, and automatically generates appropriate improvement proposals and motivation-boosting measures.

[1006] "Behavioral characteristics" refer to an employee's working style and behavioral patterns, such as strengths and weaknesses in time management and the speed at which tasks are completed.

[1007] "Tone of speech" refers to the characteristics of an employee's language and speaking style, such as a calm and polite manner of speaking or a strong tone of voice.

[1008] "Disability" means information about an employee's disability, such as attention deficit disorder or physical limitations.

[1009] "Work challenges" refer to problems or difficulties an employee faces in performing their job, such as slow task completion.

[1010] "Characteristic data" refers to data obtained as a result of analysis, such as employee behavioral characteristics and the nature of obstacles.

[1011] "Issue data" refers to data related to the work issues of employees obtained as a result of the analysis.

[1012] "Emotional data" is data that indicates an employee's emotional state and is collected through voice analysis and facial expression recognition.

[1013] "Improvement proposals" are specific improvement measures created based on an employee's behavioral characteristics and work challenges, and include, for example, training on time management.

[1014] "Motivation measures" are specific means to increase employees' motivation to work, and include setting short-term goals and motivating employees through praise.

[1015] "Administrator's device" refers to a computer or smart device used by a supervisor or manager, and is a device used to view and manage employee characteristic data and improvement proposals.

[1016] "Robot work instructions" refers to automatically giving instructions to robots in factories to optimize their collaborative work with employees.

[1017] "Break suggestion" means sensing an employee's stress level and suggesting a break at the appropriate time if necessary.

[1018] This invention realizes a system that analyzes employee behavioral characteristics, speech patterns, obstacles, work challenges, and emotional data to provide optimal improvement plans and motivational measures in order to optimize collaboration between employees and robots in a factory. A specific embodiment of this system will be described below.

[1019] System Overview

[1020] The system includes the following major components:

[1021] 1. Data Collection Device (hereinafter referred to as "Device")

[1022] 2. Central Database (hereinafter referred to as "Server")

[1023] 3. Generation AI

[1024] 4. Emotion Engine

[1025] 5. Robot Operation Interface (hereinafter "Robot Interface")

[1026] 6. Management terminal (hereinafter referred to as "Management terminal")

[1027] Operational Overview

[1028] The user inputs the employee's behavioral characteristics, tone of voice, details of the obstacles, work issues, and emotional data into the terminal and sends it to the server. The server stores this data in a central database and passes it to the generation AI and emotion engine for analysis. The generation AI generates improvement proposals and motivational measures based on the employee's individual characteristics and emotions and sends them back to the management terminal. It also provides the robot with optimal work instructions through the robot interface. Based on these results, the manager can implement the optimal response for the employee.

[1029] Program processing

[1030] Data collection

[1031] Users input employee information (behavioral characteristics, tone of voice, obstacles, work challenges) and emotional data into the terminal. Each piece of information is collected in detail using specific forms and checklists, as well as emotion recognition technology.

[1032] Example input items:

[1033] Employee ID

[1034] Behavioral characteristics: Poor time management

[1035] Tone: Calm and polite

[1036] Disability: Attention Deficit Disorder (ADHD)

[1037] Work Challenge: Slow task completion speed

[1038] Emotional data: Stress levels based on facial expressions and voice analysis

[1039] Data transmission and storage

[1040] The device sends the input data to a server, which stores it in a central database for later analysis by the generative AI and emotion engine.

[1041] Characteristics analysis and problem analysis

[1042] The server preprocesses the stored data. This preprocessing includes filling in missing values, detecting outliers, and standardizing data formats. The server then passes the preprocessed data to the generative AI and emotion engine for analysis. The generative AI analyzes employee behavioral characteristics and issues, while the emotion engine analyzes employee emotional data.

[1043] Generate improvement proposals and motivational measures

[1044] Generative AI and an emotion engine generate specific improvement proposals and motivational measures based on each employee's individual characteristics, challenges, and emotions.

[1045] This example generates:

[1046] Employee A's improvement suggestion:

[1047] Conducting time management training

[1048] Setting short-term goals and providing feedback

[1049] Motivate with positive praise

[1050] Introducing relaxation techniques based on emotional data

[1051] Employee B's improvement suggestion:

[1052] Organize your work environment and provide a space where you can focus

[1053] Incorporating a routine with short breaks

[1054] Introduction of an error checklist and confirmation before work begins

[1055] Introducing stress management methods based on emotional data

[1056] Output and action taken

[1057] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to a management terminal. The user (manager) receives this report and implements specific measures for employees based on the report. The server also provides the robot with optimal work instructions based on the employee's emotional data through the robot interface.

[1058] This example does the following:

[1059] Set goals for the day at your morning meeting

[1060] Providing feedback after completing a task

[1061] If they complete the task more quickly, they are given an extra break.

[1062] Implement relaxation and stress management techniques based on emotional data

[1063] Feedback and Continuous Improvement

[1064] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[1065] Example prompts to input to a generative AI model:

[1066] Prompt: Based on Employee A's behavioral and emotional data, please suggest the best improvement and motivational measures for him.

[1067] Behavioral data: Poor time management, slow task completion

[1068] Emotional data: high stress level, tired facial expression

[1069] As described above, this invention is a powerful tool for providing optimized support to each employee and improving their productivity and satisfaction. By utilizing generative AI and an emotion engine, personalized responses are possible, and approaches tailored to the employee's characteristics and emotions can be quickly implemented.

[1070] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1071] Step 1:

[1072] The user inputs employee information (behavioral characteristics, tone of voice, obstacles, and work challenges) and emotional data into the terminal. Specific forms and checklists are used to collect detailed data, which is then analyzed using emotion recognition technology. For example, the user inputs the employee's ID, behavioral characteristics (poor time management), tone of voice (calm and polite), obstacles (attention deficit disorder), work challenges (slow task completion speed), and emotional data (stress level determined by facial and voice analysis).

[1073] Input: Employee behavioral characteristics, tone of voice, obstacles, work issues, emotional data

[1074] Output: A set of input data

[1075] Step 2:

[1076] The device sends the input data to the server, which then stores it in a central database for later analysis by the generative AI and emotion engine.

[1077] Input: Employee data sent from the terminal

[1078] Output: Data stored in a central database

[1079] Step 3:

[1080] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats. For example, it imputes missing data and detects and corrects outliers.

[1081] Input: Raw data in a central database

[1082] Output: Preprocessed dataset

[1083] Step 4:

[1084] The server passes the preprocessed data to the generation AI and emotion engine for analysis. The generation AI analyzes employees' behavioral characteristics and issues, while the emotion engine analyzes their emotional data. Specifically, for example, GPT-4 is used to analyze the characteristic data and issue data, and the Emotion API is used to analyze the emotional data.

[1085] Input: Preprocessed data

[1086] Output: Analysis results (characteristic data, issue data, emotion data)

[1087] Step 5:

[1088] The generative AI and emotion engine generate specific improvement and motivational measures based on each employee's characteristics, challenges, and emotions. These improvement measures are optimized for each employee. For example, for employee A, time management training and short-term goal setting are suggested.

[1089] Input: Analysis results

[1090] Output: Improvement proposals and motivational measures

[1091] Step 6:

[1092] The server compiles the generated improvement proposals and motivation-boosting measures into a report format and sends it to a management terminal. Furthermore, the robot interface provides the robot with optimal work instructions based on the employee's emotional data.

[1093] Input: Improvement ideas and motivational measures

[1094] Output: Report sent to the management terminal, work instructions to the robot

[1095] Step 7:

[1096] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[1097] Input: Effects of implemented countermeasures, new issues

[1098] Output: Save feedback data to database, reanalysis results

[1099] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1100] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1101] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1102] [Third embodiment]

[1103] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1104] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1105] 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 a "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).

[1106] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1107] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1109] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1110] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1111] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1112] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1113] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1114] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1115] This invention relates to a system that uses generative AI to analyze employees' behavioral characteristics, tone of voice, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system is designed to provide a work environment and measures suited to each employee, thereby improving their productivity and motivation.

[1116] System Overview

[1117] The system includes the following major components:

[1118] 1. Data Collection Device (hereinafter referred to as "Device")

[1119] 2. Central Database (hereinafter referred to as "Server")

[1120] 3. Generation AI

[1121] 4. Management Interface (hereinafter "Terminal")

[1122] Operational Overview

[1123] The system begins by entering data on an employee's behavioral characteristics, tone of voice, obstacles, and work challenges on a terminal and sending it to a server. The server stores this data in a central database and passes it to a generation AI for analysis. The generation AI generates improvement and motivational measures based on the individual employee's characteristics and sends them back to the management terminal. Based on these results, the manager can implement the optimal response for the employee.

[1124] Program processing

[1125] Data collection

[1126] The user inputs employee information (behavioral characteristics, tone of voice, obstacles, work issues) into the terminal. Each piece of information is collected in detail through specific forms and checklists.

[1127] Example input items:

[1128] Employee ID

[1129] Behavioral characteristics: Poor time management

[1130] Tone: Calm and polite

[1131] Disability: Attention Deficit Disorder (ADHD)

[1132] Work Challenge: Slow task completion speed

[1133] Data transmission and storage

[1134] The device sends the collected information to a server, which stores the received data in a central database for later analysis by the generative AI.

[1135] Characteristics analysis and problem analysis

[1136] The server preprocesses the stored data before passing it to the generation AI. This preprocessing ensures data integrity by filling in missing values ​​and detecting outliers.

[1137] The server then launches the generative AI, which analyzes employee characteristics and issues based on the preprocessed data. The generative AI then generates optimal improvement plans and motivational measures for each employee.

[1138] Generate improvement proposals

[1139] Generative AI generates specific improvement proposals and motivation-boosting measures tailored to each employee's characteristics and challenges.

[1140] This example generates:

[1141] Employee A's improvement suggestion:

[1142] Conducting time management training

[1143] Setting short-term goals and providing feedback

[1144] Motivate with positive praise

[1145] Employee B's improvement suggestion:

[1146] Organize your work environment and provide a space where you can focus

[1147] Incorporating a routine with short breaks

[1148] Introduction of an error checklist and confirmation before work begins

[1149] Output and action taken

[1150] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to the terminal. The user (administrator) receives this and takes specific measures for employees based on the report.

[1151] This example does the following:

[1152] Set goals for the day at your morning meeting

[1153] Providing feedback after completing a task

[1154] If they complete the task more quickly, they are given an extra break.

[1155] Feedback and Continuous Improvement

[1156] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends it back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generation AI. This allows for continuous optimal work styles and motivation management.

[1157] This system is a powerful tool for providing optimized support to each employee, improving their productivity and satisfaction. By utilizing generative AI, it is possible to respond to each individual employee and quickly implement approaches tailored to the characteristics of each employee.

[1158] The processing flow will be explained below.

[1159] Step 1:

[1160] Users enter data about employee behavioral traits, tone, obstacles, and work challenges into a terminal, using specific forms and checklists.

[1161] Step 2:

[1162] The terminal transmits the input data to the server.

[1163] Step 3:

[1164] The server stores the received data in a central database.

[1165] Step 4:

[1166] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[1167] Step 5:

[1168] The server passes the preprocessed data to the generation AI, which then launches it and analyzes the employee's behavioral characteristics and issues.

[1169] Step 6:

[1170] The generative AI generates improvement proposals and motivation-boosting measures based on each employee's characteristic data and issue data.

[1171] Step 7:

[1172] The server formats the generated improvement and motivational measures and creates a report for the management interface.

[1173] Step 8:

[1174] The server sends the report to the terminal.

[1175] Step 9:

[1176] The user (manager) receives the report and takes specific action against the employee based on it.

[1177] Step 10:

[1178] The user (administrator) inputs the effectiveness of the countermeasures and any new issues that have arisen into the terminal.

[1179] Step 11:

[1180] The terminal transmits the feedback data to the server.

[1181] Step 12:

[1182] The server stores the feedback data in a database and reanalyzes it using the generative AI, which then generates new improvement proposals and motivation-boosting strategies.

[1183] Step 13:

[1184] By repeating the process from step 6 onwards, optimal working styles and motivation management can be continuously achieved.

[1185] Example 1

[1186] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1187] As the working environment becomes more diverse, it is becoming increasingly important to provide optimal improvement plans and motivational measures for each employee, taking into account their behavioral characteristics, speech patterns, disabilities, and work challenges. However, collecting, analyzing, and continuously updating detailed data for individual responses makes it difficult to propose and implement effective improvement measures. For this reason, there is a need to develop a system that can quickly generate specific countermeasures tailored to each employee's characteristics and challenges, and continuously improve them based on feedback.

[1188] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1189] In this invention, the server includes means for collecting employee behavioral characteristics, tone of voice, details of obstacles, and work issues, means for sending the collected data to the server and storing it in a central database, means for preprocessing the stored data and filling in missing values ​​and detecting outliers, means for analyzing characteristics and issues using a generation AI based on the preprocessed data, means for generating improvement plans and motivation improvement measures tailored to each employee, means for sending the generated improvement plans and motivation improvement measures to a management terminal, means for re-collecting the effects of measures implemented by the manager and newly arising issues, and means for re-analyzing based on feedback data and making continuous improvements. This allows for the rapid provision of specific improvement plans and motivation improvement measures tailored to each employee's characteristics, enabling continuously optimized work styles and motivation management.

[1190] "Employee" refers to an individual who works for an organization or company.

[1191] "Behavioral characteristics" are elements that indicate an employee's behavioral patterns, habits, and characteristics in their work.

[1192] "Tone" refers to the way an employee speaks and the expressions they use when speaking.

[1193] "Disability details" refers to information including the employee's disability or special needs.

[1194] "Work challenges" refer to specific problems or difficulties that employees face in their work.

[1195] "Collection means" refers to the methods and devices used to aggregate information about employees.

[1196] A "server" is a computer system for storing, managing, and analyzing data.

[1197] A "central database" is a database system for centrally storing and managing collected data.

[1198] "Preprocessing" refers to processes such as filling in missing values ​​and detecting outliers before data analysis.

[1199] "Generative AI" refers to a system that uses artificial intelligence to analyze data, analyze characteristics and issues, and generate improvement proposals.

[1200] "Characteristic analysis" refers to analyzing employee characteristics based on collected data.

[1201] "Problem analysis" refers to identifying the specific challenges employees face through data analysis.

[1202] "Improvement proposals" refer to specific means or methods proposed to improve employees' work and increase efficiency.

[1203] "Motivation improvement measures" refer to specific proposals to increase employee motivation and morale.

[1204] "Administrative terminal" refers to a terminal used by an administrator to check data and implement countermeasures through the system.

[1205] "Feedback data" refers to data on the effectiveness of implemented countermeasures and new issues that have arisen.

[1206] "Continuous improvement" refers to repeatedly conducting new analyses and proposals based on feedback, rather than conducting a single analysis and proposal.

[1207] This invention relates to a system that analyzes employees' behavioral characteristics, tone, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system utilizes generative AI to provide a work environment and measures suited to each employee, and is designed to improve their productivity and motivation.

[1208] Hardware and software used

[1209] Hardware: Data collection terminal, central server, management terminal

[1210] Software: Generative AI (e.g., GPT-4), Database Management Systems (e.g., MySQL)

[1211] System Operation Overview

[1212] The user operates the data collection terminal to input detailed information about the employee, including behavioral characteristics, tone of voice, obstacles, and work challenges. The data collection terminal encrypts the collected data and sends it to the server, which stores the received data in a central database.

[1213] After the data is saved, the server performs preprocessing, which includes filling in missing values, detecting outliers, and normalizing the data. The preprocessed data is then passed to a generative AI that analyzes the characteristics and challenges of each employee. This analysis generates optimal improvement and motivational measures for each employee.

[1214] The improvement proposals and motivation-boosting measures generated by the generative AI are sent to a management terminal via a server. Based on this information, managers implement specific countermeasures for employees. Managers also re-enter the effectiveness of the countermeasures and any new issues that arise into a data collection terminal and send it to the server. The server stores this data in a database and re-analyzes it using the generative AI. This allows for continuous optimization.

[1215] Prompt Sentence Examples

[1216] Provide optimal improvement and motivational strategies based on employee details, such as:

[1217] Behavioral trait: Poor time management

[1218] Tone: Calm and polite

[1219] Disability: ADHD

[1220] Work Challenge: Slow task completion rate

[1221] Specific examples

[1222] The user inputs detailed information about Employee A into the data collection terminal. For example, information such as Employee A's behavioral characteristics as "poor time management," his tone of voice as "calm and polite," his disability as "ADHD," and his work challenges as "slow task completion speed" is collected. This information is sent to the server and stored in a central database.

[1223] The server preprocesses the data and passes the preprocessed data to the generation AI. The generation AI analyzes this data and generates specific improvement proposals, such as "conduct time management training" and "set short-term goals and provide feedback." The generated improvement proposals are sent to a management terminal, and the manager uses them to implement specific measures for employee A.

[1224] In this way, this system provides specific improvement measures tailored to the characteristics and needs of employees, aiming to increase productivity and satisfaction. The use of generative AI enables quick and individual responses, making it easier to implement approaches tailored to characteristics.

[1225] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1226] Step 1: Data collection

[1227] The user operates the terminal to input detailed information about the employee. Specifically, data on the employee's behavioral characteristics, tone of voice, obstacles, and work issues is collected using forms and checklists. The input information includes specific data such as "Employee A's ID, behavioral characteristics: poor time management, tone of voice: calm and polite, obstacles: ADHD, work issues: slow task completion speed." This input data is collected by the terminal.

[1228] Step 2: Send data

[1229] The device encrypts the collected information and sends it to the server. During the transmission process, the device sends data to the server in real time via the Internet, and the server receives the data. This transmitted data is in preparation for being stored in a database in the next step.

[1230] Step 3: Save Data

[1231] The server stores the received data in a central database. Specifically, a database management system (e.g., MySQL) is used to store the data while maintaining its integrity and consistency. This stored data serves as the basis for analysis by the generative AI. Once the input data has been stored, it is passed on to the next preprocessing step.

[1232] Step 4: Data Preprocessing

[1233] The server preprocesses the data stored in the central database. Preprocessing involves filling in missing values, detecting outliers, and normalizing the data. For example, if missing values ​​exist, they are filled in with the mean or median, and if outliers are detected, appropriate corrections are made. Once preprocessing is complete, the data is ready to be passed to the generative AI.

[1234] Step 5: Characteristics analysis and problem analysis

[1235] The server passes the preprocessed data to the generation AI, which analyzes the characteristics and issues. The generation AI (e.g., GPT-4) uses a deep learning algorithm to analyze the employee's characteristics and issues. Based on the input data, it identifies and analyzes Employee A's characteristic of "poor time management" and his issue of "slow task completion speed." The results of this analysis are used to generate improvement measures in the next step.

[1236] Step 6: Generate improvement ideas and motivational strategies

[1237] Based on the results of the characteristic analysis and issue analysis, the generative AI generates improvement proposals and motivational measures tailored to each employee. For example, for employee A, it generates specific improvement proposals such as "implementing training on time management" and "setting short-term goals and providing feedback." The generated improvement proposals are compiled in report format.

[1238] Step 7: Output and action taken

[1239] The server sends a report of the generated improvement proposals and motivational measures to the management terminal. The user (administrator) receives the report and implements specific countermeasures. For example, specific countermeasures such as "setting the day's goals in a morning meeting" and "providing feedback after completing tasks" are implemented based on the report.

[1240] Step 8: Feedback and continuous improvement

[1241] The user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues they have encountered into their device and sends it back to the server. This new feedback data is stored in a central database, and the server re-analyzes it using the AI ​​generation system, achieving continuous optimization. By continuously collecting and analyzing feedback data, the cycle of providing optimal countermeasures for each employee is maintained.

[1242] (Application example 1)

[1243] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1244] In recent years, there has been a demand for improved operational efficiency and accuracy for factory robots. However, there is still a lack of effective systems that can grasp the operational status of robots on-site in real time and provide optimal improvement proposals and maintenance measures. In particular, robot operation errors and reduced operational efficiency have a negative impact on productivity, which is a problem. Conventional systems rely on manual monitoring and judgment by operators and managers, and often make it difficult to respond quickly. For this reason, there is a need for the development of a new system that can monitor the operational status of factory robots in real time and use generative AI to provide optimal improvement proposals.

[1245] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1246] In this invention, the server includes means for using a generating AI to analyze employee behavioral characteristics, tone of voice, details of obstacles, and work issues, means for generating improvement plans and motivation improvement measures based on the resulting characteristic data and issue data, means for transmitting the generated improvement plans and motivation improvement measures to a manager's terminal, and means for monitoring the robot's operation status in real time with smart glasses and using that data to provide optimal improvement plans and maintenance measures. This makes it possible to reduce operation errors and improve operation efficiency by monitoring the operation status of factory robots in real time and having the generating AI provide optimal improvement plans and maintenance measures.

[1247] "Generative AI" is an artificial intelligence technology that analyzes data and automatically generates improvement plans and suggestions based on human behavior and characteristics.

[1248] "Behavioral characteristics" are patterns of performance and behavior of employees or robots in work situations.

[1249] "Tone" refers to the style of speaking and expression in audio data.

[1250] "Disability" refers to physical or mental handicaps or limitations that arise in the course of work.

[1251] "Job challenges" are the job-related problems and challenges that employees face.

[1252] "Characteristic data" is detailed information about the behavior and status of the employee or robot being analyzed.

[1253] "Challenge data" is information about a specific problem an employee or robot is facing.

[1254] "Improvement proposals" are specific action plans proposed to improve the performance of employees or robots.

[1255] "Motivation improvement measures" are specific proposals and measures to increase employee motivation and efficiency.

[1256] The "administrator's terminal" refers to a computer or smart device used by the administrator for operation.

[1257] "Robot operation status" refers to information about the progress of the work being performed by the factory robot and the accuracy of its movements.

[1258] "Smart glasses" are wearable devices that display real-time information and record on-site conditions.

[1259] "Maintenance measures" are specific management procedures and repair proposals to maintain the normal operation of robots and equipment.

[1260] This invention relates to a system that uses generative AI to analyze employee behavioral characteristics, speech patterns, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system is particularly useful for improving the operational efficiency and accuracy of factory robots. Specific embodiments of the system are described below.

[1261] Hardware and Software Configuration

[1262] 1. Hardware:

[1263] Smart glasses (e.g., Google Glass): Used to monitor the operation status of factory robots in real time.

[1264] Administrator's device: A device such as a PC or smartphone used to receive generated improvement proposals and motivational measures.

[1265] 2. Software:

[1266] Data collection application: Runs on the smart glasses and collects and transmits robot operation data.

[1267] Generative AI model: Runs on the server and analyzes and processes collected data.

[1268] System execution procedures and operations

[1269] 1. Data Collection:

[1270] The smart glasses monitor the operating status of factory robots (operating efficiency, error frequency, accuracy, etc.) in real time and periodically send this data to a server.

[1271] 2. Data transmission and storage:

[1272] The server stores the received data in a central database, which is then used for analysis by the generative AI.

[1273] 3. Characteristics and Issues Analysis:

[1274] The server preprocesses the stored data before passing it to the generation AI, which performs missing value imputation and outlier detection to maintain data integrity.

[1275] Next, the server launches the generative AI, which uses the preprocessed data to perform characteristic analysis and problem analysis related to the operational efficiency and accuracy of the factory robot.

[1276] 4. Generate improvement proposals:

[1277] The generative AI generates optimal improvement and maintenance plans based on the robot's characteristic data and problem data.

[1278] 5. Output and action taken:

[1279] The server compiles the generated improvement proposals and maintenance measures into a report format and sends it to the administrator's terminal.

[1280] The user (administrator) receives this report and takes specific countermeasures on-site based on the report.

[1281] Specific examples

[1282] For example, if a factory robot has an operating efficiency of 85%, an error frequency of 2, and an accuracy of 90%, the data collected by the smart glasses will be converted into the following prompt sentence:

[1283] "Analyze the operational activity data of a factory robot and generate optimal improvement and maintenance plans to improve efficiency. The following data was collected: operational efficiency: 85%, error frequency: 2 times, accuracy: 90%."

[1284] If you feed this prompt to a generative AI model, you'll get the following response:

[1285] To improve the efficiency of your robot's operation, we recommend the following steps:

[1286] 1. Standardizing operating procedures and providing training

[1287] 2. Shorter maintenance intervals

[1288] 3. Software updates to improve operation accuracy

[1289] By generating specific improvement plans in this way, it is possible to effectively improve the operating conditions of factory robots and increase productivity.

[1290] This system can be applied not only to factory robots, but also to managing other employees and improving their performance. It also includes a function that continuously updates data specific to each employee and regenerates new improvement proposals and motivational measures based on previous feedback data. This allows for continuous optimal work styles and motivation management.

[1291] Finally, by utilizing generative AI, this invention enables rapid implementation of approaches tailored to the characteristics of employees and robots, making it easier to respond to individual needs.

[1292] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1293] Step 1:

[1294] Data collection

[1295] Input: The robot's operation status (operation efficiency, error frequency, accuracy, etc.) is obtained in real time from the smart glasses.

[1296] How it works: The smart glasses use sensors to collect data on the robot's operations and record it digitally.

[1297] Output: The collected operation data is sent from the terminal (smart glasses) to the server.

[1298] Step 2:

[1299] Data transmission and storage

[1300] Input: Robot operation data sent from the terminal.

[1301] Specific operation: The server receives the received data in real time and stores it in a central database.

[1302] Output: The saved operational data is used for the next analysis step.

[1303] Step 3:

[1304] Characteristics analysis and problem analysis

[1305] Input: Robot operation data stored in a central database.

[1306] Specific operation: The server performs preprocessing, imputes missing values ​​in the data, detects outliers, and maintains data integrity. The preprocessed data is then passed to the generation AI.

[1307] Output: Preprocessed data passed to the generative AI.

[1308] Step 4:

[1309] Generative AI startup and analysis

[1310] Input: Preprocessed operational data.

[1311] Specific operation: The generative AI analyzes the robot's characteristics and issues based on the input data. For example, it analyzes based on data such as 85% operational efficiency, 2 error frequencies, and 90% accuracy.

[1312] Output: Analysis results based on characteristic data and problem data regarding the robot's operating situation.

[1313] Step 5:

[1314] Generate improvement proposals

[1315] Input: Analysis results (characteristic data and problem data).

[1316] Specific actions: The generative AI generates optimal improvement and maintenance plans from the analysis results, such as standardizing operating procedures, shortening maintenance intervals, and proposing software updates.

[1317] Output: Generated improvement and maintenance recommendations.

[1318] Step 6:

[1319] Output and action taken

[1320] Input: Generated improvement and maintenance measures.

[1321] Specific operation: The server compiles the generated improvement proposals and maintenance measures into a report format and sends it to the administrator's terminal.

[1322] Output: Report received on administrator's terminal.

[1323] Step 7:

[1324] Feedback and Continuous Improvement

[1325] Input: Feedback data on the effectiveness of measures taken by administrators and new issues that have arisen.

[1326] Specific operation: The user (administrator) inputs feedback data into the terminal and sends it to the server, which stores it in a database and reanalyzes it as feedback data using the generation AI.

[1327] Output: Continuous improvement recommendations based on new feedback data.

[1328] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1329] This invention relates to a system that uses generative AI to analyze employees' behavioral characteristics, tone of voice, obstacles, and work challenges, and also to a system that uses an emotion engine to analyze employees' emotional data and provide optimal improvement proposals and motivational measures. This system is designed to provide a work environment and measures that are suited to each individual employee, thereby improving their productivity and motivation.

[1330] System Overview

[1331] The system includes the following major components:

[1332] 1. Data Collection Device (hereinafter referred to as "Device")

[1333] 2. Central Database (hereinafter referred to as "Server")

[1334] 3. Generation AI

[1335] 4. Emotion Engine

[1336] 5. Management Interface (hereinafter "Terminal")

[1337] Operational Overview

[1338] The system begins by entering an employee's behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data into a terminal and sending it to a server. The server stores this data in a central database and passes it to a generative AI and emotion engine for analysis. The generative AI generates improvement and motivational measures based on the employee's individual characteristics and emotions and sends them back to the management terminal. Based on these results, the manager can implement the optimal response for the employee.

[1339] Program processing

[1340] Data collection

[1341] Users input employee information (behavioral characteristics, tone of voice, obstacles, work challenges) and emotional data into the terminal. Each piece of information is collected in detail using specific forms and checklists, as well as emotion recognition technology.

[1342] Example input items:

[1343] Employee ID

[1344] Behavioral characteristics: Poor time management

[1345] Tone: Calm and polite

[1346] Disability: Attention Deficit Disorder (ADHD)

[1347] Work Challenge: Slow task completion speed

[1348] Emotional data: Stress levels based on facial expressions and voice analysis

[1349] Data transmission and storage

[1350] The device sends the input data to a server, which stores it in a central database for later analysis by the generative AI and emotion engine.

[1351] Characteristics analysis and problem analysis

[1352] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[1353] The server then passes the preprocessed data to the generation AI and emotion engine for analysis. The generation AI analyzes the employee's behavioral characteristics and issues, while the emotion engine analyzes the employee's emotional data.

[1354] Generate improvement proposals

[1355] Generative AI and an emotion engine generate specific improvement proposals and motivational measures based on each employee's individual characteristics, challenges, and emotions.

[1356] This example generates:

[1357] Employee A's improvement suggestion:

[1358] Conducting time management training

[1359] Setting short-term goals and providing feedback

[1360] Motivate with positive praise

[1361] Introducing relaxation techniques based on emotional data

[1362] Employee B's improvement suggestion:

[1363] Organize your work environment and provide a space where you can focus

[1364] Incorporating a routine with short breaks

[1365] Introduction of an error checklist and confirmation before work begins

[1366] Introducing stress management methods based on emotional data

[1367] Output and action taken

[1368] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to the terminal. The user (administrator) receives this and takes specific measures for employees based on the report.

[1369] This example does the following:

[1370] Set goals for the day at your morning meeting

[1371] Providing feedback after completing a task

[1372] If they complete the task more quickly, they are given an extra break.

[1373] Implement relaxation and stress management techniques based on emotional data

[1374] Feedback and Continuous Improvement

[1375] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[1376] This system is a powerful tool for providing optimized support to each employee, improving their productivity and satisfaction. Utilizing generative AI and an emotion engine, it enables personalized responses and quickly implements approaches tailored to the employee's characteristics and emotions.

[1377] The processing flow will be explained below.

[1378] Step 1:

[1379] Users input employee behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data into a terminal using specific forms and checklists, as well as emotion recognition technology (e.g., facial expression analysis cameras and voice recognition microphones).

[1380] Step 2:

[1381] The device sends the entered data to the server, where it is encrypted and transmitted using a secure protocol.

[1382] Step 3:

[1383] The server stores the received data in a central database, which stores each employee's behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data.

[1384] Step 4:

[1385] The server preprocesses the stored data. This preprocessing includes filling in missing data, detecting outliers, and standardizing data formats. Data preprocessing is essential to improve the accuracy of analysis.

[1386] Step 5:

[1387] The server passes the preprocessed data to the generation AI and emotion engine. The generation AI analyzes the employee's behavioral characteristics and issues, and the emotion engine analyzes the employee's emotional data.

[1388] Step 6:

[1389] The generative AI analyzes the characteristic data and issue data for each employee, and the emotion engine analyzes the emotional data. Based on the results of this analysis, it generates optimal improvement plans and motivation-boosting measures.

[1390] Step 7:

[1391] The server formats the generated improvement and motivational measures and creates a report for the management interface, which includes the analysis results and specific countermeasures.

[1392] Step 8:

[1393] The server sends the report to the terminal, which is provided in a format that is easy for the administrator to understand.

[1394] Step 9:

[1395] The user (manager) receives the report and takes specific action based on it, including suggestions for improvement and motivation for employees provided by the generative AI and emotion engine.

[1396] Step 10:

[1397] The user (administrator) evaluates the effectiveness of the countermeasures and any new issues that arise, and enters the evaluation results and feedback data into the terminal.

[1398] Step 11:

[1399] The terminal sends feedback data to the server, which is stored in a central database in the same way as the initial data.

[1400] Step 12:

[1401] The server reanalyzes the feedback data using the generative AI and emotion engine, which is used as important input data for the next improvement plan.

[1402] Step 13:

[1403] The server then formats the new improvement proposals and motivation-boosting measures into a report and sends it to the device. This process is repeated to continuously optimize work styles and motivation management.

[1404] In this way, the system can continuously analyze employees' characteristics and emotions and provide optimal improvement and motivational strategies.

[1405] Example 2

[1406] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1407] In today's workplace, improving employee productivity and motivation is a key challenge. However, accurately understanding the behavioral characteristics and emotional state of each employee and responding to them individually can be difficult. It is also not easy to quickly provide appropriate improvement proposals and motivation-boosting measures based on employees' characteristics and challenges. A system that effectively utilizes employee emotional data to achieve specific behavioral improvements and motivational improvements is needed.

[1408] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1409] In this invention, the server includes: means for analyzing employee behavioral characteristics, tone of voice, obstacles, and work issues using a generation AI; means for generating improvement plans and motivation-boosting measures based on the resulting characteristic data and issue data; means including an emotion analysis engine for analyzing the collected emotion data and proposing appropriate measures based on the employee's emotions; and means for sending the generated improvement plans and motivation-boosting measures to a manager's terminal in report format. This enables the rapid provision of optimized support for each employee, improving productivity and motivation.

[1410] "Generative AI" is a system that uses artificial intelligence techniques to analyze data and generate outputs or results suitable for specific purposes.

[1411] "Behavioral characteristics" are characteristics related to employee behavior patterns, habits, and actions.

[1412] "Tone" refers to the characteristics of the language and communication style used by employees.

[1413] "Disability details" is information about an employee's specific disability and its impact.

[1414] "Work challenges" are work-related problems employees face or areas that need improvement.

[1415] "Characteristic data" refers to information regarding the behavioral characteristics, tone of voice, and disability details of the employee being analyzed.

[1416] "Issue data" refers to information regarding business issues and areas requiring improvement.

[1417] An "improvement proposal" is a specific improvement measure proposed based on the employee's behavioral characteristics and challenges.

[1418] "Motivation improvement measures" are specific measures to increase employee motivation and enthusiasm.

[1419] "Emotional data" is data that indicates an employee's emotional state and is typically collected through facial and voice analysis.

[1420] An "emotion analysis engine" is a system that analyzes emotional data, evaluates employees' emotional state, and generates countermeasures based on that.

[1421] "Administrator's terminal" refers to a computer or device used by the system administrator to receive generated reports and improvement proposals.

[1422] This invention is a system that utilizes generative AI and an emotion analysis engine to analyze employees' behavioral characteristics, tone of voice, obstacles, work issues, and emotional data, and provides optimal improvement plans and motivational measures for each employee. This system consists of a data collection terminal, a server, generative AI, an emotion analysis engine, and a management terminal.

[1423] Hardware and Software Use

[1424] Data collection device: A computer or mobile device used to collect employee behavioral characteristics, tone, obstacles, work challenges, and emotional data. This device is equipped with sensors such as a camera and microphone and is also used to collect emotional data.

[1425] Server: A computer that stores collected data in a central database and passes it to the generation AI and emotion analysis engine. It also transmits generated improvement proposals and motivational measures to the management terminal.

[1426] Generative AI: An artificial intelligence model used to analyze employee behavioral characteristics and challenges. This AI generates optimal improvement plans and motivational measures based on data for each employee.

[1427] Sentiment Analysis Engine: Software that analyzes emotional data and assesses the emotional state of employees, allowing it to suggest countermeasures based on their emotions.

[1428] Management terminal: A computer or device where a manager receives generated reports and takes action against employees.

[1429] Explanation of program processing

[1430] Users enter employee behavioral characteristics, tone, obstacles, work challenges, and emotional data into data collection devices. This data is collected through forms, checklists, cameras, and microphones.

[1431] Specifically, the following data is entered:

[1432] Employee ID

[1433] Behavioral characteristics: Poor time management

[1434] Tone: Calm and polite

[1435] Disability: Attention Deficit Disorder (ADHD)

[1436] Work Challenge: Slow task completion speed

[1437] Emotional data collected using a camera and microphone: stress levels through facial and voice analysis

[1438] The terminal encrypts the input data and transmits it in real time to the server, which stores the received data in a central database and performs pre-processing on the data, including missing value imputation, outlier detection, and data format standardization.

[1439] The server then passes the preprocessed data to the generation AI and emotion analysis engine for analysis. The generation AI analyzes employees' behavioral characteristics and issues, and generates optimal improvement proposals and motivation-boosting measures. At the same time, the emotion analysis engine analyzes the emotional data and proposes countermeasures based on the employee's emotional state.

[1440] The generated improvement proposals and motivation-boosting measures are compiled into a report and sent to a management terminal. The user (manager) then implements specific measures for the employees based on this report.

[1441] for example:

[1442] Set goals for the day at your morning meeting

[1443] Providing feedback after completing a task

[1444] Offer additional breaks if the task can be completed more quickly

[1445] Implement relaxation and stress management techniques based on emotional data

[1446] Finally, the user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues that have arisen into the terminal and sends it back to the server, allowing the system to continuously update the data and continue to provide optimal improvement proposals and motivation-boosting measures.

[1447] Example prompts for generative AI models

[1448] Below are some example prompts to be input to the generative AI model:

[1449] Prompt statement:

[1450] Employee ID: 12345

[1451] Behavioral trait: Poor time management

[1452] Tone: Calm and polite

[1453] Disability: ADHD

[1454] Work Challenge: Slow task completion rate

[1455] Emotion data: High stress level based on facial expression analysis

[1456] Generate optimal improvement and motivational strategies.

[1457] This makes it possible to provide each employee with quick, optimized support, improving productivity and motivation.

[1458] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1459] Step 1:

[1460] Data collection

[1461] Users input employee behavioral characteristics, tone of voice, obstacles, work tasks, and emotional data into a terminal. This input data is collected through forms, checklists, cameras, and microphones.

[1462] Input: Employee ID, behavioral characteristics, tone of voice, obstacle details, work issues, emotional data

[1463] Specific behavior:

[1464] The user enters an employee ID into a form.

[1465] Select a behavioral trait from the selection list.

[1466] Enter the tone.

[1467] Check the fault details.

[1468] Enter work assignments.

[1469] Emotional data (facial expression analysis, voice analysis) is collected using a camera and microphone.

[1470] Step 2:

[1471] Data transmission

[1472] The device encrypts the entered data and sends it to the server. The data is sent in real time to prevent data leakage during transmission.

[1473] Input: Employee data entered into the terminal

[1474] Output: The encrypted data is sent to the server

[1475] Specific behavior:

[1476] The device encrypts all input data at once.

[1477] The encrypted data is sent to the server.

[1478] Step 3:

[1479] Data storage

[1480] The server deserializes the received data and stores it in a central database, where the storage is performed transactionally to ensure consistency and integrity.

[1481] Input: Encrypted data sent to the server

[1482] Output: Employee data deserialized and saved to the database

[1483] Specific behavior:

[1484] The server decrypts the received data.

[1485] The data is deserialized and stored in a central database.

[1486] Step 4:

[1487] Data Preprocessing

[1488] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[1489] Input: Stored raw data

[1490] Output: Preprocessed data

[1491] Specific behavior:

[1492] The server detects and completes missing values ​​in the stored data.

[1493] Correct any abnormal values.

[1494] Transform data into a unified format.

[1495] Step 5:

[1496] Characteristics analysis and problem analysis

[1497] The server passes the preprocessed data to the generation AI and sentiment analysis engine for analysis. The generation AI analyzes employee behavioral characteristics and issues, while the sentiment analysis engine analyzes the emotional data.

[1498] Input: Preprocessed data

[1499] Output: Analysis results (behavioral characteristics, tasks, emotional state)

[1500] Specific behavior:

[1501] The server converts the data into an input format for the generative AI model.

[1502] The generative AI analyzes behavioral characteristics and challenges and outputs the results.

[1503] The emotion analysis engine analyzes the emotion data and outputs the emotional state.

[1504] Step 6:

[1505] Generate improvement proposals

[1506] Generative AI and an emotion analysis engine generate specific improvement proposals and motivational measures based on each employee's characteristics, challenges, and emotions.

[1507] Input: Analysis results (behavioral characteristics, tasks, emotional state)

[1508] Output: Improvement proposals and motivational measures

[1509] Specific behavior:

[1510] The server receives the analysis results from the generation AI and the sentiment analysis engine.

[1511] Generate optimal improvement plans and motivation measures for each employee.

[1512] Step 7:

[1513] Output of improvement proposals

[1514] The server compiles the generated improvement proposals and motivation-boosting measures into a report format and sends it to the management terminal.

[1515] Input: Generated improvement ideas and motivational measures

[1516] Output: Report format data. Send to management terminal.

[1517] Specific behavior:

[1518] The server formats the data using a report template.

[1519] The formatted report is sent to the management terminal.

[1520] Step 8:

[1521] Implementing countermeasures

[1522] The user (manager) takes specific measures for the employee based on the report.

[1523] Input: Report sent to management terminal

[1524] Output: Implementing action against employee

[1525] Specific behavior:

[1526] The user (administrator) sets the day's goals at a morning meeting.

[1527] Provide feedback after completing a task.

[1528] If they can complete the task more quickly, they are given an extra break.

[1529] Relaxation and stress management techniques are implemented based on emotional data.

[1530] Step 9:

[1531] Feedback and Continuous Improvement

[1532] The user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues they have encountered into the terminal and sends it back to the server. This updates the database, and the new feedback data is reanalyzed by the generation AI and emotion analysis engine.

[1533] Input: Feedback data, effectiveness of countermeasures, new issues

[1534] Output: Updated data, continuous improvement ideas and motivational measures

[1535] Specific behavior:

[1536] The user (administrator) inputs the feedback data into the terminal.

[1537] The device sends this to the server, where it is stored in a database.

[1538] The server reanalyzes the feedback data and generates new improvement suggestions.

[1539] (Application example 2)

[1540] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1541] When workers and robots work together in factories, optimal work instructions and support that take into account the behavioral characteristics and emotional data of workers are not being provided, which is a problem that leads to reduced productivity and increased stress among workers. Furthermore, there is a lack of individualized measures for each worker, making it difficult to respond quickly and accurately, which makes it difficult to improve worker motivation and provide an efficient work environment.

[1542] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing an employee's behavioral characteristics, tone of voice, obstacle details, and work issues using a generation AI, means for generating improvement plans and motivation improvement measures based on the resulting characteristic data and issue data, means for sending the generated improvement plans and motivation improvement measures to a manager's terminal, means for analyzing employee emotion data and optimizing robot work instructions based on the analysis results, and means for detecting an employee's stress level and suggesting appropriate rest. This allows work instructions and support optimized for each employee to be automatically provided, improving productivity and reducing employee stress.

[1543] "Generative AI" is an artificial intelligence that uses artificial intelligence technology to analyze employees' behavioral characteristics and work challenges, and automatically generates appropriate improvement proposals and motivation-boosting measures.

[1544] "Behavioral characteristics" refer to an employee's working style and behavioral patterns, such as strengths and weaknesses in time management and the speed at which tasks are completed.

[1545] "Tone of speech" refers to the characteristics of an employee's language and speaking style, such as a calm and polite manner of speaking or a strong tone of voice.

[1546] "Disability" means information about an employee's disability, such as attention deficit disorder or physical limitations.

[1547] "Work challenges" refer to problems or difficulties an employee faces in performing their job, such as slow task completion.

[1548] "Characteristic data" refers to data obtained as a result of analysis, such as employee behavioral characteristics and the nature of obstacles.

[1549] "Issue data" refers to data related to the work issues of employees obtained as a result of the analysis.

[1550] "Emotional data" is data that indicates an employee's emotional state and is collected through voice analysis and facial expression recognition.

[1551] "Improvement proposals" are specific improvement measures created based on an employee's behavioral characteristics and work challenges, and include, for example, training on time management.

[1552] "Motivation measures" are specific means to increase employees' motivation to work, and include setting short-term goals and motivating employees through praise.

[1553] "Administrator's device" refers to a computer or smart device used by a supervisor or manager, and is a device used to view and manage employee characteristic data and improvement proposals.

[1554] "Robot work instructions" refers to automatically giving instructions to robots in factories to optimize their collaborative work with employees.

[1555] "Break suggestion" means sensing an employee's stress level and suggesting a break at the appropriate time if necessary.

[1556] This invention realizes a system that analyzes employee behavioral characteristics, speech patterns, obstacles, work challenges, and emotional data to provide optimal improvement plans and motivational measures in order to optimize collaboration between employees and robots in a factory. A specific embodiment of this system will be described below.

[1557] System Overview

[1558] The system includes the following major components:

[1559] 1. Data Collection Device (hereinafter referred to as "Device")

[1560] 2. Central Database (hereinafter referred to as "Server")

[1561] 3. Generation AI

[1562] 4. Emotion Engine

[1563] 5. Robot Operation Interface (hereinafter "Robot Interface")

[1564] 6. Management terminal (hereinafter referred to as "Management terminal")

[1565] Operational Overview

[1566] The user inputs the employee's behavioral characteristics, tone of voice, details of the obstacles, work issues, and emotional data into the terminal and sends it to the server. The server stores this data in a central database and passes it to the generation AI and emotion engine for analysis. The generation AI generates improvement proposals and motivational measures based on the employee's individual characteristics and emotions and sends them back to the management terminal. It also provides the robot with optimal work instructions through the robot interface. Based on these results, the manager can implement the optimal response for the employee.

[1567] Program processing

[1568] Data collection

[1569] Users input employee information (behavioral characteristics, tone of voice, obstacles, work challenges) and emotional data into the terminal. Each piece of information is collected in detail using specific forms and checklists, as well as emotion recognition technology.

[1570] Example input items:

[1571] Employee ID

[1572] Behavioral characteristics: Poor time management

[1573] Tone: Calm and polite

[1574] Disability: Attention Deficit Disorder (ADHD)

[1575] Work Challenge: Slow task completion speed

[1576] Emotional data: Stress levels based on facial expressions and voice analysis

[1577] Data transmission and storage

[1578] The device sends the input data to a server, which stores it in a central database for later analysis by the generative AI and emotion engine.

[1579] Characteristics analysis and problem analysis

[1580] The server preprocesses the stored data. This preprocessing includes filling in missing values, detecting outliers, and standardizing data formats. The server then passes the preprocessed data to the generative AI and emotion engine for analysis. The generative AI analyzes employee behavioral characteristics and issues, while the emotion engine analyzes employee emotional data.

[1581] Generate improvement proposals and motivational measures

[1582] Generative AI and an emotion engine generate specific improvement proposals and motivational measures based on each employee's individual characteristics, challenges, and emotions.

[1583] This example generates:

[1584] Employee A's improvement suggestion:

[1585] Conducting time management training

[1586] Setting short-term goals and providing feedback

[1587] Motivate with positive praise

[1588] Introducing relaxation techniques based on emotional data

[1589] Employee B's improvement suggestion:

[1590] Organize your work environment and provide a space where you can focus

[1591] Incorporating a routine with short breaks

[1592] Introduction of an error checklist and confirmation before work begins

[1593] Introducing stress management methods based on emotional data

[1594] Output and action taken

[1595] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to a management terminal. The user (manager) receives this report and implements specific measures for employees based on the report. The server also provides the robot with optimal work instructions based on the employee's emotional data through the robot interface.

[1596] This example does the following:

[1597] Set goals for the day at your morning meeting

[1598] Providing feedback after completing a task

[1599] If they complete the task more quickly, they are given an extra break.

[1600] Implement relaxation and stress management techniques based on emotional data

[1601] Feedback and Continuous Improvement

[1602] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[1603] Example prompts to input to a generative AI model:

[1604] Prompt: Based on Employee A's behavioral and emotional data, please suggest the best improvement and motivational measures for him.

[1605] Behavioral data: Poor time management, slow task completion

[1606] Emotional data: high stress level, tired facial expression

[1607] As described above, this invention is a powerful tool for providing optimized support to each employee and improving their productivity and satisfaction. By utilizing generative AI and an emotion engine, personalized responses are possible, and approaches tailored to the employee's characteristics and emotions can be quickly implemented.

[1608] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1609] Step 1:

[1610] The user inputs employee information (behavioral characteristics, tone of voice, obstacles, and work challenges) and emotional data into the terminal. Specific forms and checklists are used to collect detailed data, which is then analyzed using emotion recognition technology. For example, the user inputs the employee's ID, behavioral characteristics (poor time management), tone of voice (calm and polite), obstacles (attention deficit disorder), work challenges (slow task completion speed), and emotional data (stress level determined by facial and voice analysis).

[1611] Input: Employee behavioral characteristics, tone of voice, obstacles, work issues, emotional data

[1612] Output: A set of input data

[1613] Step 2:

[1614] The device sends the input data to the server, which then stores it in a central database for later analysis by the generative AI and emotion engine.

[1615] Input: Employee data sent from the terminal

[1616] Output: Data stored in a central database

[1617] Step 3:

[1618] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats. For example, it imputes missing data and detects and corrects outliers.

[1619] Input: Raw data in a central database

[1620] Output: Preprocessed dataset

[1621] Step 4:

[1622] The server passes the preprocessed data to the generation AI and emotion engine for analysis. The generation AI analyzes employees' behavioral characteristics and issues, while the emotion engine analyzes their emotional data. Specifically, for example, GPT-4 is used to analyze the characteristic data and issue data, and the Emotion API is used to analyze the emotional data.

[1623] Input: Preprocessed data

[1624] Output: Analysis results (characteristic data, issue data, emotion data)

[1625] Step 5:

[1626] The generative AI and emotion engine generate specific improvement and motivational measures based on each employee's characteristics, challenges, and emotions. These improvement measures are optimized for each employee. For example, for employee A, time management training and short-term goal setting are suggested.

[1627] Input: Analysis results

[1628] Output: Improvement proposals and motivational measures

[1629] Step 6:

[1630] The server compiles the generated improvement proposals and motivation-boosting measures into a report format and sends it to a management terminal. Furthermore, the robot interface provides the robot with optimal work instructions based on the employee's emotional data.

[1631] Input: Improvement ideas and motivational measures

[1632] Output: Report sent to the management terminal, work instructions to the robot

[1633] Step 7:

[1634] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[1635] Input: Effects of implemented countermeasures, new issues

[1636] Output: Save feedback data to database, reanalysis results

[1637] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1638] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1639] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1640] [Fourth embodiment]

[1641] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1642] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1643] 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 a "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).

[1644] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1645] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1646] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1647] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1648] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1649] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1650] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1651] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1652] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1653] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1654] This invention relates to a system that uses generative AI to analyze employees' behavioral characteristics, tone of voice, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system is designed to provide a work environment and measures suited to each employee, thereby improving their productivity and motivation.

[1655] System Overview

[1656] The system includes the following major components:

[1657] 1. Data Collection Device (hereinafter referred to as "Device")

[1658] 2. Central Database (hereinafter referred to as "Server")

[1659] 3. Generation AI

[1660] 4. Management Interface (hereinafter "Terminal")

[1661] Operational Overview

[1662] The system begins by entering data on an employee's behavioral characteristics, tone of voice, obstacles, and work challenges on a terminal and sending it to a server. The server stores this data in a central database and passes it to a generation AI for analysis. The generation AI generates improvement and motivational measures based on the individual employee's characteristics and sends them back to the management terminal. Based on these results, the manager can implement the optimal response for the employee.

[1663] Program processing

[1664] Data collection

[1665] The user inputs employee information (behavioral characteristics, tone of voice, obstacles, work issues) into the terminal. Each piece of information is collected in detail through specific forms and checklists.

[1666] Example input items:

[1667] Employee ID

[1668] Behavioral characteristics: Poor time management

[1669] Tone: Calm and polite

[1670] Disability: Attention Deficit Disorder (ADHD)

[1671] Work Challenge: Slow task completion speed

[1672] Data transmission and storage

[1673] The device sends the collected information to a server, which stores the received data in a central database for later analysis by the generative AI.

[1674] Characteristics analysis and problem analysis

[1675] The server preprocesses the stored data before passing it to the generation AI. This preprocessing ensures data integrity by filling in missing values ​​and detecting outliers.

[1676] The server then launches the generative AI, which analyzes employee characteristics and issues based on the preprocessed data. The generative AI then generates optimal improvement plans and motivational measures for each employee.

[1677] Generate improvement proposals

[1678] Generative AI generates specific improvement proposals and motivation-boosting measures tailored to each employee's characteristics and challenges.

[1679] This example generates:

[1680] Employee A's improvement suggestion:

[1681] Conducting time management training

[1682] Setting short-term goals and providing feedback

[1683] Motivate with positive praise

[1684] Employee B's improvement suggestion:

[1685] Organize your work environment and provide a space where you can focus

[1686] Incorporating a routine with short breaks

[1687] Introduction of an error checklist and confirmation before work begins

[1688] Output and action taken

[1689] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to the terminal. The user (administrator) receives this and takes specific measures for employees based on the report.

[1690] This example does the following:

[1691] Set goals for the day at your morning meeting

[1692] Providing feedback after completing a task

[1693] If they complete the task more quickly, they are given an extra break.

[1694] Feedback and Continuous Improvement

[1695] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends it back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generation AI. This allows for continuous optimal work styles and motivation management.

[1696] This system is a powerful tool for providing optimized support to each employee, improving their productivity and satisfaction. By utilizing generative AI, it is possible to respond to each individual employee and quickly implement approaches tailored to the characteristics of each employee.

[1697] The processing flow will be explained below.

[1698] Step 1:

[1699] Users enter data about employee behavioral traits, tone, obstacles, and work challenges into a terminal, using specific forms and checklists.

[1700] Step 2:

[1701] The terminal transmits the input data to the server.

[1702] Step 3:

[1703] The server stores the received data in a central database.

[1704] Step 4:

[1705] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[1706] Step 5:

[1707] The server passes the preprocessed data to the generation AI, which then launches it and analyzes the employee's behavioral characteristics and issues.

[1708] Step 6:

[1709] The generative AI generates improvement proposals and motivation-boosting measures based on each employee's characteristic data and issue data.

[1710] Step 7:

[1711] The server formats the generated improvement and motivational measures and creates a report for the management interface.

[1712] Step 8:

[1713] The server sends the report to the terminal.

[1714] Step 9:

[1715] The user (manager) receives the report and takes specific action against the employee based on it.

[1716] Step 10:

[1717] The user (administrator) inputs the effectiveness of the countermeasures and any new issues that have arisen into the terminal.

[1718] Step 11:

[1719] The terminal transmits the feedback data to the server.

[1720] Step 12:

[1721] The server stores the feedback data in a database and reanalyzes it using the generative AI, which then generates new improvement proposals and motivation-boosting strategies.

[1722] Step 13:

[1723] By repeating the process from step 6 onwards, optimal working styles and motivation management can be continuously achieved.

[1724] Example 1

[1725] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1726] As the working environment becomes more diverse, it is becoming increasingly important to provide optimal improvement plans and motivational measures for each employee, taking into account their behavioral characteristics, speech patterns, disabilities, and work challenges. However, collecting, analyzing, and continuously updating detailed data for individual responses makes it difficult to propose and implement effective improvement measures. For this reason, there is a need to develop a system that can quickly generate specific countermeasures tailored to each employee's characteristics and challenges, and continuously improve them based on feedback.

[1727] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1728] In this invention, the server includes means for collecting employee behavioral characteristics, tone of voice, details of obstacles, and work issues, means for sending the collected data to the server and storing it in a central database, means for preprocessing the stored data and filling in missing values ​​and detecting outliers, means for analyzing characteristics and issues using a generation AI based on the preprocessed data, means for generating improvement plans and motivation improvement measures tailored to each employee, means for sending the generated improvement plans and motivation improvement measures to a management terminal, means for re-collecting the effects of measures implemented by the manager and newly arising issues, and means for re-analyzing based on feedback data and making continuous improvements. This allows for the rapid provision of specific improvement plans and motivation improvement measures tailored to each employee's characteristics, enabling continuously optimized work styles and motivation management.

[1729] "Employee" refers to an individual who works for an organization or company.

[1730] "Behavioral characteristics" are elements that indicate an employee's behavioral patterns, habits, and characteristics in their work.

[1731] "Tone" refers to the way an employee speaks and the expressions they use when speaking.

[1732] "Disability details" refers to information including the employee's disability or special needs.

[1733] "Work challenges" refer to specific problems or difficulties that employees face in their work.

[1734] "Collection means" refers to the methods and devices used to aggregate information about employees.

[1735] A "server" is a computer system for storing, managing, and analyzing data.

[1736] A "central database" is a database system for centrally storing and managing collected data.

[1737] "Preprocessing" refers to processes such as filling in missing values ​​and detecting outliers before data analysis.

[1738] "Generative AI" refers to a system that uses artificial intelligence to analyze data, analyze characteristics and issues, and generate improvement proposals.

[1739] "Characteristic analysis" refers to analyzing employee characteristics based on collected data.

[1740] "Problem analysis" refers to identifying the specific challenges employees face through data analysis.

[1741] "Improvement proposals" refer to specific means or methods proposed to improve employees' work and increase efficiency.

[1742] "Motivation improvement measures" refer to specific proposals to increase employee motivation and morale.

[1743] "Administrative terminal" refers to a terminal used by an administrator to check data and implement countermeasures through the system.

[1744] "Feedback data" refers to data on the effectiveness of implemented countermeasures and new issues that have arisen.

[1745] "Continuous improvement" refers to repeatedly conducting new analyses and proposals based on feedback, rather than conducting a single analysis and proposal.

[1746] This invention relates to a system that analyzes employees' behavioral characteristics, tone, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system utilizes generative AI to provide a work environment and measures suited to each employee, and is designed to improve their productivity and motivation.

[1747] Hardware and software used

[1748] Hardware: Data collection terminal, central server, management terminal

[1749] Software: Generative AI (e.g., GPT-4), Database Management Systems (e.g., MySQL)

[1750] System Operation Overview

[1751] The user operates the data collection terminal to input detailed information about the employee. This information includes behavioral characteristics, tone of voice, obstacles, and work challenges. The data collection terminal encrypts the collected data and sends it to the server. The server stores the received data in a central database.

[1752] After the data is saved, the server performs preprocessing, which includes filling in missing values, detecting outliers, and normalizing the data. The preprocessed data is then passed to a generative AI that analyzes the characteristics and challenges of each employee. This analysis generates optimal improvement and motivational measures for each employee.

[1753] The improvement proposals and motivation-boosting measures generated by the generative AI are sent to a management terminal via a server. Based on this information, managers implement specific countermeasures for employees. Managers also re-enter the effectiveness of the countermeasures and any new issues that arise into a data collection terminal and send it to the server. The server stores this data in a database and re-analyzes it using the generative AI. This allows for continuous optimization.

[1754] Prompt Sentence Examples

[1755] Provide optimal improvement and motivational strategies based on employee details, such as:

[1756] Behavioral trait: Poor time management

[1757] Tone: Calm and polite

[1758] Disability: ADHD

[1759] Work Challenge: Slow task completion rate

[1760] Specific examples

[1761] The user inputs detailed information about Employee A into the data collection terminal. For example, information such as Employee A's behavioral characteristics as "poor time management," his tone of voice as "calm and polite," his disability as "ADHD," and his work challenges as "slow task completion speed" is collected. This information is sent to the server and stored in a central database.

[1762] The server preprocesses the data and passes the preprocessed data to the generation AI. The generation AI analyzes this data and generates specific improvement proposals, such as "conduct time management training" and "set short-term goals and provide feedback." The generated improvement proposals are sent to a management terminal, and the manager uses them to implement specific measures for employee A.

[1763] In this way, this system provides specific improvement measures tailored to the characteristics and needs of employees, aiming to increase productivity and satisfaction. The use of generative AI enables quick and individual responses, making it easier to implement approaches tailored to characteristics.

[1764] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1765] Step 1: Data collection

[1766] The user operates the terminal to input detailed information about the employee. Specifically, data on the employee's behavioral characteristics, tone of voice, obstacles, and work issues is collected using forms and checklists. The input information includes specific data such as "Employee A's ID, behavioral characteristics: poor time management, tone of voice: calm and polite, obstacles: ADHD, work issues: slow task completion speed." This input data is collected by the terminal.

[1767] Step 2: Send data

[1768] The device encrypts the collected information and sends it to the server. During the transmission process, the device sends data to the server in real time via the Internet, and the server receives the data. This transmitted data is in preparation for being stored in a database in the next step.

[1769] Step 3: Save Data

[1770] The server stores the received data in a central database. Specifically, a database management system (e.g., MySQL) is used to store the data while maintaining its integrity and consistency. This stored data serves as the basis for analysis by the generative AI. Once the input data has been stored, it is passed on to the next preprocessing step.

[1771] Step 4: Data Preprocessing

[1772] The server preprocesses the data stored in the central database. Preprocessing involves filling in missing values, detecting outliers, and normalizing the data. For example, if missing values ​​exist, they are filled in with the mean or median, and if outliers are detected, appropriate corrections are made. Once preprocessing is complete, the data is ready to be passed to the generative AI.

[1773] Step 5: Characteristics analysis and problem analysis

[1774] The server passes the preprocessed data to the generation AI, which analyzes the characteristics and issues. The generation AI (e.g., GPT-4) uses a deep learning algorithm to analyze the employee's characteristics and issues. Based on the input data, it identifies and analyzes Employee A's characteristic of "poor time management" and his issue of "slow task completion speed." The results of this analysis are used to generate improvement measures in the next step.

[1775] Step 6: Generate improvement ideas and motivational strategies

[1776] Based on the results of the characteristic analysis and issue analysis, the generative AI generates improvement proposals and motivational measures tailored to each employee. For example, for employee A, it generates specific improvement proposals such as "implementing training on time management" and "setting short-term goals and providing feedback." The generated improvement proposals are compiled in report format.

[1777] Step 7: Output and action taken

[1778] The server sends a report of the generated improvement proposals and motivational measures to the management terminal. The user (administrator) receives the report and implements specific countermeasures. For example, specific countermeasures such as "setting the day's goals in a morning meeting" and "providing feedback after completing tasks" are implemented based on the report.

[1779] Step 8: Feedback and continuous improvement

[1780] The user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues they have encountered into their device and sends it back to the server. This new feedback data is stored in a central database, and the server re-analyzes it using the AI ​​generation system, achieving continuous optimization. By continuously collecting and analyzing feedback data, the cycle of providing optimal countermeasures for each employee is maintained.

[1781] (Application example 1)

[1782] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1783] In recent years, there has been a demand for improved operational efficiency and accuracy for factory robots. However, there is still a lack of effective systems that can grasp the operational status of robots on-site in real time and provide optimal improvement proposals and maintenance measures. In particular, robot operation errors and reduced operational efficiency have a negative impact on productivity, which is a problem. Conventional systems rely on manual monitoring and judgment by operators and managers, and often make it difficult to respond quickly. For this reason, there is a need for the development of a new system that can monitor the operational status of factory robots in real time and use generative AI to provide optimal improvement proposals.

[1784] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1785] In this invention, the server includes means for using a generating AI to analyze employee behavioral characteristics, tone of voice, details of obstacles, and work issues, means for generating improvement plans and motivation improvement measures based on the resulting characteristic data and issue data, means for transmitting the generated improvement plans and motivation improvement measures to a manager's terminal, and means for monitoring the robot's operation status in real time with smart glasses and using that data to provide optimal improvement plans and maintenance measures. This makes it possible to reduce operation errors and improve operation efficiency by monitoring the operation status of factory robots in real time and having the generating AI provide optimal improvement plans and maintenance measures.

[1786] "Generative AI" is an artificial intelligence technology that analyzes data and automatically generates improvement plans and suggestions based on human behavior and characteristics.

[1787] "Behavioral characteristics" are patterns of performance and behavior of employees or robots in work situations.

[1788] "Tone" refers to the style of speaking and expression in audio data.

[1789] "Disability" refers to physical or mental handicaps or limitations that arise in the course of work.

[1790] "Job challenges" are the job-related problems and challenges that employees face.

[1791] "Characteristic data" is detailed information about the behavior and status of the employee or robot being analyzed.

[1792] "Challenge data" is information about a specific problem an employee or robot is facing.

[1793] "Improvement proposals" are specific action plans proposed to improve the performance of employees or robots.

[1794] "Motivation improvement measures" are specific proposals and measures to increase employee motivation and efficiency.

[1795] The "administrator's terminal" refers to a computer or smart device used by the administrator for operation.

[1796] "Robot operation status" refers to information about the progress of the work being performed by the factory robot and the accuracy of its movements.

[1797] "Smart glasses" are wearable devices that display real-time information and record on-site conditions.

[1798] "Maintenance measures" are specific management procedures and repair proposals to maintain the normal operation of robots and equipment.

[1799] This invention relates to a system that uses generative AI to analyze employee behavioral characteristics, speech patterns, obstacles, and work challenges, and provides optimal improvement proposals and motivational measures. This system is particularly useful for improving the operational efficiency and accuracy of factory robots. Specific embodiments of the system are described below.

[1800] Hardware and Software Configuration

[1801] 1. Hardware:

[1802] Smart glasses (e.g., Google Glass): Used to monitor the operation status of factory robots in real time.

[1803] Administrator's device: A device such as a PC or smartphone used to receive generated improvement proposals and motivational measures.

[1804] 2. Software:

[1805] Data collection application: Runs on the smart glasses and collects and transmits robot operation data.

[1806] Generative AI model: Runs on the server and analyzes and processes collected data.

[1807] System execution procedures and operations

[1808] 1. Data Collection:

[1809] The smart glasses monitor the operating status of factory robots (operating efficiency, error frequency, accuracy, etc.) in real time and periodically send this data to a server.

[1810] 2. Data transmission and storage:

[1811] The server stores the received data in a central database, which is then used for analysis by the generative AI.

[1812] 3. Characteristics and Issues Analysis:

[1813] The server preprocesses the stored data before passing it to the generation AI, which performs missing value imputation and outlier detection to maintain data integrity.

[1814] Next, the server launches the generative AI, which uses the preprocessed data to perform characteristic analysis and problem analysis related to the operational efficiency and accuracy of the factory robot.

[1815] 4. Generate improvement proposals:

[1816] The generative AI generates optimal improvement and maintenance plans based on the robot's characteristic data and problem data.

[1817] 5. Output and action taken:

[1818] The server compiles the generated improvement proposals and maintenance measures into a report format and sends it to the administrator's terminal.

[1819] The user (administrator) receives this report and takes specific countermeasures on-site based on the report.

[1820] Specific examples

[1821] For example, if a factory robot has an operating efficiency of 85%, an error frequency of 2, and an accuracy of 90%, the data collected by the smart glasses will be converted into the following prompt sentence:

[1822] "Analyze the operational activity data of a factory robot and generate optimal improvement and maintenance plans to improve efficiency. The following data was collected: operational efficiency: 85%, error frequency: 2 times, accuracy: 90%."

[1823] If you feed this prompt to a generative AI model, you'll get the following response:

[1824] To improve the efficiency of your robot's operation, we recommend the following steps:

[1825] 1. Standardizing operating procedures and providing training

[1826] 2. Shorter maintenance intervals

[1827] 3. Software updates to improve operation accuracy

[1828] By generating specific improvement plans in this way, it is possible to effectively improve the operating conditions of factory robots and increase productivity.

[1829] This system can be applied not only to factory robots, but also to managing other employees and improving their performance. It also includes a function that continuously updates data specific to each employee and regenerates new improvement proposals and motivational measures based on previous feedback data. This allows for continuous optimal work styles and motivation management.

[1830] Finally, by utilizing generative AI, this invention enables rapid implementation of approaches tailored to the characteristics of employees and robots, making it easier to respond to individual needs.

[1831] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1832] Step 1:

[1833] Data collection

[1834] Input: The robot's operation status (operation efficiency, error frequency, accuracy, etc.) is obtained in real time from the smart glasses.

[1835] How it works: The smart glasses use sensors to collect data on the robot's operations and record it digitally.

[1836] Output: The collected operation data is sent from the terminal (smart glasses) to the server.

[1837] Step 2:

[1838] Data transmission and storage

[1839] Input: Robot operation data sent from the terminal.

[1840] Specific operation: The server receives the received data in real time and stores it in a central database.

[1841] Output: The saved operational data is used for the next analysis step.

[1842] Step 3:

[1843] Characteristics analysis and problem analysis

[1844] Input: Robot operation data stored in a central database.

[1845] Specific operation: The server performs preprocessing, imputes missing values ​​in the data, detects outliers, and maintains data integrity. The preprocessed data is then passed to the generation AI.

[1846] Output: Preprocessed data passed to the generative AI.

[1847] Step 4:

[1848] Generative AI startup and analysis

[1849] Input: Preprocessed operational data.

[1850] Specific operation: The generative AI analyzes the robot's characteristics and issues based on the input data. For example, it analyzes based on data such as 85% operational efficiency, 2 error frequencies, and 90% accuracy.

[1851] Output: Analysis results based on characteristic data and problem data regarding the robot's operating situation.

[1852] Step 5:

[1853] Generate improvement proposals

[1854] Input: Analysis results (characteristic data and problem data).

[1855] Specific actions: The generative AI generates optimal improvement and maintenance plans from the analysis results, such as standardizing operating procedures, shortening maintenance intervals, and proposing software updates.

[1856] Output: Generated improvement and maintenance recommendations.

[1857] Step 6:

[1858] Output and action taken

[1859] Input: Generated improvement and maintenance measures.

[1860] Specific operation: The server compiles the generated improvement proposals and maintenance measures into a report format and sends it to the administrator's terminal.

[1861] Output: Report received on administrator's terminal.

[1862] Step 7:

[1863] Feedback and Continuous Improvement

[1864] Input: Feedback data on the effectiveness of measures taken by administrators and new issues that have arisen.

[1865] Specific operation: The user (administrator) inputs feedback data into the terminal and sends it to the server, which stores it in a database and reanalyzes it as feedback data using the generation AI.

[1866] Output: Continuous improvement recommendations based on new feedback data.

[1867] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1868] This invention relates to a system that uses generative AI to analyze employees' behavioral characteristics, tone of voice, obstacles, and work challenges, and also to a system that uses an emotion engine to analyze employees' emotional data and provide optimal improvement proposals and motivational measures. This system is designed to provide a work environment and measures that are suited to each individual employee, thereby improving their productivity and motivation.

[1869] System Overview

[1870] The system includes the following major components:

[1871] 1. Data Collection Device (hereinafter referred to as "Device")

[1872] 2. Central Database (hereinafter referred to as "Server")

[1873] 3. Generation AI

[1874] 4. Emotion Engine

[1875] 5. Management Interface (hereinafter "Terminal")

[1876] Operational Overview

[1877] The system begins by entering an employee's behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data into a terminal and sending it to a server. The server stores this data in a central database and passes it to a generative AI and emotion engine for analysis. The generative AI generates improvement and motivational measures based on the employee's individual characteristics and emotions and sends them back to the management terminal. Based on these results, the manager can implement the optimal response for the employee.

[1878] Program processing

[1879] Data collection

[1880] Users input employee information (behavioral characteristics, tone of voice, obstacles, work challenges) and emotional data into the terminal. Each piece of information is collected in detail using specific forms and checklists, as well as emotion recognition technology.

[1881] Example input items:

[1882] Employee ID

[1883] Behavioral characteristics: Poor time management

[1884] Tone: Calm and polite

[1885] Disability: Attention Deficit Disorder (ADHD)

[1886] Work Challenge: Slow task completion speed

[1887] Emotional data: Stress levels based on facial expressions and voice analysis

[1888] Data transmission and storage

[1889] The device sends the input data to a server, which stores it in a central database for later analysis by the generative AI and emotion engine.

[1890] Characteristics analysis and problem analysis

[1891] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[1892] The server then passes the preprocessed data to the generation AI and emotion engine for analysis. The generation AI analyzes the employee's behavioral characteristics and issues, while the emotion engine analyzes the employee's emotional data.

[1893] Generate improvement proposals

[1894] Generative AI and an emotion engine generate specific improvement proposals and motivational measures based on each employee's individual characteristics, challenges, and emotions.

[1895] This example generates:

[1896] Employee A's improvement suggestion:

[1897] Conducting time management training

[1898] Setting short-term goals and providing feedback

[1899] Motivate with positive praise

[1900] Introducing relaxation techniques based on emotional data

[1901] Employee B's improvement suggestion:

[1902] Organize your work environment and provide a space where you can focus

[1903] Incorporating a routine with short breaks

[1904] Introduction of an error checklist and confirmation before work begins

[1905] Introducing stress management methods based on emotional data

[1906] Output and action taken

[1907] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to the terminal. The user (administrator) receives this and takes specific measures for employees based on the report.

[1908] This example does the following:

[1909] Set goals for the day at your morning meeting

[1910] Providing feedback after completing a task

[1911] If they complete the task more quickly, they are given an extra break.

[1912] Implement relaxation and stress management techniques based on emotional data

[1913] Feedback and Continuous Improvement

[1914] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[1915] This system is a powerful tool for providing optimized support to each employee, improving their productivity and satisfaction. Utilizing generative AI and an emotion engine, it enables personalized responses and quickly implements approaches tailored to the employee's characteristics and emotions.

[1916] The processing flow will be explained below.

[1917] Step 1:

[1918] Users input employee behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data into a terminal using specific forms and checklists, as well as emotion recognition technology (e.g., facial expression analysis cameras and voice recognition microphones).

[1919] Step 2:

[1920] The device sends the entered data to the server, where it is encrypted and transmitted using a secure protocol.

[1921] Step 3:

[1922] The server stores the received data in a central database, which stores each employee's behavioral characteristics, tone of voice, obstacles, work challenges, and emotional data.

[1923] Step 4:

[1924] The server preprocesses the stored data. This preprocessing includes filling in missing data, detecting outliers, and standardizing data formats. Data preprocessing is essential to improve the accuracy of analysis.

[1925] Step 5:

[1926] The server passes the preprocessed data to the generation AI and emotion engine. The generation AI analyzes the employee's behavioral characteristics and issues, and the emotion engine analyzes the employee's emotional data.

[1927] Step 6:

[1928] The generative AI analyzes the characteristic data and issue data for each employee, and the emotion engine analyzes the emotional data. Based on the results of this analysis, it generates optimal improvement plans and motivation-boosting measures.

[1929] Step 7:

[1930] The server formats the generated improvement and motivational measures and creates a report for the management interface, which includes the analysis results and specific countermeasures.

[1931] Step 8:

[1932] The server sends the report to the terminal, which is provided in a format that is easy for the administrator to understand.

[1933] Step 9:

[1934] The user (manager) receives the report and takes specific action based on it, including suggestions for improvement and motivation provided by the generative AI and emotion engine.

[1935] Step 10:

[1936] The user (administrator) evaluates the effectiveness of the countermeasures and any new issues that arise, and enters the evaluation results and feedback data into the terminal.

[1937] Step 11:

[1938] The terminal sends feedback data to the server, which is stored in a central database in the same way as the initial data.

[1939] Step 12:

[1940] The server reanalyzes the feedback data using the generative AI and emotion engine, which is used as important input data for the next improvement plan.

[1941] Step 13:

[1942] The server then formats the new improvement proposals and motivation-boosting measures into a report and sends it to the device. This process is repeated to continuously optimize work styles and motivation management.

[1943] In this way, the system can continuously analyze employees' characteristics and emotions and provide optimal improvement and motivational strategies.

[1944] Example 2

[1945] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1946] In today's workplace, improving employee productivity and motivation is a key challenge. However, accurately understanding the behavioral characteristics and emotional state of each employee and responding to them individually can be difficult. It is also not easy to quickly provide appropriate improvement proposals and motivation-boosting measures based on employees' characteristics and challenges. A system that effectively utilizes employee emotional data to achieve specific behavioral improvements and motivational improvements is needed.

[1947] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1948] In this invention, the server includes: means for analyzing employee behavioral characteristics, tone of voice, obstacles, and work issues using a generation AI; means for generating improvement plans and motivation-boosting measures based on the resulting characteristic data and issue data; means including an emotion analysis engine for analyzing the collected emotion data and proposing appropriate measures based on the employee's emotions; and means for sending the generated improvement plans and motivation-boosting measures to a manager's terminal in report format. This enables the rapid provision of optimized support for each employee, improving productivity and motivation.

[1949] "Generative AI" is a system that uses artificial intelligence techniques to analyze data and generate outputs or results suitable for specific purposes.

[1950] "Behavioral characteristics" are characteristics related to employee behavior patterns, habits, and actions.

[1951] "Tone" refers to the characteristics of the language and communication style used by employees.

[1952] "Disability details" is information about an employee's specific disability and its impact.

[1953] "Work challenges" are work-related problems employees face or areas that need improvement.

[1954] "Characteristic data" refers to information regarding the behavioral characteristics, tone of voice, and disability details of the employee being analyzed.

[1955] "Issue data" refers to information regarding business issues and areas requiring improvement.

[1956] An "improvement proposal" is a specific improvement measure proposed based on the employee's behavioral characteristics and challenges.

[1957] "Motivation improvement measures" are specific measures to increase employee motivation and enthusiasm.

[1958] "Emotional data" is data that indicates an employee's emotional state and is typically collected through facial and voice analysis.

[1959] An "emotion analysis engine" is a system that analyzes emotional data, evaluates employees' emotional state, and generates countermeasures based on that.

[1960] "Administrator's terminal" refers to a computer or device used by the system administrator to receive generated reports and improvement proposals.

[1961] This invention is a system that utilizes generative AI and an emotion analysis engine to analyze employees' behavioral characteristics, tone of voice, obstacles, work issues, and emotional data, and provides optimal improvement plans and motivational measures for each employee. This system consists of a data collection terminal, a server, generative AI, an emotion analysis engine, and a management terminal.

[1962] Hardware and Software Use

[1963] Data collection device: A computer or mobile device used to collect employee behavioral characteristics, tone, obstacles, work challenges, and emotional data. This device is equipped with sensors such as a camera and microphone and is also used to collect emotional data.

[1964] Server: A computer that stores collected data in a central database and passes it to the generation AI and emotion analysis engine. It also transmits generated improvement proposals and motivational measures to the management terminal.

[1965] Generative AI: An artificial intelligence model used to analyze employee behavioral characteristics and challenges. This AI generates optimal improvement plans and motivational measures based on data for each employee.

[1966] Sentiment Analysis Engine: Software that analyzes emotional data and assesses the emotional state of employees, allowing it to suggest countermeasures based on their emotions.

[1967] Management terminal: A computer or device where a manager receives generated reports and takes action against employees.

[1968] Explanation of program processing

[1969] Users enter employee behavioral characteristics, tone, obstacles, work challenges, and emotional data into data collection devices. This data is collected through forms, checklists, cameras, and microphones.

[1970] Specifically, the following data is entered:

[1971] Employee ID

[1972] Behavioral characteristics: Poor time management

[1973] Tone: Calm and polite

[1974] Disability: Attention Deficit Disorder (ADHD)

[1975] Work Challenge: Slow task completion speed

[1976] Emotional data collected using a camera and microphone: stress levels through facial and voice analysis

[1977] The terminal encrypts the input data and transmits it in real time to the server, which stores the received data in a central database and performs pre-processing on the data, including missing value imputation, outlier detection, and data format standardization.

[1978] The server then passes the preprocessed data to the generation AI and emotion analysis engine for analysis. The generation AI analyzes employees' behavioral characteristics and issues, and generates optimal improvement proposals and motivation-boosting measures. At the same time, the emotion analysis engine analyzes the emotional data and proposes countermeasures based on the employee's emotional state.

[1979] The generated improvement proposals and motivation-boosting measures are compiled into a report and sent to a management terminal. The user (manager) then implements specific measures for the employees based on this report.

[1980] for example:

[1981] Set goals for the day at your morning meeting

[1982] Providing feedback after completing a task

[1983] Offer additional breaks if the task can be completed more quickly

[1984] Implement relaxation and stress management techniques based on emotional data

[1985] Finally, the user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues that have arisen into the terminal and sends it back to the server, allowing the system to continuously update the data and continue to provide optimal improvement proposals and motivation-boosting measures.

[1986] Example prompts for generative AI models

[1987] Below are some example prompts to be input to the generative AI model:

[1988] Prompt statement:

[1989] Employee ID: 12345

[1990] Behavioral trait: Poor time management

[1991] Tone: Calm and polite

[1992] Disability: ADHD

[1993] Work Challenge: Slow task completion rate

[1994] Emotion data: High stress level based on facial expression analysis

[1995] Generate optimal improvement and motivational strategies.

[1996] This makes it possible to provide each employee with quick, optimized support, improving productivity and motivation.

[1997] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1998] Step 1:

[1999] Data collection

[2000] Users input employee behavioral characteristics, tone of voice, obstacles, work tasks, and emotional data into a terminal. This input data is collected through forms, checklists, cameras, and microphones.

[2001] Input: Employee ID, behavioral characteristics, tone of voice, obstacle details, work issues, emotional data

[2002] Specific behavior:

[2003] The user enters an employee ID into a form.

[2004] Select a behavioral trait from the selection list.

[2005] Enter the tone.

[2006] Check the fault details.

[2007] Enter work assignments.

[2008] Emotional data (facial expression analysis, voice analysis) is collected using a camera and microphone.

[2009] Step 2:

[2010] Data transmission

[2011] The device encrypts the entered data and sends it to the server. The data is sent in real time to prevent data leakage during transmission.

[2012] Input: Employee data entered into the terminal

[2013] Output: The encrypted data is sent to the server

[2014] Specific behavior:

[2015] The device encrypts all input data at once.

[2016] The encrypted data is sent to the server.

[2017] Step 3:

[2018] Data storage

[2019] The server deserializes the received data and stores it in a central database, where the storage is performed transactionally to ensure consistency and integrity.

[2020] Input: Encrypted data sent to the server

[2021] Output: Employee data deserialized and saved to the database

[2022] Specific behavior:

[2023] The server decrypts the received data.

[2024] The data is deserialized and stored in a central database.

[2025] Step 4:

[2026] Data Preprocessing

[2027] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats.

[2028] Input: Stored raw data

[2029] Output: Preprocessed data

[2030] Specific behavior:

[2031] The server detects and completes missing values ​​in the stored data.

[2032] Correct any abnormal values.

[2033] Transform data into a unified format.

[2034] Step 5:

[2035] Characteristics analysis and problem analysis

[2036] The server passes the preprocessed data to the generation AI and sentiment analysis engine for analysis. The generation AI analyzes employee behavioral characteristics and issues, while the sentiment analysis engine analyzes the emotional data.

[2037] Input: Preprocessed data

[2038] Output: Analysis results (behavioral characteristics, tasks, emotional state)

[2039] Specific behavior:

[2040] The server converts the data into an input format for the generative AI model.

[2041] The generative AI analyzes behavioral characteristics and challenges and outputs the results.

[2042] The emotion analysis engine analyzes the emotion data and outputs the emotional state.

[2043] Step 6:

[2044] Generate improvement proposals

[2045] Generative AI and an emotion analysis engine generate specific improvement proposals and motivational measures based on each employee's characteristics, challenges, and emotions.

[2046] Input: Analysis results (behavioral characteristics, tasks, emotional state)

[2047] Output: Improvement proposals and motivational measures

[2048] Specific behavior:

[2049] The server receives the analysis results from the generation AI and the sentiment analysis engine.

[2050] Generate optimal improvement plans and motivation measures for each employee.

[2051] Step 7:

[2052] Output of improvement proposals

[2053] The server compiles the generated improvement proposals and motivation-boosting measures into a report format and sends it to the management terminal.

[2054] Input: Generated improvement ideas and motivational measures

[2055] Output: Report format data. Send to management terminal.

[2056] Specific behavior:

[2057] The server formats the data using a report template.

[2058] The formatted report is sent to the management terminal.

[2059] Step 8:

[2060] Implementing countermeasures

[2061] The user (manager) takes specific measures for the employee based on the report.

[2062] Input: Report sent to management terminal

[2063] Output: Implementing action against employee

[2064] Specific behavior:

[2065] The user (administrator) sets the day's goals at a morning meeting.

[2066] Provide feedback after completing a task.

[2067] If they can complete the task more quickly, they are given an extra break.

[2068] Relaxation and stress management techniques are implemented based on emotional data.

[2069] Step 9:

[2070] Feedback and Continuous Improvement

[2071] The user (administrator) inputs the effectiveness of the countermeasures they have implemented and any new issues they have encountered into the terminal and sends it back to the server. This updates the database, and the new feedback data is reanalyzed by the generation AI and emotion analysis engine.

[2072] Input: Feedback data, effectiveness of countermeasures, new issues

[2073] Output: Updated data, continuous improvement ideas and motivational measures

[2074] Specific behavior:

[2075] The user (administrator) inputs the feedback data into the terminal.

[2076] The device sends this to the server, where it is stored in a database.

[2077] The server reanalyzes the feedback data and generates new improvement suggestions.

[2078] (Application example 2)

[2079] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2080] When workers and robots work together in factories, optimal work instructions and support that take into account the behavioral characteristics and emotional data of workers are not being provided, which is a problem that leads to reduced productivity and increased stress among workers. Furthermore, there is a lack of individualized measures for each worker, making it difficult to respond quickly and accurately, which makes it difficult to improve worker motivation and provide an efficient work environment.

[2081] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing an employee's behavioral characteristics, tone of voice, obstacle details, and work issues using a generation AI, means for generating improvement plans and motivation improvement measures based on the resulting characteristic data and issue data, means for sending the generated improvement plans and motivation improvement measures to a manager's terminal, means for analyzing employee emotion data and optimizing robot work instructions based on the analysis results, and means for detecting an employee's stress level and suggesting appropriate rest. This allows work instructions and support optimized for each employee to be automatically provided, improving productivity and reducing employee stress.

[2082] "Generative AI" is an artificial intelligence that uses artificial intelligence technology to analyze employees' behavioral characteristics and work challenges, and automatically generates appropriate improvement proposals and motivation-boosting measures.

[2083] "Behavioral characteristics" refer to an employee's working style and behavioral patterns, such as strengths and weaknesses in time management and the speed at which tasks are completed.

[2084] "Tone of speech" refers to the characteristics of an employee's language and speaking style, such as a calm and polite manner of speaking or a strong tone of voice.

[2085] "Disability" means information about an employee's disability, such as attention deficit disorder or physical limitations.

[2086] "Work challenges" refer to problems or difficulties an employee faces in performing their job, such as slow task completion.

[2087] "Characteristic data" refers to data obtained as a result of analysis, such as employee behavioral characteristics and the nature of obstacles.

[2088] "Issue data" refers to data related to the work issues of employees obtained as a result of the analysis.

[2089] "Emotional data" is data that indicates an employee's emotional state and is collected through voice analysis and facial expression recognition.

[2090] "Improvement proposals" are specific improvement measures created based on an employee's behavioral characteristics and work challenges, and include, for example, training on time management.

[2091] "Motivation measures" are specific means to increase employees' motivation to work, and include setting short-term goals and motivating employees through praise.

[2092] "Administrator's device" refers to a computer or smart device used by a supervisor or manager, and is a device used to view and manage employee characteristic data and improvement proposals.

[2093] "Robot work instructions" refers to automatically giving instructions to robots in factories to optimize their collaborative work with employees.

[2094] "Break suggestion" means sensing an employee's stress level and suggesting a break at the appropriate time if necessary.

[2095] This invention realizes a system that analyzes employee behavioral characteristics, speech patterns, obstacles, work challenges, and emotional data to provide optimal improvement plans and motivational measures in order to optimize collaboration between employees and robots in a factory. A specific embodiment of this system will be described below.

[2096] System Overview

[2097] The system includes the following major components:

[2098] 1. Data Collection Device (hereinafter referred to as "Device")

[2099] 2. Central Database (hereinafter referred to as "Server")

[2100] 3. Generation AI

[2101] 4. Emotion Engine

[2102] 5. Robot Operation Interface (hereinafter "Robot Interface")

[2103] 6. Management terminal (hereinafter referred to as "Management terminal")

[2104] Operational Overview

[2105] The user inputs the employee's behavioral characteristics, tone of voice, details of the obstacles, work issues, and emotional data into the terminal and sends it to the server. The server stores this data in a central database and passes it to the generation AI and emotion engine for analysis. The generation AI generates improvement proposals and motivational measures based on the employee's individual characteristics and emotions and sends them back to the management terminal. It also provides the robot with optimal work instructions through the robot interface. Based on these results, the manager can implement the optimal response for the employee.

[2106] Program processing

[2107] Data collection

[2108] Users input employee information (behavioral characteristics, tone of voice, obstacles, work challenges) and emotional data into the terminal. Each piece of information is collected in detail using specific forms and checklists, as well as emotion recognition technology.

[2109] Example input items:

[2110] Employee ID

[2111] Behavioral characteristics: Poor time management

[2112] Tone: Calm and polite

[2113] Disability: Attention Deficit Disorder (ADHD)

[2114] Work Challenge: Slow task completion speed

[2115] Emotional data: Stress levels based on facial expressions and voice analysis

[2116] Data transmission and storage

[2117] The device sends the input data to a server, which stores it in a central database for later analysis by the generative AI and emotion engine.

[2118] Characteristics analysis and problem analysis

[2119] The server preprocesses the stored data. This preprocessing includes filling in missing values, detecting outliers, and standardizing data formats. The server then passes the preprocessed data to the generative AI and emotion engine for analysis. The generative AI analyzes employee behavioral characteristics and issues, while the emotion engine analyzes employee emotional data.

[2120] Generate improvement proposals and motivational measures

[2121] Generative AI and an emotion engine generate specific improvement proposals and motivational measures based on each employee's individual characteristics, challenges, and emotions.

[2122] This example generates:

[2123] Employee A's improvement suggestion:

[2124] Conducting time management training

[2125] Setting short-term goals and providing feedback

[2126] Motivate with positive praise

[2127] Introducing relaxation techniques based on emotional data

[2128] Employee B's improvement suggestion:

[2129] Organize your work environment and provide a space where you can focus

[2130] Incorporating a routine with short breaks

[2131] Introduction of an error checklist and confirmation before work begins

[2132] Introducing stress management methods based on emotional data

[2133] Output and action taken

[2134] The server compiles the generated improvement proposals and motivation-boosting measures into a report and sends it to a management terminal. The user (manager) receives this report and implements specific measures for employees based on the report. The server also provides the robot with optimal work instructions based on the employee's emotional data through the robot interface.

[2135] This example does the following:

[2136] Set goals for the day at your morning meeting

[2137] Providing feedback after completing a task

[2138] If they complete the task more quickly, they are given an extra break.

[2139] Implement relaxation and stress management techniques based on emotional data

[2140] Feedback and Continuous Improvement

[2141] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[2142] Example prompts to input to a generative AI model:

[2143] Prompt: Based on Employee A's behavioral and emotional data, please suggest the best improvement and motivational measures for him.

[2144] Behavioral data: Poor time management, slow task completion

[2145] Emotional data: high stress level, tired facial expression

[2146] As described above, this invention is a powerful tool for providing optimized support to each employee and improving their productivity and satisfaction. By utilizing generative AI and an emotion engine, personalized responses are possible, and approaches tailored to the employee's characteristics and emotions can be quickly implemented.

[2147] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2148] Step 1:

[2149] The user inputs employee information (behavioral characteristics, tone of voice, obstacles, and work challenges) and emotional data into the terminal. Specific forms and checklists are used to collect detailed data, which is then analyzed using emotion recognition technology. For example, the user inputs the employee's ID, behavioral characteristics (poor time management), tone of voice (calm and polite), obstacles (attention deficit disorder), work challenges (slow task completion speed), and emotional data (stress level determined by facial and voice analysis).

[2150] Input: Employee behavioral characteristics, tone of voice, obstacles, work issues, emotional data

[2151] Output: A set of input data

[2152] Step 2:

[2153] The device sends the input data to the server, which then stores it in a central database for later analysis by the generative AI and emotion engine.

[2154] Input: Employee data sent from the terminal

[2155] Output: Data stored in a central database

[2156] Step 3:

[2157] The server preprocesses the stored data, which includes imputing missing values, detecting outliers, and standardizing data formats. For example, it imputes missing data and detects and corrects outliers.

[2158] Input: Raw data in a central database

[2159] Output: Preprocessed dataset

[2160] Step 4:

[2161] The server passes the preprocessed data to the generation AI and emotion engine for analysis. The generation AI analyzes employees' behavioral characteristics and issues, while the emotion engine analyzes their emotional data. Specifically, for example, GPT-4 is used to analyze the characteristic data and issue data, and the Emotion API is used to analyze the emotional data.

[2162] Input: Preprocessed data

[2163] Output: Analysis results (characteristic data, issue data, emotion data)

[2164] Step 5:

[2165] The generative AI and emotion engine generate specific improvement and motivational measures based on each employee's characteristics, challenges, and emotions. These improvement measures are optimized for each employee. For example, for employee A, time management training and short-term goal setting are suggested.

[2166] Input: Analysis results

[2167] Output: Improvement proposals and motivational measures

[2168] Step 6:

[2169] The server compiles the generated improvement proposals and motivation-boosting measures into a report format and sends it to a management terminal. Furthermore, the robot interface provides the robot with optimal work instructions based on the employee's emotional data.

[2170] Input: Improvement ideas and motivational measures

[2171] Output: Report sent to the management terminal, work instructions to the robot

[2172] Step 7:

[2173] The user (administrator) inputs the results of the countermeasures they have implemented and any new issues that have arisen into the device and sends them back to the server. The server stores this in a database and reanalyzes it as new feedback data using the generative AI and emotion engine. This allows for continuous optimal work styles and motivation management.

[2174] Input: Effects of implemented countermeasures, new issues

[2175] Output: Save feedback data to database, reanalysis results

[2176] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2177] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2178] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2179] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2180] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2181] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2182] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2183] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2184] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2185] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2186] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2187] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2188] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2189] 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.

[2190] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2191] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2192] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resour...

Claims

1. Using generative AI, we analyze employee behavioral characteristics, tone of voice, obstacles, and work challenges. A means for generating improvement proposals and motivation-enhancing measures based on the resulting characteristic data and problem data; A means for transmitting the generated improvement proposals and motivation improvement measures to a terminal of an administrator; A system including:

2. 10. The system of claim 1, further comprising means for continuously updating employee-specific data and regenerating new improvement and motivational strategies based on previous feedback data.

3. The system according to claim 1, further comprising means for storing the characteristic data and task data of each employee in a database and preprocessing the data before the generation AI performs analysis.

Images