System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting past leave acquisition data of an employee; means for preprocessing the collected data; means for analyzing a leave acquisition pattern based on the preprocessed data and generating a prediction model; means for generating a leave acquisition advice for the employee using the prediction model; and means for notifying a terminal of the employee of the generated advice.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] In today's business environment, employees often find it difficult to effectively use their paid leave due to their busy schedules. This can lead to increased employee stress, reduced work efficiency, and health problems. Furthermore, a low rate of paid leave usage within an organization can lead to problems such as poor progress in improving the working environment. To solve these problems, a system is needed to support employees in taking paid leave at the appropriate time. [Means for solving the problem]

[0005] This invention provides a system that predicts the optimal timing for each employee to take paid leave by collecting and preprocessing employees' past leave data and analyzing it using generative AI. This system includes a means for learning employees' leave-taking patterns and generating leave advice that also takes workload data into account. Furthermore, by notifying employees of this advice via their devices, employees are more likely to take paid leave at the appropriate time. This reduces employee stress, improves work efficiency, and creates a healthier working environment.

[0006] An "employee" is an individual employed by a particular organization or company.

[0007] "Vacation data" refers to information such as the date, duration, and reason for an employee's paid vacation.

[0008] "Collection means" refers to the methods and systems used to obtain the required data from databases and other sources.

[0009] "Preprocessing" is the process of data cleansing and processing to convert collected data into an analyzable format.

[0010] Analyzing "vacation patterns" means using past vacation data to analyze when employees tend to take vacation.

[0011] A "prediction model" is a model for predicting future vacation timing based on the analysis results.

[0012] "Means for generating advice" refers to a method or system that uses a predictive model to suggest optimal vacation timing for employees.

[0013] The "notification means" refers to a method or system for transmitting the generated vacation advice to an employee's terminal.

[0014] "Workload data" is information relating to the busyness and workload of employees.

[0015] "Generative AI" is an artificial intelligence technique used to analyze data and generate predictive models. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention relates to a system for supporting employees in taking paid leave at an appropriate time. This system is implemented in the following manner.

[0038] Collecting employee vacation history data

[0039] The server has a means for collecting employee's past vacation acquisition data from the company's internal database, including information such as the date and duration of each employee's paid vacation.

[0040] Example: The server uses an SQL query to retrieve vacation data for employee ID "B456" for the past year. This data is stored in a temporary data store.

[0041] Data Preprocessing

[0042] The server performs pre-processing on the collected leave-taking data, including imputing missing values ​​and detecting and correcting outliers.

[0043] For example: If the collected data contains missing values, the server will perform reasonable imputation and correct any values ​​that are found to be significantly outside of normal holiday periods.

[0044] Pattern Analysis and Model Generation

[0045] The server uses generation AI to analyze vacation-taking patterns from past vacation-taking data and generate a predictive model.

[0046] Example: The server uses generative AI to identify patterns, such as a tendency to take vacation every three months, based on vacation-taking data. This generates a predictive model.

[0047] Generating Advice

[0048] The server uses the generated predictive model to generate vacation advice for each employee, which is optimized taking into account workload data.

[0049] Example: The server retrieves the latest business data and generates specific advice based on that data, such as "We recommend that you take paid vacation on next Friday, December 8, 2023."

[0050] User Notification

[0051] The server then sends the generated advice to the employee's device via email, internal chat tools, etc.

[0052] Example: The server obtains employee B's email address and sends the generated vacation advice by email, saying, "We recommend that you take paid vacation next Friday, December 8, 2023. There has been a recent peak in workload, so you need to refresh yourself."

[0053] The system of the present invention can be implemented by following the above steps. Using this system makes it easier for employees to take paid leave at appropriate times, reducing stress, improving work efficiency, and creating a healthy working environment.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The server executes an SQL query to collect employee's past vacation data from the company database. For example, for employee ID "B456", retrieve data including vacation dates and duration for the past year. The collected data is stored in a temporary data store.

[0057] Step 2:

[0058] The server performs pre-processing on the collected leave taking data, which specifically includes the following actions:

[0059] Detecting and imputing missing values, for example, inserting reasonable approximations when data are missing for a period.

[0060] Detecting and correcting outliers, for example, correcting periods that significantly exceed normal vacation periods.

[0061] Step 3:

[0062] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[0063] Step 4:

[0064] The server runs additional database queries to retrieve up-to-date workload data, which indicates employee workload and workload levels and is used to inform vacation advice.

[0065] Step 5:

[0066] The server predicts the optimal time to take vacation for each employee based on the trained generative AI model and the latest workload data, generating specific advice such as, "We recommend taking paid vacation on next Friday, December 8, 2023."

[0067] Step 6:

[0068] The server obtains the employee's contact information (e.g., email address) to notify them of the generated vacation advice, constructs a notification message, and sends it to the employee's device.

[0069] Step 7:

[0070] The user (employee) receives a notification from the server and considers taking paid leave at the recommended time. Based on this notification, the user incorporates the leave into their schedule.

[0071] Example 1

[0072] 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."

[0073] Currently, many companies face the problem of employees being unable to take paid leave at the appropriate time. This increases employee stress, reduces work efficiency, and risks health problems. Furthermore, typical systems recommend taking leave without considering individual employees' workloads or past leave-taking patterns, making it difficult to ensure that leave is appropriate for actual work situations. A system that can solve this problem is needed.

[0074] 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.

[0075] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the generated advice to employee terminals, and means for notifying the employees via email or an internal chat tool. This allows employees to take vacation at appropriate times, which is expected to reduce stress and improve work efficiency.

[0076] "Employee's past vacation data" refers to information about the dates and duration of paid vacation taken by an employee in the past.

[0077] "Preprocessing" refers to the process of complementing missing values ​​and correcting outliers in collected data.

[0078] "Vacation patterns" are data patterns that indicate the tendency and frequency of employees taking paid vacation.

[0079] A "predictive model" is a model for predicting future vacation time taken based on past data.

[0080] "Vacation Advice" means advice provided to employees regarding recommended timing for taking vacation based on predictive models.

[0081] "Notification" refers to the act of informing employees of the generated vacation advice.

[0082] "Email" is a communication method for sending text messages over the Internet.

[0083] An "internal chat tool" is a real-time messaging system used for communication between employees within a company.

[0084] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate models.

[0085] "Work volume data" refers to data relating to the volume and progress of an employee's work.

[0086] The present invention relates to a system for supporting employees in taking paid leave at the appropriate time, and this system is implemented using various hardware and software.

[0087] Hardware and Software Configuration

[0088] 1. Server: The server, which is the core of the system, accesses the database and is responsible for the series of processes of collection, analysis, and notification. The server has the computing power to run a high-performance database management system (DBMS) and generative AI models.

[0089] 2. Devices: The devices used by employees are devices that receive the vacation advice sent from the server. These include PCs, tablets, smartphones, etc.

[0090] 3. Network: The Internet or an internal company network is used for communication between the server and the terminal.

[0091] Program processing

[0092] The main program processing in this system is carried out as follows.

[0093] 1. Collect employee vacation history data

[0094] The server collects employee's past vacation data from the company's database, including important information such as the date and duration of vacation.

[0095] 2. Data Preprocessing

[0096] The server performs preprocessing on the collected data, including missing value imputation and outlier detection and correction.

[0097] 3. Pattern Analysis and Model Generation

[0098] The server uses generative AI to analyze vacation-taking patterns from past data and generate a predictive model.

[0099] 4. Generating Advice

[0100] The server generates vacation advice for each employee based on the predictive model, which is optimized by taking into account workload data.

[0101] 5. Notice to Users

[0102] The server then sends the generated advice to employees' devices via email or internal chat tools.

[0103] Specific examples

[0104] For example, the server uses an SQL query to collect vacation data for employee ID "B456" over the past year, analyzes patterns using this data, and then generates advice, such as "We recommend taking paid vacation on next Friday, December 8, 2023," taking into account workload data. This advice is then sent to the employee via email and internal chat tools.

[0105] Prompt Sentence Examples

[0106] Below are some example prompts to input to a generative AI model:

[0107] Analyze leave taking patterns based on the leave taking data for employee ID "B456" over the past year. Next, preprocess this data to correct missing values ​​and outliers. Next, use generative AI to analyze leave taking patterns and generate leave taking advice. Optimize this advice by taking into account the latest workload data. Finally, notify the generated advice to the employee's device.

[0108] As described above, the system of the present invention implements a series of precisely designed processes to enable employees to take paid leave at the optimal timing for them. This system is expected to solve the problem we are aiming for.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1: Collect employee leave history data

[0111] The server accesses the company database to collect employee leave history data. The input for this process is parameters such as employee ID and the period of leave. The server runs an SQL query to extract data such as the date and period of leave taken. This data is temporarily stored in a data store. Specifically, the following SQL query is used:

[0112] sql

[0113] SELECT leave_date, leave_duration FROM employee_leave WHERE employee_id = 'B456' AND leave_date >= '2022-01-01';

[0114] The output is the collected leave taking data in a predefined format.

[0115] Step 2: Preprocessing the data

[0116] The server performs preprocessing on the collected data. The input for this process is the raw data collected in step 1. The server performs imputation of missing values ​​and correction of outliers. For example, it imputes missing values ​​with the mean value and detects and corrects outliers. Specifically, it executes the following:

[0117] python

[0118] df['leave_duration'].fillna(df['leave_duration'].mean(), inplace=True)

[0119] if df['leave_duration'].sum() > 30:

[0120] df['leave_duration'] = 30

[0121] The output is pre-processed, clean data.

[0122] Step 3: Pattern analysis and model generation

[0123] The server uses the preprocessed data to analyze leave-taking patterns using a generative AI model and generate a predictive model. The input to this process is the preprocessed data from step 2. The server inputs prompts to the generative AI to identify patterns. For example, the following prompts can be used:

[0124] Analyze the vacation pattern based on the vacation data for employee ID "B456" over the past year.

[0125] The output is the generated leave taking prediction model.

[0126] Step 4: Generating Advice

[0127] The server uses the generated predictive model to generate vacation advice for each employee. The inputs to this process are the predictive model generated in step 3 and the latest workload data. The server considers past patterns and current workload data to suggest specific vacation timings. For example, the server generates advice as follows:

[0128] I recommend taking paid leave next Friday, December 8, 2023. My workload has recently peaked, so I need a break.

[0129] The output is specific vacation advice.

[0130] Step 5: Notify users

[0131] The server notifies the generated advice to the employee's device. The input for this process is the vacation advice generated in step 4 and the employee's contact information. The server sends the notification via email or an internal chat tool. Specifically, it sends an email as follows:

[0132] python

[0133] send_email(to="employeeB@example.com", subject="Vacation Advice", body=advice)

[0134] The output is a notification of the leave advice sent to the employee.

[0135] Through these steps, the system provides employees with advice on how to take paid leave at the appropriate time and efficiently notifies them.

[0136] (Application example 1)

[0137] 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."

[0138] While conventional employee vacation support systems have been effective in optimizing the timing of individual employees' vacations, they have limited functionality for monitoring on-site workers' workloads in real time and providing appropriate vacation advice. Furthermore, they lack the seamless integration required for installing predictive models on work support devices. This has created a need for optimization of the work environment's efficiency and worker health management.

[0139] 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.

[0140] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the generated advice to the employee's terminal, and means for notifying the advice to a work support device and for the device to monitor the workload in real time. This makes it possible to not only optimize the timing of each employee's vacation, but also to propose appropriate vacations that take into account the workload of field workers.

[0141] "Employee's past vacation data" refers to information such as the date, duration, and frequency of paid vacation taken by an employee in the past.

[0142] "Means of collection" refers to the functionality for obtaining and aggregating employee's past vacation data from internal databases and other sources.

[0143] "Preprocessing means" refers to the process of filling in missing values ​​and correcting outliers in the collected data.

[0144] "Means for analyzing vacation-taking patterns and generating predictive models" refers to a function that analyzes vacation-taking trends and patterns based on past vacation-taking data and creates a model that predicts future vacation taking based on that information.

[0145] "Means for generating vacation advice" refers to a function that uses predictive models to suggest optimal vacation dates and durations to employees.

[0146] "Means of notification" refers to the function for sending the generated vacation advice to employees' devices such as smartphones, PCs, and tablets.

[0147] "Work support equipment" refers to devices, including robots and computing units, installed in factories and work sites.

[0148] "Means for monitoring workload in real time" refers to a function for measuring and monitoring the workload and load of on-site workers in real time.

[0149] This invention is a system for supporting employees in taking paid leave at the appropriate time. This system is implemented using the following methods and means.

[0150] The server first collects employee's past vacation data. Specifically, it uses SQL queries to retrieve information such as the dates and periods of paid vacation taken for each employee from the company's database. For example, it retrieves vacation data for employee ID "B456" over the past year and stores it in a temporary data store.

[0151] The server then performs preprocessing on the collected data, including imputing missing values ​​and correcting outliers using Pandas. For example, if the collected data contains missing values, it performs rational imputation and corrects any values ​​that significantly exceed the normal holiday period.

[0152] Based on the preprocessed data, the server uses a generative AI model to analyze vacation-taking patterns and generate a predictive model. Specifically, it uses scikit-learn's Linear Regression to create a model based on past vacation-taking patterns. This model identifies patterns such as "people tend to take vacation every three months."

[0153] Using the generated predictive model, the server generates vacation advice for employees, taking into account workload data to optimize the timing of vacation. For example, it generates specific advice such as "We recommend taking paid vacation on next Friday, December 8, 2023."

[0154] The generated advice is sent by the server to the employee's device (smartphone, tablet, PC, etc.). Notifications are sent via email or internal chat tools. For example, a message is sent to employee B's email address saying, "We recommend that you take paid leave next Friday, December 8, 2023. Your workload has peaked recently, so you need to take a break."

[0155] Furthermore, this system also notifies the work support device of the advice, which has the function of monitoring the workload in real time. This function makes it possible to measure the workload and load of on-site workers in real time and provide appropriate advice on vacation.

[0156] As a specific example, after analyzing the vacation data for employee ID "B456" over the past year, it is predicted that the next vacation recommendation will be on December 8, 2023, and this information is notified to the employee and the work support device.

[0157] Example prompt sentence:

[0158] Based on the vacation data for employee ID "B456" over the past year, please predict the next appropriate vacation date and notify the employee.

[0159] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0160] Step 1:

[0161] The server collects employees' past vacation data. Specifically, it uses an SQL query to filter by employee ID from the company's database and retrieves information such as vacation dates and periods over the course of a year. For example, it collects data for employee ID "B456" and stores it in a temporary data store. The input is the employee ID and the vacation database, and the output is the filtered vacation data.

[0162] Step 2:

[0163] The server performs preprocessing on the collected data. The input data may contain missing values ​​or outliers, so these are imputed and corrected using Pandas. For example, if the data contains missing values, they are imputed with reasonable values, and if an outlier value that significantly exceeds the normal holiday period is detected, it is corrected to an appropriate range. The input is the collected raw data, and the output is preprocessed, clean data.

[0164] Step 3:

[0165] The server analyzes vacation-taking patterns based on the preprocessed data and generates a predictive model using generative AI. Specifically, it uses scikit-learn's Linear Regression to predict when an employee should take their next vacation based on their past vacation data. For example, it identifies a pattern such as "Employee B456 tends to take vacation every three months." The input is the preprocessed data, and the output is the vacation-taking pattern and predictive model.

[0166] Step 4:

[0167] The server uses the generated predictive model to generate vacation advice for employees. It also acquires and takes into account workload data for the current day and future periods. For example, it generates specific advice such as "We recommend that you take paid vacation on next Friday, December 8, 2023." The input is the predictive model and the latest workload data, and the output is the generated vacation advice.

[0168] Step 5:

[0169] The server notifies the employee of the generated vacation advice on their device. The advice is communicated to the employee via email or internal chat tools. For example, a notification may say, "We recommend that you take paid vacation next Friday, December 8, 2023. There has been a recent peak in workload, so you need to take a break." The input is the generated advice and the employee's contact information, and the output is the notification that arrives on the employee's device.

[0170] Step 6:

[0171] The advice is also sent to the work support device, allowing the device to monitor the workload in real time. This makes it possible to measure the workload and load of on-site workers in real time and provide appropriate vacation advice. The input is the generated advice and the on-site work support device, and the output is the device's real-time load data.

[0172] 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.

[0173] The present invention relates to a system for supporting employees in taking paid leave at the appropriate time. This system provides more personalized advice on taking leave by combining an employee emotion recognition engine.

[0174] Collecting employee vacation history data

[0175] The server has a means for collecting employee's past vacation acquisition data from the company's internal database, including information such as the date and duration of each employee's paid vacation.

[0176] Example: The server uses an SQL query to retrieve vacation data for employee ID "B789" for the past year. This data is stored in a temporary data store.

[0177] Data Preprocessing

[0178] The server performs pre-processing on the collected leave-taking data, including imputing missing values ​​and detecting and correcting outliers.

[0179] For example: If the collected data contains missing values, the server will perform reasonable imputation and correct any values ​​that are found to be significantly outside of normal holiday periods.

[0180] Pattern Analysis and Model Generation

[0181] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[0182] Collecting and analyzing emotional data

[0183] The server acquires data from various sources such as emails, chat logs, and voice data to collect user (employee) emotion data using an emotion engine.

[0184] Example: The server uses an emotion engine to analyze emails, chat logs, and audio data from meetings sent and received during employees' daily work to assess their stress levels. For example, the server may produce an evaluation result such as, "Your recent emails show a tendency toward emotional instability."

[0185] Generating Advice

[0186] The server generates optimal vacation advice for each employee based on the analysis results of the generated AI model and emotion engine, and also takes into account workload data to predict more personalized vacation timing.

[0187] Example: Based on the latest work data and emotional data, the server generates specific advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation next Friday, December 8, 2023."

[0188] User Notification

[0189] The server then sends the generated advice to the employee's device via email, internal chat tools, etc.

[0190] Example: The server obtains employee B's email address and sends the generated vacation advice by email, saying, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation on next Friday, December 8, 2023."

[0191] The system of the present invention can be implemented using the above steps. Using this system makes it easier for employees to take paid leave at the appropriate time, reducing stress, improving work efficiency, and creating a healthy working environment. Furthermore, by utilizing emotional data, more accurate advice can be provided, reducing the psychological burden on employees.

[0192] The processing flow will be explained below.

[0193] Step 1:

[0194] The server executes an SQL query to retrieve employee's past vacation data from the company database. For example, for employee ID "B789," retrieve data including vacation dates and durations for the past year. The retrieved data is stored in a temporary data store.

[0195] Step 2:

[0196] The server performs pre-processing on the collected leave taking data, which specifically includes the following actions:

[0197] Detecting and imputing missing values, for example, inserting reasonable approximations when data are missing for a period.

[0198] Detecting and correcting outliers, for example, periods that significantly exceed normal vacation periods.

[0199] Step 3:

[0200] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[0201] Step 4:

[0202] The server uses an emotion engine to collect emotion data from users (employees), including methods for acquiring data from various sources such as email, chat logs, and voice data.

[0203] Example: The server collects messages sent by employee B during his or her daily work from the company's internal email system and chat tools, and passes them to the emotion engine. The emotion engine analyzes the content of the messages and evaluates their stress level.

[0204] Step 5:

[0205] The server uses the emotion engine to analyze the emotional data and identify the user's stress level and emotional state. For example, the analysis may yield results such as, "Your recent messages have been expressing more negative emotions."

[0206] Step 6:

[0207] The server performs additional database queries to obtain up-to-date workload data, which includes information indicating employee workload and workload levels.

[0208] Example: The server retrieves the progress of business tasks and cases for the current month from the database and uses it for analysis.

[0209] Step 7:

[0210] The server predicts the optimal time for each employee to take leave based on the analysis results of the generative AI model and emotion engine, as well as workload data, and generates specific advice.

[0211] Example: The server generates advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation next Friday, December 8, 2023."

[0212] Step 8:

[0213] The server obtains the employee's contact information (e.g., email address) to notify them of the generated vacation advice, constructs a notification message, and sends it to the employee's device.

[0214] Example: The server obtains the email address of employee B and sends the generated vacation advice by email, saying, "Your current stress level is high, so we recommend that you take paid vacation on next Friday, December 8, 2023."

[0215] Step 9:

[0216] The user (employee) receives a notification from the server and considers taking paid leave at the recommended time. Based on this notification, the user incorporates the leave into their schedule.

[0217] Example 2

[0218] 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."

[0219] With traditional paid leave systems, employees must manage when to take their own leave, often resulting in employees being unable to take leave at the appropriate time. Furthermore, they rarely provide advice on taking leave that takes into account employees' emotional state and workload, and do not attempt to reduce stress or improve work efficiency. If this situation continues, it could increase the psychological burden on employees and result in a decline in the quality of their work.

[0220] 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.

[0221] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for collecting and analyzing employee emotion data, means for generating vacation advice for employees using the prediction model and the emotion data, and means for notifying the generated advice to the employee's terminal. This allows employees to take paid vacation at the appropriate time, which is expected to reduce stress and improve work efficiency. Furthermore, by utilizing emotion data, more accurate advice can be provided, reducing the psychological burden on employees.

[0222] "Employee's past vacation data" refers to data including the dates and duration of paid vacation time taken by an employee, as well as other related vacation usage information.

[0223] "Preprocessing" refers to processes such as filling in missing values ​​in collected data, correcting outliers, and formatting data.

[0224] "Vacation patterns" refer to the timing, frequency, and pattern of when a particular employee has taken paid vacation time in the past.

[0225] "Predictive model" refers to a model for predicting future vacation timing based on collected data and the results of its analysis.

[0226] "Emotional data" refers to data that indicates stress levels and emotional states extracted from emails, chat logs, audio data, etc. sent by employees during their daily work.

[0227] An "emotion recognition engine" refers to technology that analyzes collected emotional data and assesses employees' emotional state and stress levels.

[0228] "Vacation advice" refers to advice that suggests appropriate times for employees to take vacation based on collected data and predictive models.

[0229] "Employee devices" refers to devices such as computers, smartphones, and tablets used by employees for work.

[0230] "Workload data" refers to data that shows the status of the work that an employee is responsible for, such as the employee's current workload, project progress, and task list.

[0231] The present invention relates to a system that supports employees in taking paid leave at the appropriate time. This system provides more personalized advice on taking leave by combining an employee emotion recognition engine.

[0232] Collecting employee vacation history data

[0233] The server has the function of collecting employee's past vacation data from the company database, specifically, collecting information such as the date and period of paid vacation taken by each employee.

[0234] Specific behavior:

[0235] The server retrieves data from the company's internal database using SQL queries.

[0236] For example, run the query "SELECT FROM employee_leave WHERE employee_id = 'B789' AND date >= DATE_SUB(CURDATE(), INTERVAL 1 YEAR);".

[0237] This data is stored in a temporary data store (e.g., a memory cache).

[0238] Data Preprocessing

[0239] The server performs pre-processing on the collected data, including missing value imputation and outlier detection and correction.

[0240] Specific behavior:

[0241] The server detects data with missing values ​​and performs the imputation.

[0242] The server detects abnormal values ​​and corrects them to appropriate values.

[0243] Pattern Analysis and Model Generation

[0244] The server loads the generative AI model and feeds the preprocessed data into the model, which learns vacation-taking patterns from historical data.

[0245] Specific behavior:

[0246] The server loads a generative AI model (e.g., a model built with TensorFlow or PyTorch).

[0247] The preprocessed data is fed into the model to learn vacation-taking patterns.

[0248] For example, it learns patterns such as "employees tend to take vacation every three months."

[0249] Collecting and analyzing emotional data

[0250] The server uses an emotion recognition engine to collect emotional data from users (employees). Data sources include emails, chat logs, and voice data.

[0251] Specific behavior:

[0252] The server filters emails and chat logs sent and received during employees' daily work and sends them to an emotion recognition engine.

[0253] Use a speech analysis module (e.g., Google Cloud Speech-to-Text API) to analyze audio data during meetings in real time.

[0254] An emotion recognition engine analyzes this data and assesses the employee's emotional state (e.g., high stress levels).

[0255] Generating Advice

[0256] The server generates optimal vacation advice for each employee based on the analysis results of the generated AI model and emotion recognition engine, taking into account workload data as well.

[0257] Specific behavior:

[0258] The server obtains the latest business data.

[0259] Emotional and business data are fed into a generative AI model to generate personalized vacation advice.

[0260] For example, it generates specific advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[0261] User Notification

[0262] The server then sends the generated advice to the employee's device via email or an internal chat tool.

[0263] Specific behavior:

[0264] The server obtains the employee's email address and uses an SMTP server to send the advice via email.

[0265] For example, you could send an email that reads, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[0266] Similarly, notifications can be sent using internal chat tools (e.g., Slack, Microsoft Teams).

[0267] An example of a prompt sentence for the system of the present invention:

[0268] Employee ID: B789

[0269] Past vacation dates: 2022-11-10, 2023-02-15, 2023-05-20

[0270] Current mood assessment: High stress level

[0271] Workload: High

[0272] This system allows employees to take paid leave in a timely manner, improving the overall working environment.

[0273] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0274] Step 1: Collect employee leave history data

[0275] The server collects employee vacation history data from the company's internal database, including the dates and durations of paid vacation taken by each employee.

[0276] input:

[0277] Employee ID (e.g. B789)

[0278] Data processing and calculation:

[0279] The server executes an SQL query to extract the leave data for the corresponding employee ID. An example query would be "SELECT FROM employee_leave WHERE employee_id = 'B789' AND date >= DATE_SUB(CURDATE(), INTERVAL 1 YEAR);".

[0280] Stores the extracted data in a temporary data store.

[0281] Specific behavior:

[0282] Use an SQL query to retrieve vacation data for the past year corresponding to the employee ID from the database.

[0283] output:

[0284] Data on vacation taken over the past year (e.g., vacation date, duration)

[0285] Step 2: Preprocessing the data

[0286] The server pre-processes the collected leave-taking data, which includes imputing missing values ​​and detecting and correcting outliers.

[0287] input:

[0288] Collected leave taking data

[0289] Data processing and calculation:

[0290] The server detects missing values ​​and imputes them with the mean or median.

[0291] Detect outliers (values ​​significantly exceeding normal holiday periods) and correct them to appropriate values.

[0292] Specific behavior:

[0293] Find data with missing values ​​and impute them with reasonable values.

[0294] Detecting abnormal vacation duration data and correcting these with the average vacation duration.

[0295] output:

[0296] Preprocessed leave taking data

[0297] Step 3: Pattern analysis and model generation

[0298] The server inputs the pre-processed data using a generative AI model to learn leave-taking patterns.

[0299] input:

[0300] Preprocessed leave taking data

[0301] Data processing and calculation:

[0302] The server loads a generative AI model (e.g., a model built with TensorFlow or PyTorch).

[0303] The preprocessed data is fed into the model to learn vacation-taking patterns.

[0304] Specific behavior:

[0305] Load the generative AI model into memory.

[0306] Input data is fed into the model and a learning process is run to analyze vacation-taking trends.

[0307] output:

[0308] Predictive model based on vacation patterns

[0309] Step 4: Collect and analyze sentiment data

[0310] The server uses an emotion recognition engine to collect and analyze the emotion data of users (employees).

[0311] input:

[0312] Emails, chat logs, and voice data

[0313] Data processing and calculation:

[0314] The server collects emails and chat logs and sends them to an emotion recognition engine.

[0315] The voice data is converted into text using a voice analysis module (e.g., Google Cloud Speech-to-Text API) and then analyzed using an emotion recognition engine.

[0316] An emotion recognition engine analyzes the emotional data and assesses the employee's emotional state.

[0317] Specific behavior:

[0318] Filter and collect emails and chat logs during daily work.

[0319] Audio data during meetings is converted into text and analyzed in real time.

[0320] output:

[0321] Employee emotional state (e.g., stress level)

[0322] Step 5: Generating Advice

[0323] The server generates vacation advice for each employee based on the results of the analysis of the predictive model and emotion data, taking into account workload data.

[0324] input:

[0325] Predictive Model

[0326] Emotion data analysis results

[0327] Workload data

[0328] Data processing and calculation:

[0329] The server retrieves the latest business data.

[0330] Feed business and emotional data into a generative AI model to predict when to take vacation.

[0331] Specific behavior:

[0332] Collect workload and project progress data.

[0333] Emotional data and work data are input into an AI model to generate the timing for taking vacation.

[0334] output:

[0335] Vacation advice (e.g., "We recommend that you take paid vacation next Friday, December 8, 2023.")

[0336] Step 6: Notify users

[0337] The server then sends the generated advice to the employee's device via email or an internal chat tool.

[0338] input:

[0339] Generated leave advice

[0340] Employee contact information

[0341] Data processing and calculation:

[0342] The server obtains the employee's email address and sends the email using the SMTP server.

[0343] Advice is shared using internal chat tools (e.g., Slack or Microsoft Teams).

[0344] Specific behavior:

[0345] Capture employee contact information and send notifications via email or chat tools.

[0346] For example, you could send an email stating, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[0347] output:

[0348] Vacation advice displayed on employees' devices

[0349] (Application example 2)

[0350] 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."

[0351] In today's work environment, managing employee stress and encouraging appropriate vacation time are key issues. However, traditional vacation time systems do not take into account employees' emotional states or individual stress levels, making it difficult to ensure that vacation time is taken at the appropriate time. This increases employees' psychological burden and leads to problems with a declining work environment. In response, a new system is needed that utilizes multifaceted information, including emotional data, to improve employee health and efficiency.

[0352] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0353] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the employees of the advice to their terminals, means for collecting and analyzing emotional data in real time, means for assessing the employees' stress levels using the emotional data, and means for optimizing the timing of vacation time based on the stress levels. This enables personalized vacation advice that takes into account the employees' emotional states and stress levels, and encourages them to take vacation time at appropriate times.

[0354] "Employee" refers to an individual who belongs to a company or organization and is engaged in its work.

[0355] "Leave Taken Data" means information regarding the dates, duration and frequency of leave taken by an Employee.

[0356] "Emotional data" refers to information about an employee's emotional state extracted from email, chat, and voice data.

[0357] "Preprocessing" refers to the process of filling in missing values ​​and correcting outliers in collected data.

[0358] "Leave taking patterns" refer to regular or characteristic vacation taking tendencies extracted from employees' past vacation taking data.

[0359] "Predictive model" refers to the algorithm used to learn from past data and predict future leave taking.

[0360] "Vacation Advice" refers to appropriate vacation recommendations for employees that are generated based on the results of predictive models and analysis of sentiment data.

[0361] "Notification" refers to the act of sending the generated vacation advice to an employee's device.

[0362] "Real-time collection" refers to obtaining emotional data instantly while employees are engaged in their activities.

[0363] "Stress level" refers to the degree of psychological stress an employee experiences, assessed based on the analysis of emotional data.

[0364] "Optimization" refers to adjusting employees' vacation timing to make it the most effective based on collected data.

[0365] MODE FOR CARRYING OUT THE INVENTION

[0366] To implement this invention, the system has the following procedures and components: First, the server has a means for collecting employee's past vacation data. This data includes the date and duration of vacation taken by the employee. The server uses SQL queries to collect this data from the company's internal database.

[0367] The server performs preprocessing on the collected data to impute missing values ​​and correct outliers. For example, if there are missing values ​​in the collected data, the server will impute them rationally, and if values ​​that significantly exceed the normal holiday period are detected, they will be corrected.

[0368] The server then analyzes vacation patterns based on the preprocessed data and generates a predictive model. Specifically, the server loads a generative AI model and learns vacation patterns from past data. For example, the server identifies that employees tend to take vacation every three months.

[0369] In addition, emotional data is collected and analyzed. The server uses an emotion engine to collect employee emotional data, retrieving data from emails, chat logs, and voice data. This data is used to evaluate an employee's stress level during their daily work. For example, if recent emails show a tendency toward emotional instability, the system will evaluate the employee's "current stress level is high."

[0370] The server then generates personalized vacation advice based on the analysis results of the generated AI model and emotion engine. This advice also takes workload data into account, allowing for more accurate recommendations. For example, specific advice could be generated such as, "Based on your emotion data, your current stress level is high. We recommend that you take paid vacation next Friday."

[0371] The generated advice is ultimately sent to the employee's device. The server then sends reminders and notifications via email or internal chat tools. For example, the server could obtain an employee's email address and send a notification such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday."

[0372] Examples:

[0373] Assume that employees at a physical store wear smartphones or smart glasses. An application installed on this device collects and analyzes the employee's emotional and work data in real time, and recommends taking time off at the appropriate time. The server collects the employee's past vacation data and analyzes the emotional data using an emotion engine. For example, if the stress level is determined to be high, the server will notify the employee, "We recommend taking time off next Friday."

[0374] Example prompt sentence:

[0375] "Please calculate the recommended date for the next paid vacation based on the vacation data taken by employee ID 'B789' over the past year. Using past data and the employee's emotional data (email, chat, voice) during daily work, if the employee's stress level is high, please suggest the best vacation date in the near future."

[0376] In this way, the system can provide personalized leave advice that takes into account employees' emotional state and stress levels, which will encourage timely leave taking and reduce the psychological burden on employees.

[0377] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0378] Step 1:

[0379] The server collects employee's past vacation data from the company database. Specifically, it uses SQL queries to retrieve information such as vacation dates and durations corresponding to employee IDs, and stores this information in a temporary data store. The input is the employee ID and database connection information, and the output is the vacation data.

[0380] Step 2:

[0381] The server performs preprocessing on the collected vacation data. This preprocessing includes imputing missing values ​​and detecting and correcting outliers. First, if missing values ​​exist, it imputes the most reasonable value. Second, it detects outliers that significantly exceed the normal vacation period and corrects them to an appropriate range. The input is the collected vacation data, and the output is the preprocessed data.

[0382] Step 3:

[0383] The server analyzes vacation-taking patterns based on the preprocessed data and generates a predictive model. To do this, it loads a generative AI model and inputs the preprocessed data into the model. The model learns vacation-taking patterns from the data and outputs a pattern for predicting future vacation taking. The input is the preprocessed data, and the output is the generated predictive model.

[0384] Step 4:

[0385] The server uses an emotion engine to collect employee emotion data. Data is obtained from a variety of sources, including emails, chat logs, and voice data, and analyzed by the emotion engine. Specifically, it collects emails and chat logs sent and received during daily work, as well as voice data during meetings. The input is employee activity data, and the output is analyzed emotion data.

[0386] Step 5:

[0387] The server evaluates the employee's stress level based on the obtained emotional data. Using the analysis results of the emotion engine, the stress level of the employee during daily work is quantified and evaluated. For example, the evaluation may be "Your recent emails show a tendency toward emotional instability." The input is the analyzed emotional data, and the output is the evaluated stress level.

[0388] Step 6:

[0389] The server generates optimal vacation advice for each employee based on the generated AI model and the analysis results of the emotion engine. For example, it generates specific advice such as, "Based on your emotion data, your current stress level is high. We recommend that you take paid vacation next Friday." The input is the prediction model and stress level, and the output is the generated vacation advice.

[0390] Step 7:

[0391] The server notifies the generated advice to the employee's device. Reminders and notifications are sent using email or internal chat tools. For example, an employee's email address can be used to send a message saying, "Based on your emotional data, your current stress level is high. We recommend that you take vacation next Friday." The input is the generated vacation advice and the employee's contact information, and the output is the sent notification.

[0392] These steps enable the system to provide personalized leave advice that takes into account an employee's emotional state and stress level.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Second embodiment]

[0397] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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. 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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."

[0409] The present invention relates to a system for supporting employees in taking paid leave at an appropriate time. This system is implemented in the following manner.

[0410] Collecting employee vacation history data

[0411] The server has a means for collecting employee's past vacation acquisition data from the company's internal database, including information such as the date and duration of each employee's paid vacation.

[0412] Example: The server uses an SQL query to retrieve vacation data for employee ID "B456" for the past year. This data is stored in a temporary data store.

[0413] Data Preprocessing

[0414] The server performs pre-processing on the collected leave-taking data, including imputing missing values ​​and detecting and correcting outliers.

[0415] For example: If the collected data contains missing values, the server will perform reasonable imputation and correct any values ​​that are found to be significantly outside of normal holiday periods.

[0416] Pattern Analysis and Model Generation

[0417] The server uses generation AI to analyze vacation-taking patterns from past vacation-taking data and generate a predictive model.

[0418] Example: The server uses generative AI to identify patterns, such as a tendency to take vacation every three months, based on vacation-taking data. This generates a predictive model.

[0419] Generating Advice

[0420] The server uses the generated predictive model to generate vacation advice for each employee, which is optimized taking into account workload data.

[0421] Example: The server retrieves the latest business data and generates specific advice based on that data, such as "We recommend that you take paid vacation on next Friday, December 8, 2023."

[0422] User Notification

[0423] The server then sends the generated advice to the employee's device via email, internal chat tools, etc.

[0424] Example: The server obtains employee B's email address and sends the generated vacation advice by email, saying, "We recommend that you take paid vacation next Friday, December 8, 2023. There has been a recent peak in workload, so you need to refresh yourself."

[0425] The system of the present invention can be implemented by following the above steps. Using this system makes it easier for employees to take paid leave at appropriate times, reducing stress, improving work efficiency, and creating a healthy working environment.

[0426] The processing flow will be explained below.

[0427] Step 1:

[0428] The server executes an SQL query to collect employee's past vacation data from the company database. For example, for employee ID "B456", retrieve data including vacation dates and duration for the past year. The collected data is stored in a temporary data store.

[0429] Step 2:

[0430] The server performs pre-processing on the collected leave taking data, which specifically includes the following actions:

[0431] Detecting and imputing missing values, for example, inserting reasonable approximations when data are missing for a period.

[0432] Detecting and correcting outliers, for example, correcting periods that significantly exceed normal vacation periods.

[0433] Step 3:

[0434] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[0435] Step 4:

[0436] The server runs additional database queries to retrieve up-to-date workload data, which indicates employee workload and workload levels and is used to inform vacation advice.

[0437] Step 5:

[0438] The server predicts the optimal time to take vacation for each employee based on the trained generative AI model and the latest workload data, generating specific advice such as, "We recommend taking paid vacation on next Friday, December 8, 2023."

[0439] Step 6:

[0440] The server obtains the employee's contact information (e.g., email address) to notify them of the generated vacation advice, constructs a notification message, and sends it to the employee's device.

[0441] Step 7:

[0442] The user (employee) receives a notification from the server and considers taking paid leave at the recommended time. Based on this notification, the user incorporates the leave into their schedule.

[0443] Example 1

[0444] 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."

[0445] Currently, many companies face the problem of employees being unable to take paid leave at the appropriate time. This increases employee stress, reduces work efficiency, and risks health problems. Furthermore, typical systems recommend taking leave without considering individual employees' workloads or past leave-taking patterns, making it difficult to ensure that leave is appropriate for actual work situations. A system that can solve this problem is needed.

[0446] 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.

[0447] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the generated advice to employee terminals, and means for notifying the employees via email or an internal chat tool. This allows employees to take vacation at appropriate times, which is expected to reduce stress and improve work efficiency.

[0448] "Employee's past vacation data" refers to information about the dates and duration of paid vacation taken by an employee in the past.

[0449] "Preprocessing" refers to the process of complementing missing values ​​and correcting outliers in collected data.

[0450] "Vacation patterns" are data patterns that indicate the tendency and frequency of employees taking paid vacation.

[0451] A "predictive model" is a model for predicting future vacation time taken based on past data.

[0452] "Vacation Advice" means advice provided to employees regarding recommended timing for taking vacation based on predictive models.

[0453] "Notification" refers to the act of informing employees of the generated vacation advice.

[0454] "Email" is a communication method for sending text messages over the Internet.

[0455] An "internal chat tool" is a real-time messaging system used for communication between employees within a company.

[0456] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate models.

[0457] "Work volume data" refers to data relating to the volume and progress of an employee's work.

[0458] The present invention relates to a system for supporting employees in taking paid leave at the appropriate time, and this system is implemented using various hardware and software.

[0459] Hardware and Software Configuration

[0460] 1. Server: The server, which is the core of the system, accesses the database and is responsible for the series of processes of collection, analysis, and notification. The server has the computing power to run a high-performance database management system (DBMS) and generative AI models.

[0461] 2. Devices: The devices used by employees are devices that receive the vacation advice sent from the server. These include PCs, tablets, smartphones, etc.

[0462] 3. Network: The Internet or an internal company network is used for communication between the server and the terminal.

[0463] Program processing

[0464] The main program processing in this system is carried out as follows.

[0465] 1. Collect employee vacation history data

[0466] The server collects employee's past vacation data from the company's database, including important information such as the date and duration of vacation.

[0467] 2. Data Preprocessing

[0468] The server performs preprocessing on the collected data, including missing value imputation and outlier detection and correction.

[0469] 3. Pattern Analysis and Model Generation

[0470] The server uses generative AI to analyze vacation-taking patterns from past data and generate a predictive model.

[0471] 4. Generating Advice

[0472] The server generates vacation advice for each employee based on the predictive model, which is optimized by taking into account workload data.

[0473] 5. Notice to Users

[0474] The server then sends the generated advice to employees' devices via email or internal chat tools.

[0475] Specific examples

[0476] For example, the server uses an SQL query to collect vacation data for employee ID "B456" over the past year, analyzes patterns using this data, and then generates advice, such as "We recommend taking paid vacation on next Friday, December 8, 2023," taking into account workload data. This advice is then sent to the employee via email and internal chat tools.

[0477] Prompt Sentence Examples

[0478] Below are some example prompts to input to a generative AI model:

[0479] Analyze leave taking patterns based on the leave taking data for employee ID "B456" over the past year. Next, preprocess this data to correct missing values ​​and outliers. Next, use generative AI to analyze leave taking patterns and generate leave taking advice. Optimize this advice by taking into account the latest workload data. Finally, notify the generated advice to the employee's device.

[0480] As described above, the system of the present invention implements a series of precisely designed processes to enable employees to take paid leave at the optimal timing for them. This system is expected to solve the problem we are aiming for.

[0481] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0482] Step 1: Collect employee leave history data

[0483] The server accesses the company database to collect employee leave history data. The input for this process is parameters such as employee ID and the period of leave. The server runs an SQL query to extract data such as the date and period of leave taken. This data is temporarily stored in a data store. Specifically, the following SQL query is used:

[0484] sql

[0485] SELECT leave_date, leave_duration FROM employee_leave WHERE employee_id = 'B456' AND leave_date >= '2022-01-01';

[0486] The output is the collected leave taking data in a predefined format.

[0487] Step 2: Preprocessing the data

[0488] The server performs preprocessing on the collected data. The input for this process is the raw data collected in step 1. The server performs imputation of missing values ​​and correction of outliers. For example, it imputes missing values ​​with the mean value and detects and corrects outliers. Specifically, it executes the following:

[0489] python

[0490] df['leave_duration'].fillna(df['leave_duration'].mean(), inplace=True)

[0491] if df['leave_duration'].sum() > 30:

[0492] df['leave_duration'] = 30

[0493] The output is pre-processed, clean data.

[0494] Step 3: Pattern analysis and model generation

[0495] The server uses the preprocessed data to analyze leave-taking patterns using a generative AI model and generate a predictive model. The input to this process is the preprocessed data from step 2. The server inputs prompts to the generative AI to identify patterns. For example, the following prompts can be used:

[0496] Analyze the vacation pattern based on the vacation data for employee ID "B456" over the past year.

[0497] The output is the generated leave taking prediction model.

[0498] Step 4: Generating Advice

[0499] The server uses the generated predictive model to generate vacation advice for each employee. The inputs to this process are the predictive model generated in step 3 and the latest workload data. The server considers past patterns and current workload data to suggest specific vacation timings. For example, the server generates advice as follows:

[0500] I recommend taking paid leave next Friday, December 8, 2023. My workload has recently peaked, so I need a break.

[0501] The output is specific vacation advice.

[0502] Step 5: Notify users

[0503] The server notifies the generated advice to the employee's device. The input for this process is the vacation advice generated in step 4 and the employee's contact information. The server sends the notification via email or an internal chat tool. Specifically, it sends an email as follows:

[0504] python

[0505] send_email(to="employeeB@example.com", subject="Vacation Advice", body=advice)

[0506] The output is a notification of the leave advice sent to the employee.

[0507] Through these steps, the system provides employees with advice on how to take paid leave at the appropriate time and efficiently notifies them.

[0508] (Application example 1)

[0509] 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."

[0510] While conventional employee vacation support systems have been effective in optimizing the timing of individual employees' vacations, they have limited functionality for monitoring on-site workers' workloads in real time and providing appropriate vacation advice. Furthermore, they lack the seamless integration required for installing predictive models on work support devices. This has created a need for optimization of the work environment's efficiency and worker health management.

[0511] 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.

[0512] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the generated advice to the employee's terminal, and means for notifying the advice to a work support device and for the device to monitor the workload in real time. This makes it possible to not only optimize the timing of each employee's vacation, but also to propose appropriate vacations that take into account the workload of field workers.

[0513] "Employee's past vacation data" refers to information such as the date, duration, and frequency of paid vacation taken by an employee in the past.

[0514] "Means of collection" refers to the functionality for obtaining and aggregating employee's past vacation data from internal databases and other sources.

[0515] "Preprocessing means" refers to the process of filling in missing values ​​and correcting outliers in the collected data.

[0516] "Means for analyzing vacation-taking patterns and generating predictive models" refers to a function that analyzes vacation-taking trends and patterns based on past vacation-taking data and creates a model that predicts future vacation taking based on that information.

[0517] "Means for generating vacation advice" refers to a function that uses predictive models to suggest optimal vacation dates and durations to employees.

[0518] "Means of notification" refers to the function for sending the generated vacation advice to employees' devices such as smartphones, PCs, and tablets.

[0519] "Work support equipment" refers to devices, including robots and computing units, installed in factories and work sites.

[0520] "Means for monitoring workload in real time" refers to a function for measuring and monitoring the workload and load of on-site workers in real time.

[0521] This invention is a system for supporting employees in taking paid leave at the appropriate time. This system is implemented using the following methods and means.

[0522] The server first collects employee's past vacation data. Specifically, it uses SQL queries to retrieve information such as the dates and periods of paid vacation taken for each employee from the company's database. For example, it retrieves vacation data for employee ID "B456" over the past year and stores it in a temporary data store.

[0523] The server then performs preprocessing on the collected data, including imputing missing values ​​and correcting outliers using Pandas. For example, if the collected data contains missing values, it performs rational imputation and corrects any values ​​that significantly exceed the normal holiday period.

[0524] Based on the preprocessed data, the server uses a generative AI model to analyze vacation-taking patterns and generate a predictive model. Specifically, it uses scikit-learn's Linear Regression to create a model based on past vacation-taking patterns. This model identifies patterns such as "people tend to take vacation every three months."

[0525] Using the generated predictive model, the server generates vacation advice for employees, taking into account workload data to optimize the timing of vacation. For example, it generates specific advice such as "We recommend taking paid vacation on next Friday, December 8, 2023."

[0526] The generated advice is sent by the server to the employee's device (smartphone, tablet, PC, etc.). Notifications are sent via email or internal chat tools. For example, a message is sent to employee B's email address saying, "We recommend that you take paid leave next Friday, December 8, 2023. Your workload has peaked recently, so you need to take a break."

[0527] Furthermore, this system also notifies the work support device of the advice, which has the function of monitoring the workload in real time. This function makes it possible to measure the workload and load of on-site workers in real time and provide appropriate advice on vacation.

[0528] As a specific example, after analyzing the vacation data for employee ID "B456" over the past year, it is predicted that the next vacation recommendation will be on December 8, 2023, and this information is notified to the employee and the work support device.

[0529] Example prompt sentence:

[0530] Based on the vacation data for employee ID "B456" over the past year, please predict the next appropriate vacation date and notify the employee.

[0531] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0532] Step 1:

[0533] The server collects employees' past vacation data. Specifically, it uses an SQL query to filter by employee ID from the company's database and retrieves information such as vacation dates and periods over the course of a year. For example, it collects data for employee ID "B456" and stores it in a temporary data store. The input is the employee ID and the vacation database, and the output is the filtered vacation data.

[0534] Step 2:

[0535] The server performs preprocessing on the collected data. The input data may contain missing values ​​or outliers, so these are imputed and corrected using Pandas. For example, if the data contains missing values, they are imputed with reasonable values, and if an outlier value that significantly exceeds the normal holiday period is detected, it is corrected to an appropriate range. The input is the collected raw data, and the output is preprocessed, clean data.

[0536] Step 3:

[0537] The server analyzes vacation-taking patterns based on the preprocessed data and generates a predictive model using generative AI. Specifically, it uses scikit-learn's Linear Regression to predict when an employee should take their next vacation based on their past vacation data. For example, it identifies a pattern such as "Employee B456 tends to take vacation every three months." The input is the preprocessed data, and the output is the vacation-taking pattern and predictive model.

[0538] Step 4:

[0539] The server uses the generated predictive model to generate vacation advice for employees. It also acquires and takes into account workload data for the current day and future periods. For example, it generates specific advice such as "We recommend that you take paid vacation on next Friday, December 8, 2023." The input is the predictive model and the latest workload data, and the output is the generated vacation advice.

[0540] Step 5:

[0541] The server notifies the employee of the generated vacation advice on their device. The advice is communicated to the employee via email or internal chat tools. For example, a notification may say, "We recommend that you take paid vacation next Friday, December 8, 2023. There has been a recent peak in workload, so you need to take a break." The input is the generated advice and the employee's contact information, and the output is the notification that arrives on the employee's device.

[0542] Step 6:

[0543] The advice is also sent to the work support device, allowing the device to monitor the workload in real time. This makes it possible to measure the workload and load of on-site workers in real time and provide appropriate vacation advice. The input is the generated advice and the on-site work support device, and the output is the device's real-time load data.

[0544] 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.

[0545] The present invention relates to a system for supporting employees in taking paid leave at the appropriate time. This system provides more personalized advice on taking leave by combining an employee emotion recognition engine.

[0546] Collecting employee vacation history data

[0547] The server has a means for collecting employee's past vacation acquisition data from the company's internal database, including information such as the date and duration of each employee's paid vacation.

[0548] Example: The server uses an SQL query to retrieve vacation data for employee ID "B789" for the past year. This data is stored in a temporary data store.

[0549] Data Preprocessing

[0550] The server performs pre-processing on the collected leave-taking data, including imputing missing values ​​and detecting and correcting outliers.

[0551] For example: If the collected data contains missing values, the server will perform reasonable imputation and correct any values ​​that are found to be significantly outside of normal holiday periods.

[0552] Pattern Analysis and Model Generation

[0553] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[0554] Collecting and analyzing emotional data

[0555] The server acquires data from various sources such as emails, chat logs, and voice data to collect user (employee) emotion data using an emotion engine.

[0556] Example: The server uses an emotion engine to analyze emails, chat logs, and audio data from meetings sent and received during employees' daily work to assess their stress levels. For example, the server may produce an evaluation result such as, "Your recent emails show a tendency toward emotional instability."

[0557] Generating Advice

[0558] The server generates optimal vacation advice for each employee based on the analysis results of the generated AI model and emotion engine, and also takes into account workload data to predict more personalized vacation timing.

[0559] Example: Based on the latest work data and emotional data, the server generates specific advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation next Friday, December 8, 2023."

[0560] User Notification

[0561] The server then sends the generated advice to the employee's device via email, internal chat tools, etc.

[0562] Example: The server obtains employee B's email address and sends the generated vacation advice by email, saying, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation on next Friday, December 8, 2023."

[0563] The system of the present invention can be implemented using the above steps. Using this system makes it easier for employees to take paid leave at the appropriate time, reducing stress, improving work efficiency, and creating a healthy working environment. Furthermore, by utilizing emotional data, more accurate advice can be provided, reducing the psychological burden on employees.

[0564] The processing flow will be explained below.

[0565] Step 1:

[0566] The server executes an SQL query to retrieve employee's past vacation data from the company database. For example, for employee ID "B789," retrieve data including vacation dates and durations for the past year. The retrieved data is stored in a temporary data store.

[0567] Step 2:

[0568] The server performs pre-processing on the collected leave taking data, which specifically includes the following actions:

[0569] Detecting and imputing missing values, for example, inserting reasonable approximations when data are missing for a period.

[0570] Detecting and correcting outliers, for example, periods that significantly exceed normal vacation periods.

[0571] Step 3:

[0572] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[0573] Step 4:

[0574] The server uses an emotion engine to collect emotion data from users (employees), including methods for acquiring data from various sources such as email, chat logs, and voice data.

[0575] Example: The server collects messages sent by employee B during his or her daily work from the company's internal email system and chat tools, and passes them to the emotion engine. The emotion engine analyzes the content of the messages and evaluates their stress level.

[0576] Step 5:

[0577] The server uses the emotion engine to analyze the emotional data and identify the user's stress level and emotional state. For example, the analysis may yield results such as, "Your recent messages have been expressing more negative emotions."

[0578] Step 6:

[0579] The server performs additional database queries to obtain up-to-date workload data, which includes information indicating employee workload and workload levels.

[0580] Example: The server retrieves the progress of business tasks and cases for the current month from the database and uses it for analysis.

[0581] Step 7:

[0582] The server predicts the optimal time for each employee to take leave based on the analysis results of the generative AI model and emotion engine, as well as workload data, and generates specific advice.

[0583] Example: The server generates advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation next Friday, December 8, 2023."

[0584] Step 8:

[0585] The server obtains the employee's contact information (e.g., email address) to notify them of the generated vacation advice, constructs a notification message, and sends it to the employee's device.

[0586] Example: The server obtains the email address of employee B and sends the generated vacation advice by email, saying, "Your current stress level is high, so we recommend that you take paid vacation on next Friday, December 8, 2023."

[0587] Step 9:

[0588] The user (employee) receives a notification from the server and considers taking paid leave at the recommended time. Based on this notification, the user incorporates the leave into their schedule.

[0589] Example 2

[0590] 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."

[0591] With traditional paid leave systems, employees must manage when to take their own leave, often resulting in employees being unable to take leave at the appropriate time. Furthermore, they rarely provide advice on taking leave that takes into account employees' emotional state and workload, and do not attempt to reduce stress or improve work efficiency. If this situation continues, it could increase the psychological burden on employees and result in a decline in the quality of their work.

[0592] 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.

[0593] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for collecting and analyzing employee emotion data, means for generating vacation advice for employees using the prediction model and the emotion data, and means for notifying the generated advice to the employee's terminal. This allows employees to take paid vacation at the appropriate time, which is expected to reduce stress and improve work efficiency. Furthermore, by utilizing emotion data, more accurate advice can be provided, reducing the psychological burden on employees.

[0594] "Employee's past vacation data" refers to data including the dates and duration of paid vacation time taken by an employee, as well as other related vacation usage information.

[0595] "Preprocessing" refers to processes such as filling in missing values ​​in collected data, correcting outliers, and formatting data.

[0596] "Vacation patterns" refer to the timing, frequency, and pattern of when a particular employee has taken paid vacation time in the past.

[0597] "Predictive model" refers to a model for predicting future vacation timing based on collected data and the results of its analysis.

[0598] "Emotional data" refers to data that indicates stress levels and emotional states extracted from emails, chat logs, audio data, etc. sent by employees during their daily work.

[0599] An "emotion recognition engine" refers to technology that analyzes collected emotional data and assesses employees' emotional state and stress levels.

[0600] "Vacation advice" refers to advice that suggests appropriate times for employees to take vacation based on collected data and predictive models.

[0601] "Employee devices" refers to devices such as computers, smartphones, and tablets used by employees for work.

[0602] "Workload data" refers to data that shows the status of the work that an employee is responsible for, such as the employee's current workload, project progress, and task list.

[0603] The present invention relates to a system that supports employees in taking paid leave at the appropriate time. This system provides more personalized advice on taking leave by combining an employee emotion recognition engine.

[0604] Collecting employee vacation history data

[0605] The server has the function of collecting employee's past vacation data from the company database, specifically, collecting information such as the date and period of paid vacation taken by each employee.

[0606] Specific behavior:

[0607] The server retrieves data from the company's internal database using SQL queries.

[0608] For example, run the query "SELECT FROM employee_leave WHERE employee_id = 'B789' AND date >= DATE_SUB(CURDATE(), INTERVAL 1 YEAR);".

[0609] This data is stored in a temporary data store (e.g., a memory cache).

[0610] Data Preprocessing

[0611] The server performs pre-processing on the collected data, including missing value imputation and outlier detection and correction.

[0612] Specific behavior:

[0613] The server detects data with missing values ​​and performs the imputation.

[0614] The server detects abnormal values ​​and corrects them to appropriate values.

[0615] Pattern Analysis and Model Generation

[0616] The server loads the generative AI model and feeds the preprocessed data into the model, which learns vacation-taking patterns from historical data.

[0617] Specific behavior:

[0618] The server loads a generative AI model (e.g., a model built with TensorFlow or PyTorch).

[0619] The preprocessed data is fed into the model to learn vacation-taking patterns.

[0620] For example, it learns patterns such as "employees tend to take vacation every three months."

[0621] Collecting and analyzing emotional data

[0622] The server uses an emotion recognition engine to collect emotional data from users (employees). Data sources include emails, chat logs, and voice data.

[0623] Specific behavior:

[0624] The server filters emails and chat logs sent and received during employees' daily work and sends them to an emotion recognition engine.

[0625] Use a speech analysis module (e.g., Google Cloud Speech-to-Text API) to analyze audio data during meetings in real time.

[0626] An emotion recognition engine analyzes this data and assesses the employee's emotional state (e.g., high stress levels).

[0627] Generating Advice

[0628] The server generates optimal vacation advice for each employee based on the analysis results of the generated AI model and emotion recognition engine, taking into account workload data as well.

[0629] Specific behavior:

[0630] The server obtains the latest business data.

[0631] Emotional and business data are fed into a generative AI model to generate personalized vacation advice.

[0632] For example, it generates specific advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[0633] User Notification

[0634] The server then sends the generated advice to the employee's device via email or an internal chat tool.

[0635] Specific behavior:

[0636] The server obtains the employee's email address and uses an SMTP server to send the advice via email.

[0637] For example, you could send an email that reads, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[0638] Similarly, notifications can be sent using internal chat tools (e.g., Slack, Microsoft Teams).

[0639] An example of a prompt sentence for the system of the present invention:

[0640] Employee ID: B789

[0641] Past vacation dates: 2022-11-10, 2023-02-15, 2023-05-20

[0642] Current mood assessment: High stress level

[0643] Workload: High

[0644] This system allows employees to take paid leave in a timely manner, improving the overall working environment.

[0645] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0646] Step 1: Collect employee leave history data

[0647] The server collects employee vacation history data from the company's internal database, including the dates and durations of paid vacation taken by each employee.

[0648] input:

[0649] Employee ID (e.g. B789)

[0650] Data processing and calculation:

[0651] The server executes an SQL query to extract the leave data for the corresponding employee ID. An example query would be "SELECT FROM employee_leave WHERE employee_id = 'B789' AND date >= DATE_SUB(CURDATE(), INTERVAL 1 YEAR);".

[0652] Stores the extracted data in a temporary data store.

[0653] Specific behavior:

[0654] Use an SQL query to retrieve vacation data for the past year corresponding to the employee ID from the database.

[0655] output:

[0656] Data on vacation taken over the past year (e.g., vacation date, duration)

[0657] Step 2: Preprocessing the data

[0658] The server pre-processes the collected leave-taking data, which includes imputing missing values ​​and detecting and correcting outliers.

[0659] input:

[0660] Collected leave taking data

[0661] Data processing and calculation:

[0662] The server detects missing values ​​and imputes them with the mean or median.

[0663] Detect outliers (values ​​significantly exceeding normal holiday periods) and correct them to appropriate values.

[0664] Specific behavior:

[0665] Find data with missing values ​​and impute them with reasonable values.

[0666] Detecting abnormal vacation duration data and correcting these with the average vacation duration.

[0667] output:

[0668] Preprocessed leave taking data

[0669] Step 3: Pattern analysis and model generation

[0670] The server inputs the pre-processed data using a generative AI model to learn leave-taking patterns.

[0671] input:

[0672] Preprocessed leave taking data

[0673] Data processing and calculation:

[0674] The server loads a generative AI model (e.g., a model built with TensorFlow or PyTorch).

[0675] The preprocessed data is fed into the model to learn vacation-taking patterns.

[0676] Specific behavior:

[0677] Load the generative AI model into memory.

[0678] Input data is fed into the model and a learning process is run to analyze vacation-taking trends.

[0679] output:

[0680] Predictive model based on vacation patterns

[0681] Step 4: Collect and analyze sentiment data

[0682] The server uses an emotion recognition engine to collect and analyze the emotion data of users (employees).

[0683] input:

[0684] Emails, chat logs, and voice data

[0685] Data processing and calculation:

[0686] The server collects emails and chat logs and sends them to an emotion recognition engine.

[0687] The voice data is converted into text using a voice analysis module (e.g., Google Cloud Speech-to-Text API) and then analyzed using an emotion recognition engine.

[0688] An emotion recognition engine analyzes the emotional data and assesses the employee's emotional state.

[0689] Specific behavior:

[0690] Filter and collect emails and chat logs during daily work.

[0691] Audio data during meetings is converted into text and analyzed in real time.

[0692] output:

[0693] Employee emotional state (e.g., stress level)

[0694] Step 5: Generating Advice

[0695] The server generates vacation advice for each employee based on the results of the analysis of the predictive model and emotion data, taking into account workload data.

[0696] input:

[0697] Predictive Model

[0698] Emotion data analysis results

[0699] Workload data

[0700] Data processing and calculation:

[0701] The server retrieves the latest business data.

[0702] Feed business and emotional data into a generative AI model to predict when to take vacation.

[0703] Specific behavior:

[0704] Collect workload and project progress data.

[0705] Emotional data and work data are input into an AI model to generate the timing for taking vacation.

[0706] output:

[0707] Vacation advice (e.g., "We recommend that you take paid vacation next Friday, December 8, 2023.")

[0708] Step 6: Notify users

[0709] The server then sends the generated advice to the employee's device via email or an internal chat tool.

[0710] input:

[0711] Generated leave advice

[0712] Employee contact information

[0713] Data processing and calculation:

[0714] The server obtains the employee's email address and sends the email using the SMTP server.

[0715] Advice is shared using internal chat tools (e.g., Slack or Microsoft Teams).

[0716] Specific behavior:

[0717] Capture employee contact information and send notifications via email or chat tools.

[0718] For example, you could send an email stating, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[0719] output:

[0720] Vacation advice displayed on employees' devices

[0721] (Application example 2)

[0722] 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."

[0723] In today's work environment, managing employee stress and encouraging appropriate vacation time are key issues. However, traditional vacation time systems do not take into account employees' emotional states or individual stress levels, making it difficult to ensure that vacation time is taken at the appropriate time. This increases employees' psychological burden and leads to problems with a declining work environment. In response, a new system is needed that utilizes multifaceted information, including emotional data, to improve employee health and efficiency.

[0724] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0725] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the employees of the advice to their terminals, means for collecting and analyzing emotional data in real time, means for assessing the employees' stress levels using the emotional data, and means for optimizing the timing of vacation time based on the stress levels. This enables personalized vacation advice that takes into account the employees' emotional states and stress levels, and encourages them to take vacation time at appropriate times.

[0726] "Employee" refers to an individual who belongs to a company or organization and is engaged in its work.

[0727] "Leave Taken Data" means information regarding the dates, duration and frequency of leave taken by an Employee.

[0728] "Emotional data" refers to information about an employee's emotional state extracted from email, chat, and voice data.

[0729] "Preprocessing" refers to the process of filling in missing values ​​and correcting outliers in collected data.

[0730] "Leave taking patterns" refer to regular or characteristic vacation taking tendencies extracted from employees' past vacation taking data.

[0731] "Predictive model" refers to the algorithm used to learn from past data and predict future leave taking.

[0732] "Vacation Advice" refers to appropriate vacation recommendations for employees that are generated based on the results of predictive models and analysis of sentiment data.

[0733] "Notification" refers to the act of sending the generated vacation advice to an employee's device.

[0734] "Real-time collection" refers to obtaining emotional data instantly while employees are engaged in their activities.

[0735] "Stress level" refers to the degree of psychological stress an employee experiences, assessed based on the analysis of emotional data.

[0736] "Optimization" refers to adjusting employees' vacation timing to make it the most effective based on collected data.

[0737] MODE FOR CARRYING OUT THE INVENTION

[0738] To implement this invention, the system has the following procedures and components: First, the server has a means for collecting employee's past vacation data. This data includes the date and duration of vacation taken by the employee. The server uses SQL queries to collect this data from the company's internal database.

[0739] The server performs preprocessing on the collected data to impute missing values ​​and correct outliers. For example, if there are missing values ​​in the collected data, the server will impute them rationally, and if values ​​that significantly exceed the normal holiday period are detected, they will be corrected.

[0740] The server then analyzes vacation patterns based on the preprocessed data and generates a predictive model. Specifically, the server loads a generative AI model and learns vacation patterns from past data. For example, the server identifies that employees tend to take vacation every three months.

[0741] In addition, emotional data is collected and analyzed. The server uses an emotion engine to collect employee emotional data, retrieving data from emails, chat logs, and voice data. This data is used to evaluate an employee's stress level during their daily work. For example, if recent emails show a tendency toward emotional instability, the system will evaluate the employee's "current stress level is high."

[0742] The server then generates personalized vacation advice based on the analysis results of the generated AI model and emotion engine. This advice also takes workload data into account, allowing for more accurate recommendations. For example, specific advice could be generated such as, "Based on your emotion data, your current stress level is high. We recommend that you take paid vacation next Friday."

[0743] The generated advice is ultimately sent to the employee's device. The server then sends reminders and notifications via email or internal chat tools. For example, the server could obtain an employee's email address and send a notification such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday."

[0744] Examples:

[0745] Assume that employees at a physical store wear smartphones or smart glasses. An application installed on this device collects and analyzes the employee's emotional and work data in real time, and recommends taking time off at the appropriate time. The server collects the employee's past vacation data and analyzes the emotional data using an emotion engine. For example, if the stress level is determined to be high, the server will notify the employee, "We recommend taking time off next Friday."

[0746] Example prompt sentence:

[0747] "Please calculate the recommended date for the next paid vacation based on the vacation data taken by employee ID 'B789' over the past year. Using past data and the employee's emotional data (email, chat, voice) during daily work, if the employee's stress level is high, please suggest the best vacation date in the near future."

[0748] In this way, the system can provide personalized leave advice that takes into account employees' emotional state and stress levels, which will encourage timely leave taking and reduce the psychological burden on employees.

[0749] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0750] Step 1:

[0751] The server collects employee's past vacation data from the company database. Specifically, it uses SQL queries to retrieve information such as vacation dates and durations corresponding to employee IDs, and stores this information in a temporary data store. The input is the employee ID and database connection information, and the output is the vacation data.

[0752] Step 2:

[0753] The server performs preprocessing on the collected vacation data. This preprocessing includes imputing missing values ​​and detecting and correcting outliers. First, if missing values ​​exist, it imputes the most reasonable value. Second, it detects outliers that significantly exceed the normal vacation period and corrects them to an appropriate range. The input is the collected vacation data, and the output is the preprocessed data.

[0754] Step 3:

[0755] The server analyzes vacation-taking patterns based on the preprocessed data and generates a predictive model. To do this, it loads a generative AI model and inputs the preprocessed data into the model. The model learns vacation-taking patterns from the data and outputs a pattern for predicting future vacation taking. The input is the preprocessed data, and the output is the generated predictive model.

[0756] Step 4:

[0757] The server uses an emotion engine to collect employee emotion data. Data is obtained from a variety of sources, including emails, chat logs, and voice data, and analyzed by the emotion engine. Specifically, it collects emails and chat logs sent and received during daily work, as well as voice data during meetings. The input is employee activity data, and the output is analyzed emotion data.

[0758] Step 5:

[0759] The server evaluates the employee's stress level based on the obtained emotional data. Using the analysis results of the emotion engine, the stress level of the employee during daily work is quantified and evaluated. For example, the evaluation may be "Your recent emails show a tendency toward emotional instability." The input is the analyzed emotional data, and the output is the evaluated stress level.

[0760] Step 6:

[0761] The server generates optimal vacation advice for each employee based on the generated AI model and the analysis results of the emotion engine. For example, it generates specific advice such as, "Based on your emotion data, your current stress level is high. We recommend that you take paid vacation next Friday." The input is the prediction model and stress level, and the output is the generated vacation advice.

[0762] Step 7:

[0763] The server notifies the generated advice to the employee's device. Reminders and notifications are sent using email or internal chat tools. For example, an employee's email address can be used to send a message saying, "Based on your emotional data, your current stress level is high. We recommend that you take vacation next Friday." The input is the generated vacation advice and the employee's contact information, and the output is the sent notification.

[0764] These steps enable the system to provide personalized leave advice that takes into account an employee's emotional state and stress level.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] [Third embodiment]

[0769] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0770] 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.

[0771] 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).

[0772] 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.

[0773] 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.

[0774] 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).

[0775] 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. 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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."

[0781] The present invention relates to a system for supporting employees in taking paid leave at an appropriate time. This system is implemented in the following manner.

[0782] Collecting employee vacation history data

[0783] The server has a means for collecting employee's past vacation acquisition data from the company's internal database, including information such as the date and duration of each employee's paid vacation.

[0784] Example: The server uses an SQL query to retrieve vacation data for employee ID "B456" for the past year. This data is stored in a temporary data store.

[0785] Data Preprocessing

[0786] The server performs pre-processing on the collected leave-taking data, including imputing missing values ​​and detecting and correcting outliers.

[0787] For example: If the collected data contains missing values, the server will perform reasonable imputation and correct any values ​​that are found to be significantly outside of normal holiday periods.

[0788] Pattern Analysis and Model Generation

[0789] The server uses generation AI to analyze vacation-taking patterns from past vacation-taking data and generate a predictive model.

[0790] Example: The server uses generative AI to identify patterns, such as a tendency to take vacation every three months, based on vacation-taking data. This generates a predictive model.

[0791] Generating Advice

[0792] The server uses the generated predictive model to generate vacation advice for each employee, which is optimized taking into account workload data.

[0793] Example: The server retrieves the latest business data and generates specific advice based on that data, such as "We recommend that you take paid vacation on next Friday, December 8, 2023."

[0794] User Notification

[0795] The server then sends the generated advice to the employee's device via email, internal chat tools, etc.

[0796] Example: The server obtains employee B's email address and sends the generated vacation advice by email, saying, "We recommend that you take paid vacation next Friday, December 8, 2023. There has been a recent peak in workload, so you need to refresh yourself."

[0797] The system of the present invention can be implemented by following the above steps. Using this system makes it easier for employees to take paid leave at appropriate times, reducing stress, improving work efficiency, and creating a healthy working environment.

[0798] The processing flow will be explained below.

[0799] Step 1:

[0800] The server executes an SQL query to collect employee's past vacation data from the company database. For example, for employee ID "B456", retrieve data including vacation dates and duration for the past year. The collected data is stored in a temporary data store.

[0801] Step 2:

[0802] The server performs pre-processing on the collected leave taking data, which specifically includes the following actions:

[0803] Detecting and imputing missing values, for example, inserting reasonable approximations when data are missing for a period.

[0804] Detecting and correcting outliers, for example, correcting periods that significantly exceed normal vacation periods.

[0805] Step 3:

[0806] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[0807] Step 4:

[0808] The server runs additional database queries to retrieve up-to-date workload data, which indicates employee workload and workload levels and is used to inform vacation advice.

[0809] Step 5:

[0810] The server predicts the optimal time to take vacation for each employee based on the trained generative AI model and the latest workload data, generating specific advice such as, "We recommend taking paid vacation on next Friday, December 8, 2023."

[0811] Step 6:

[0812] The server obtains the employee's contact information (e.g., email address) to notify them of the generated vacation advice, constructs a notification message, and sends it to the employee's device.

[0813] Step 7:

[0814] The user (employee) receives a notification from the server and considers taking paid leave at the recommended time. Based on this notification, the user incorporates the leave into their schedule.

[0815] Example 1

[0816] 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."

[0817] Currently, many companies face the problem of employees being unable to take paid leave at the appropriate time. This increases employee stress, reduces work efficiency, and risks health problems. Furthermore, typical systems recommend taking leave without considering individual employees' workloads or past leave-taking patterns, making it difficult to ensure that leave is appropriate for actual work situations. A system that can solve this problem is needed.

[0818] 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.

[0819] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the generated advice to employee terminals, and means for notifying the employees via email or an internal chat tool. This allows employees to take vacation at appropriate times, which is expected to reduce stress and improve work efficiency.

[0820] "Employee's past vacation data" refers to information about the dates and duration of paid vacation taken by an employee in the past.

[0821] "Preprocessing" refers to the process of complementing missing values ​​and correcting outliers in collected data.

[0822] "Vacation patterns" are data patterns that indicate the tendency and frequency of employees taking paid vacation.

[0823] A "predictive model" is a model for predicting future vacation time taken based on past data.

[0824] "Vacation Advice" means advice provided to employees regarding recommended timing for taking vacation based on predictive models.

[0825] "Notification" refers to the act of informing employees of the generated vacation advice.

[0826] "Email" is a communication method for sending text messages over the Internet.

[0827] An "internal chat tool" is a real-time messaging system used for communication between employees within a company.

[0828] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate models.

[0829] "Work volume data" refers to data relating to the volume and progress of an employee's work.

[0830] The present invention relates to a system for supporting employees in taking paid leave at the appropriate time, and this system is implemented using various hardware and software.

[0831] Hardware and Software Configuration

[0832] 1. Server: The server, which is the core of the system, accesses the database and is responsible for the series of processes of collection, analysis, and notification. The server has the computing power to run a high-performance database management system (DBMS) and generative AI models.

[0833] 2. Devices: The devices used by employees are devices that receive the vacation advice sent from the server. These include PCs, tablets, smartphones, etc.

[0834] 3. Network: The Internet or an internal company network is used for communication between the server and the terminal.

[0835] Program processing

[0836] The main program processing in this system is carried out as follows.

[0837] 1. Collect employee vacation history data

[0838] The server collects employee's past vacation data from the company's database, including important information such as the date and duration of vacation.

[0839] 2. Data Preprocessing

[0840] The server performs preprocessing on the collected data, including missing value imputation and outlier detection and correction.

[0841] 3. Pattern Analysis and Model Generation

[0842] The server uses generative AI to analyze vacation-taking patterns from past data and generate a predictive model.

[0843] 4. Generating Advice

[0844] The server generates vacation advice for each employee based on the predictive model, which is optimized by taking into account workload data.

[0845] 5. Notice to Users

[0846] The server then sends the generated advice to employees' devices via email or internal chat tools.

[0847] Specific examples

[0848] For example, the server uses an SQL query to collect vacation data for employee ID "B456" over the past year, analyzes patterns using this data, and then generates advice, such as "We recommend taking paid vacation on next Friday, December 8, 2023," taking into account workload data. This advice is then sent to the employee via email and internal chat tools.

[0849] Prompt Sentence Examples

[0850] Below are some example prompts to input to a generative AI model:

[0851] Analyze leave taking patterns based on the leave taking data for employee ID "B456" over the past year. Next, preprocess this data to correct missing values ​​and outliers. Next, use generative AI to analyze leave taking patterns and generate leave taking advice. Optimize this advice by taking into account the latest workload data. Finally, notify the generated advice to the employee's device.

[0852] As described above, the system of the present invention implements a series of precisely designed processes to enable employees to take paid leave at the optimal timing for them. This system is expected to solve the problem we are aiming for.

[0853] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0854] Step 1: Collect employee leave history data

[0855] The server accesses the company database to collect employee leave history data. The input for this process is parameters such as employee ID and the period of leave. The server runs an SQL query to extract data such as the date and period of leave taken. This data is temporarily stored in a data store. Specifically, the following SQL query is used:

[0856] sql

[0857] SELECT leave_date, leave_duration FROM employee_leave WHERE employee_id = 'B456' AND leave_date >= '2022-01-01';

[0858] The output is the collected leave taking data in a predefined format.

[0859] Step 2: Preprocessing the data

[0860] The server performs preprocessing on the collected data. The input for this process is the raw data collected in step 1. The server performs imputation of missing values ​​and correction of outliers. For example, it imputes missing values ​​with the mean value and detects and corrects outliers. Specifically, it executes the following:

[0861] python

[0862] df['leave_duration'].fillna(df['leave_duration'].mean(), inplace=True)

[0863] if df['leave_duration'].sum() > 30:

[0864] df['leave_duration'] = 30

[0865] The output is pre-processed, clean data.

[0866] Step 3: Pattern analysis and model generation

[0867] The server uses the preprocessed data to analyze leave-taking patterns using a generative AI model and generate a predictive model. The input to this process is the preprocessed data from step 2. The server inputs prompts to the generative AI to identify patterns. For example, the following prompts can be used:

[0868] Analyze the vacation pattern based on the vacation data for employee ID "B456" over the past year.

[0869] The output is the generated leave taking prediction model.

[0870] Step 4: Generating Advice

[0871] The server uses the generated predictive model to generate vacation advice for each employee. The inputs to this process are the predictive model generated in step 3 and the latest workload data. The server considers past patterns and current workload data to suggest specific vacation timings. For example, the server generates advice as follows:

[0872] I recommend taking paid leave next Friday, December 8, 2023. My workload has recently peaked, so I need a break.

[0873] The output is specific vacation advice.

[0874] Step 5: Notify users

[0875] The server notifies the generated advice to the employee's device. The input for this process is the vacation advice generated in step 4 and the employee's contact information. The server sends the notification via email or an internal chat tool. Specifically, it sends an email as follows:

[0876] python

[0877] send_email(to="employeeB@example.com", subject="Vacation Advice", body=advice)

[0878] The output is a notification of the leave advice sent to the employee.

[0879] Through these steps, the system provides employees with advice on how to take paid leave at the appropriate time and efficiently notifies them.

[0880] (Application example 1)

[0881] 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."

[0882] While conventional employee vacation support systems have been effective in optimizing the timing of individual employees' vacations, they have limited functionality for monitoring on-site workers' workloads in real time and providing appropriate vacation advice. Furthermore, they lack the seamless integration required for installing predictive models on work support devices. This has created a need for optimization of the work environment's efficiency and worker health management.

[0883] 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.

[0884] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the generated advice to the employee's terminal, and means for notifying the advice to a work support device and for the device to monitor the workload in real time. This makes it possible to not only optimize the timing of each employee's vacation, but also to propose appropriate vacations that take into account the workload of field workers.

[0885] "Employee's past vacation data" refers to information such as the date, duration, and frequency of paid vacation taken by an employee in the past.

[0886] "Means of collection" refers to the functionality for obtaining and aggregating employee's past vacation data from internal databases and other sources.

[0887] "Preprocessing means" refers to the process of filling in missing values ​​and correcting outliers in the collected data.

[0888] "Means for analyzing vacation-taking patterns and generating predictive models" refers to a function that analyzes vacation-taking trends and patterns based on past vacation-taking data and creates a model that predicts future vacation taking based on that information.

[0889] "Means for generating vacation advice" refers to a function that uses predictive models to suggest optimal vacation dates and durations to employees.

[0890] "Means of notification" refers to the function for sending the generated vacation advice to employees' devices such as smartphones, PCs, and tablets.

[0891] "Work support equipment" refers to devices, including robots and computing units, installed in factories and work sites.

[0892] "Means for monitoring workload in real time" refers to a function for measuring and monitoring the workload and load of on-site workers in real time.

[0893] This invention is a system for supporting employees in taking paid leave at the appropriate time. This system is implemented using the following methods and means.

[0894] The server first collects employee's past vacation data. Specifically, it uses SQL queries to retrieve information such as the dates and periods of paid vacation taken for each employee from the company's database. For example, it retrieves vacation data for employee ID "B456" over the past year and stores it in a temporary data store.

[0895] The server then performs preprocessing on the collected data, including imputing missing values ​​and correcting outliers using Pandas. For example, if the collected data contains missing values, it performs rational imputation and corrects any values ​​that significantly exceed the normal holiday period.

[0896] Based on the preprocessed data, the server uses a generative AI model to analyze vacation-taking patterns and generate a predictive model. Specifically, it uses scikit-learn's Linear Regression to create a model based on past vacation-taking patterns. This model identifies patterns such as "people tend to take vacation every three months."

[0897] Using the generated predictive model, the server generates vacation advice for employees, taking into account workload data to optimize the timing of vacation. For example, it generates specific advice such as "We recommend taking paid vacation on next Friday, December 8, 2023."

[0898] The generated advice is sent by the server to the employee's device (smartphone, tablet, PC, etc.). Notifications are sent via email or internal chat tools. For example, a message is sent to employee B's email address saying, "We recommend that you take paid leave next Friday, December 8, 2023. Your workload has peaked recently, so you need to take a break."

[0899] Furthermore, this system also notifies the work support device of the advice, which has the function of monitoring the workload in real time. This function makes it possible to measure the workload and load of on-site workers in real time and provide appropriate advice on vacation.

[0900] As a specific example, after analyzing the vacation data for employee ID "B456" over the past year, it is predicted that the next vacation recommendation will be on December 8, 2023, and this information is notified to the employee and the work support device.

[0901] Example prompt sentence:

[0902] Based on the vacation data for employee ID "B456" over the past year, please predict the next appropriate vacation date and notify the employee.

[0903] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0904] Step 1:

[0905] The server collects employees' past vacation data. Specifically, it uses an SQL query to filter by employee ID from the company's database and retrieves information such as vacation dates and periods over the course of a year. For example, it collects data for employee ID "B456" and stores it in a temporary data store. The input is the employee ID and the vacation database, and the output is the filtered vacation data.

[0906] Step 2:

[0907] The server performs preprocessing on the collected data. The input data may contain missing values ​​or outliers, so these are imputed and corrected using Pandas. For example, if the data contains missing values, they are imputed with reasonable values, and if an outlier value that significantly exceeds the normal holiday period is detected, it is corrected to an appropriate range. The input is the collected raw data, and the output is preprocessed, clean data.

[0908] Step 3:

[0909] The server analyzes vacation-taking patterns based on the preprocessed data and generates a predictive model using generative AI. Specifically, it uses scikit-learn's Linear Regression to predict when an employee should take their next vacation based on their past vacation data. For example, it identifies a pattern such as "Employee B456 tends to take vacation every three months." The input is the preprocessed data, and the output is the vacation-taking pattern and predictive model.

[0910] Step 4:

[0911] The server uses the generated predictive model to generate vacation advice for employees. It also acquires and takes into account workload data for the current day and future periods. For example, it generates specific advice such as "We recommend that you take paid vacation on next Friday, December 8, 2023." The input is the predictive model and the latest workload data, and the output is the generated vacation advice.

[0912] Step 5:

[0913] The server notifies the employee of the generated vacation advice on their device. The advice is communicated to the employee via email or internal chat tools. For example, a notification may say, "We recommend that you take paid vacation next Friday, December 8, 2023. There has been a recent peak in workload, so you need to take a break." The input is the generated advice and the employee's contact information, and the output is the notification that arrives on the employee's device.

[0914] Step 6:

[0915] The advice is also sent to the work support device, allowing the device to monitor the workload in real time. This makes it possible to measure the workload and load of on-site workers in real time and provide appropriate vacation advice. The input is the generated advice and the on-site work support device, and the output is the device's real-time load data.

[0916] 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.

[0917] The present invention relates to a system for supporting employees in taking paid leave at the appropriate time. This system provides more personalized advice on taking leave by combining an employee emotion recognition engine.

[0918] Collecting employee vacation history data

[0919] The server has a means for collecting employee's past vacation acquisition data from the company's internal database, including information such as the date and duration of each employee's paid vacation.

[0920] Example: The server uses an SQL query to retrieve vacation data for employee ID "B789" for the past year. This data is stored in a temporary data store.

[0921] Data Preprocessing

[0922] The server performs pre-processing on the collected leave-taking data, including imputing missing values ​​and detecting and correcting outliers.

[0923] For example: If the collected data contains missing values, the server will perform reasonable imputation and correct any values ​​that are found to be significantly outside of normal holiday periods.

[0924] Pattern Analysis and Model Generation

[0925] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[0926] Collecting and analyzing emotional data

[0927] The server acquires data from various sources such as emails, chat logs, and voice data to collect user (employee) emotion data using an emotion engine.

[0928] Example: The server uses an emotion engine to analyze emails, chat logs, and audio data from meetings sent and received during employees' daily work to assess their stress levels. For example, the server may produce an evaluation result such as, "Your recent emails show a tendency toward emotional instability."

[0929] Generating Advice

[0930] The server generates optimal vacation advice for each employee based on the analysis results of the generated AI model and emotion engine, and also takes into account workload data to predict more personalized vacation timing.

[0931] Example: Based on the latest work data and emotional data, the server generates specific advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation next Friday, December 8, 2023."

[0932] User Notification

[0933] The server then sends the generated advice to the employee's device via email, internal chat tools, etc.

[0934] Example: The server obtains employee B's email address and sends the generated vacation advice by email, saying, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation on next Friday, December 8, 2023."

[0935] The system of the present invention can be implemented using the above steps. Using this system makes it easier for employees to take paid leave at the appropriate time, reducing stress, improving work efficiency, and creating a healthy working environment. Furthermore, by utilizing emotional data, more accurate advice can be provided, reducing the psychological burden on employees.

[0936] The processing flow will be explained below.

[0937] Step 1:

[0938] The server executes an SQL query to retrieve employee's past vacation data from the company database. For example, for employee ID "B789," retrieve data including vacation dates and durations for the past year. The retrieved data is stored in a temporary data store.

[0939] Step 2:

[0940] The server performs pre-processing on the collected leave taking data, which specifically includes the following actions:

[0941] Detecting and imputing missing values, for example, inserting reasonable approximations when data are missing for a period.

[0942] Detecting and correcting outliers, for example, periods that significantly exceed normal vacation periods.

[0943] Step 3:

[0944] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[0945] Step 4:

[0946] The server uses an emotion engine to collect emotion data from users (employees), including methods for acquiring data from various sources such as email, chat logs, and voice data.

[0947] Example: The server collects messages sent by employee B during his or her daily work from the company's internal email system and chat tools, and passes them to the emotion engine. The emotion engine analyzes the content of the messages and evaluates their stress level.

[0948] Step 5:

[0949] The server uses the emotion engine to analyze the emotional data and identify the user's stress level and emotional state. For example, the analysis may yield results such as, "Your recent messages have been expressing more negative emotions."

[0950] Step 6:

[0951] The server performs additional database queries to obtain up-to-date workload data, which includes information indicating employee workload and workload levels.

[0952] Example: The server retrieves the progress of business tasks and cases for the current month from the database and uses it for analysis.

[0953] Step 7:

[0954] The server predicts the optimal time for each employee to take leave based on the analysis results of the generative AI model and emotion engine, as well as workload data, and generates specific advice.

[0955] Example: The server generates advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation next Friday, December 8, 2023."

[0956] Step 8:

[0957] The server obtains the employee's contact information (e.g., email address) to notify them of the generated vacation advice, constructs a notification message, and sends it to the employee's device.

[0958] Example: The server obtains the email address of employee B and sends the generated vacation advice by email, saying, "Your current stress level is high, so we recommend that you take paid vacation on next Friday, December 8, 2023."

[0959] Step 9:

[0960] The user (employee) receives a notification from the server and considers taking paid leave at the recommended time. Based on this notification, the user incorporates the leave into their schedule.

[0961] Example 2

[0962] 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."

[0963] With traditional paid leave systems, employees must manage when to take their own leave, often resulting in employees being unable to take leave at the appropriate time. Furthermore, they rarely provide advice on taking leave that takes into account employees' emotional state and workload, and do not attempt to reduce stress or improve work efficiency. If this situation continues, it could increase the psychological burden on employees and result in a decline in the quality of their work.

[0964] 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.

[0965] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for collecting and analyzing employee emotion data, means for generating vacation advice for employees using the prediction model and the emotion data, and means for notifying the generated advice to the employee's terminal. This allows employees to take paid vacation at the appropriate time, which is expected to reduce stress and improve work efficiency. Furthermore, by utilizing emotion data, more accurate advice can be provided, reducing the psychological burden on employees.

[0966] "Employee's past vacation data" refers to data including the dates and duration of paid vacation time taken by an employee, as well as other related vacation usage information.

[0967] "Preprocessing" refers to processes such as filling in missing values ​​in collected data, correcting outliers, and formatting data.

[0968] "Vacation patterns" refer to the timing, frequency, and pattern of when a particular employee has taken paid vacation time in the past.

[0969] "Predictive model" refers to a model for predicting future vacation timing based on collected data and the results of its analysis.

[0970] "Emotional data" refers to data that indicates stress levels and emotional states extracted from emails, chat logs, audio data, etc. sent by employees during their daily work.

[0971] An "emotion recognition engine" refers to technology that analyzes collected emotional data and assesses employees' emotional state and stress levels.

[0972] "Vacation advice" refers to advice that suggests appropriate times for employees to take vacation based on collected data and predictive models.

[0973] "Employee devices" refers to devices such as computers, smartphones, and tablets used by employees for work.

[0974] "Workload data" refers to data that shows the status of the work that an employee is responsible for, such as the employee's current workload, project progress, and task list.

[0975] The present invention relates to a system that supports employees in taking paid leave at the appropriate time. This system provides more personalized advice on taking leave by combining an employee emotion recognition engine.

[0976] Collecting employee vacation history data

[0977] The server has the function of collecting employee's past vacation data from the company database, specifically, collecting information such as the date and period of paid vacation taken by each employee.

[0978] Specific behavior:

[0979] The server retrieves data from the company's internal database using SQL queries.

[0980] For example, run the query "SELECT FROM employee_leave WHERE employee_id = 'B789' AND date >= DATE_SUB(CURDATE(), INTERVAL 1 YEAR);".

[0981] This data is stored in a temporary data store (e.g., a memory cache).

[0982] Data Preprocessing

[0983] The server performs pre-processing on the collected data, including missing value imputation and outlier detection and correction.

[0984] Specific behavior:

[0985] The server detects data with missing values ​​and performs the imputation.

[0986] The server detects abnormal values ​​and corrects them to appropriate values.

[0987] Pattern Analysis and Model Generation

[0988] The server loads the generative AI model and feeds the preprocessed data into the model, which learns vacation-taking patterns from historical data.

[0989] Specific behavior:

[0990] The server loads a generative AI model (e.g., a model built with TensorFlow or PyTorch).

[0991] The preprocessed data is fed into the model to learn vacation-taking patterns.

[0992] For example, it learns patterns such as "employees tend to take vacation every three months."

[0993] Collecting and analyzing emotional data

[0994] The server uses an emotion recognition engine to collect emotional data from users (employees). Data sources include emails, chat logs, and voice data.

[0995] Specific behavior:

[0996] The server filters emails and chat logs sent and received during employees' daily work and sends them to an emotion recognition engine.

[0997] Use a speech analysis module (e.g., Google Cloud Speech-to-Text API) to analyze audio data during meetings in real time.

[0998] An emotion recognition engine analyzes this data and assesses the employee's emotional state (e.g., high stress levels).

[0999] Generating Advice

[1000] The server generates optimal vacation advice for each employee based on the analysis results of the generated AI model and emotion recognition engine, taking into account workload data as well.

[1001] Specific behavior:

[1002] The server obtains the latest business data.

[1003] Emotional and business data are fed into a generative AI model to generate personalized vacation advice.

[1004] For example, it generates specific advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[1005] User Notification

[1006] The server then sends the generated advice to the employee's device via email or an internal chat tool.

[1007] Specific behavior:

[1008] The server obtains the employee's email address and uses an SMTP server to send the advice via email.

[1009] For example, you could send an email that reads, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[1010] Similarly, notifications can be sent using internal chat tools (e.g., Slack, Microsoft Teams).

[1011] An example of a prompt sentence for the system of the present invention:

[1012] Employee ID: B789

[1013] Past vacation dates: 2022-11-10, 2023-02-15, 2023-05-20

[1014] Current mood assessment: High stress level

[1015] Workload: High

[1016] This system allows employees to take paid leave in a timely manner, improving the overall working environment.

[1017] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1018] Step 1: Collect employee leave history data

[1019] The server collects employee vacation history data from the company's internal database, including the dates and durations of paid vacation taken by each employee.

[1020] input:

[1021] Employee ID (e.g. B789)

[1022] Data processing and calculation:

[1023] The server executes an SQL query to extract the leave data for the corresponding employee ID. An example query would be "SELECT FROM employee_leave WHERE employee_id = 'B789' AND date >= DATE_SUB(CURDATE(), INTERVAL 1 YEAR);".

[1024] Stores the extracted data in a temporary data store.

[1025] Specific behavior:

[1026] Use an SQL query to retrieve vacation data for the past year corresponding to the employee ID from the database.

[1027] output:

[1028] Data on vacation taken over the past year (e.g., vacation date, duration)

[1029] Step 2: Preprocessing the data

[1030] The server pre-processes the collected leave-taking data, which includes imputing missing values ​​and detecting and correcting outliers.

[1031] input:

[1032] Collected leave taking data

[1033] Data processing and calculation:

[1034] The server detects missing values ​​and imputes them with the mean or median.

[1035] Detect outliers (values ​​significantly exceeding normal holiday periods) and correct them to appropriate values.

[1036] Specific behavior:

[1037] Find data with missing values ​​and impute them with reasonable values.

[1038] Detecting abnormal vacation duration data and correcting these with the average vacation duration.

[1039] output:

[1040] Preprocessed leave taking data

[1041] Step 3: Pattern analysis and model generation

[1042] The server inputs the pre-processed data using a generative AI model to learn leave-taking patterns.

[1043] input:

[1044] Preprocessed leave taking data

[1045] Data processing and calculation:

[1046] The server loads a generative AI model (e.g., a model built with TensorFlow or PyTorch).

[1047] The preprocessed data is fed into the model to learn vacation-taking patterns.

[1048] Specific behavior:

[1049] Load the generative AI model into memory.

[1050] Input data is fed into the model and a learning process is run to analyze vacation-taking trends.

[1051] output:

[1052] Predictive model based on vacation patterns

[1053] Step 4: Collect and analyze sentiment data

[1054] The server uses an emotion recognition engine to collect and analyze the emotion data of users (employees).

[1055] input:

[1056] Emails, chat logs, and voice data

[1057] Data processing and calculation:

[1058] The server collects emails and chat logs and sends them to an emotion recognition engine.

[1059] The voice data is converted into text using a voice analysis module (e.g., Google Cloud Speech-to-Text API) and then analyzed using an emotion recognition engine.

[1060] An emotion recognition engine analyzes the emotional data and assesses the employee's emotional state.

[1061] Specific behavior:

[1062] Filter and collect emails and chat logs during daily work.

[1063] Audio data during meetings is converted into text and analyzed in real time.

[1064] output:

[1065] Employee emotional state (e.g., stress level)

[1066] Step 5: Generating Advice

[1067] The server generates vacation advice for each employee based on the results of the analysis of the predictive model and emotion data, taking into account workload data.

[1068] input:

[1069] Predictive Model

[1070] Emotion data analysis results

[1071] Workload data

[1072] Data processing and calculation:

[1073] The server retrieves the latest business data.

[1074] Feed business and emotional data into a generative AI model to predict when to take vacation.

[1075] Specific behavior:

[1076] Collect workload and project progress data.

[1077] Emotional data and work data are input into an AI model to generate the timing for taking vacation.

[1078] output:

[1079] Vacation advice (e.g., "We recommend that you take paid vacation next Friday, December 8, 2023.")

[1080] Step 6: Notify users

[1081] The server then sends the generated advice to the employee's device via email or an internal chat tool.

[1082] input:

[1083] Generated leave advice

[1084] Employee contact information

[1085] Data processing and calculation:

[1086] The server obtains the employee's email address and sends the email using the SMTP server.

[1087] Advice is shared using internal chat tools (e.g., Slack or Microsoft Teams).

[1088] Specific behavior:

[1089] Capture employee contact information and send notifications via email or chat tools.

[1090] For example, you could send an email stating, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[1091] output:

[1092] Vacation advice displayed on employees' devices

[1093] (Application example 2)

[1094] 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."

[1095] In today's work environment, managing employee stress and encouraging appropriate vacation time are key issues. However, traditional vacation time systems do not take into account employees' emotional states or individual stress levels, making it difficult to ensure that vacation time is taken at the appropriate time. This increases employees' psychological burden and leads to problems with a declining work environment. In response, a new system is needed that utilizes multifaceted information, including emotional data, to improve employee health and efficiency.

[1096] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1097] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the employees of the advice to their terminals, means for collecting and analyzing emotional data in real time, means for assessing the employees' stress levels using the emotional data, and means for optimizing the timing of vacation time based on the stress levels. This enables personalized vacation advice that takes into account the employees' emotional states and stress levels, and encourages them to take vacation time at appropriate times.

[1098] "Employee" refers to an individual who belongs to a company or organization and is engaged in its work.

[1099] "Leave Taken Data" means information regarding the dates, duration and frequency of leave taken by an Employee.

[1100] "Emotional data" refers to information about an employee's emotional state extracted from email, chat, and voice data.

[1101] "Preprocessing" refers to the process of filling in missing values ​​and correcting outliers in collected data.

[1102] "Leave taking patterns" refer to regular or characteristic vacation taking tendencies extracted from employees' past vacation taking data.

[1103] "Predictive model" refers to the algorithm used to learn from past data and predict future leave taking.

[1104] "Vacation Advice" refers to appropriate vacation recommendations for employees that are generated based on the results of predictive models and analysis of sentiment data.

[1105] "Notification" refers to the act of sending the generated vacation advice to an employee's device.

[1106] "Real-time collection" refers to obtaining emotional data instantly while employees are engaged in their activities.

[1107] "Stress level" refers to the degree of psychological stress an employee experiences, assessed based on the analysis of emotional data.

[1108] "Optimization" refers to adjusting employees' vacation timing to make it the most effective based on collected data.

[1109] MODE FOR CARRYING OUT THE INVENTION

[1110] To implement this invention, the system has the following procedures and components: First, the server has a means for collecting employee's past vacation data. This data includes the date and duration of vacation taken by the employee. The server uses SQL queries to collect this data from the company's internal database.

[1111] The server performs preprocessing on the collected data to impute missing values ​​and correct outliers. For example, if there are missing values ​​in the collected data, the server will impute them rationally, and if values ​​that significantly exceed the normal holiday period are detected, they will be corrected.

[1112] The server then analyzes vacation patterns based on the preprocessed data and generates a predictive model. Specifically, the server loads a generative AI model and learns vacation patterns from past data. For example, the server identifies that employees tend to take vacation every three months.

[1113] In addition, emotional data is collected and analyzed. The server uses an emotion engine to collect employee emotional data, retrieving data from emails, chat logs, and voice data. This data is used to evaluate an employee's stress level during their daily work. For example, if recent emails show a tendency toward emotional instability, the system will evaluate the employee's "current stress level is high."

[1114] The server then generates personalized vacation advice based on the analysis results of the generated AI model and emotion engine. This advice also takes workload data into account, allowing for more accurate recommendations. For example, specific advice could be generated such as, "Based on your emotion data, your current stress level is high. We recommend that you take paid vacation next Friday."

[1115] The generated advice is ultimately sent to the employee's device. The server then sends reminders and notifications via email or internal chat tools. For example, the server could obtain an employee's email address and send a notification such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday."

[1116] Examples:

[1117] Assume that employees at a physical store wear smartphones or smart glasses. An application installed on this device collects and analyzes the employee's emotional and work data in real time, and recommends taking time off at the appropriate time. The server collects the employee's past vacation data and analyzes the emotional data using an emotion engine. For example, if the stress level is determined to be high, the server will notify the employee, "We recommend taking time off next Friday."

[1118] Example prompt sentence:

[1119] "Please calculate the recommended date for the next paid vacation based on the vacation data taken by employee ID 'B789' over the past year. Using past data and the employee's emotional data (email, chat, voice) during daily work, if the employee's stress level is high, please suggest the best vacation date in the near future."

[1120] In this way, the system can provide personalized leave advice that takes into account employees' emotional state and stress levels, which will encourage timely leave taking and reduce the psychological burden on employees.

[1121] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1122] Step 1:

[1123] The server collects employee's past vacation data from the company database. Specifically, it uses SQL queries to retrieve information such as vacation dates and durations corresponding to employee IDs, and stores this information in a temporary data store. The input is the employee ID and database connection information, and the output is the vacation data.

[1124] Step 2:

[1125] The server performs preprocessing on the collected vacation data. This preprocessing includes imputing missing values ​​and detecting and correcting outliers. First, if missing values ​​exist, it imputes the most reasonable value. Second, it detects outliers that significantly exceed the normal vacation period and corrects them to an appropriate range. The input is the collected vacation data, and the output is the preprocessed data.

[1126] Step 3:

[1127] The server analyzes vacation-taking patterns based on the preprocessed data and generates a predictive model. To do this, it loads a generative AI model and inputs the preprocessed data into the model. The model learns vacation-taking patterns from the data and outputs a pattern for predicting future vacation taking. The input is the preprocessed data, and the output is the generated predictive model.

[1128] Step 4:

[1129] The server uses an emotion engine to collect employee emotion data. Data is obtained from a variety of sources, including emails, chat logs, and voice data, and analyzed by the emotion engine. Specifically, it collects emails and chat logs sent and received during daily work, as well as voice data during meetings. The input is employee activity data, and the output is analyzed emotion data.

[1130] Step 5:

[1131] The server evaluates the employee's stress level based on the obtained emotional data. Using the analysis results of the emotion engine, the stress level of the employee during daily work is quantified and evaluated. For example, the evaluation may be "Your recent emails show a tendency toward emotional instability." The input is the analyzed emotional data, and the output is the evaluated stress level.

[1132] Step 6:

[1133] The server generates optimal vacation advice for each employee based on the generated AI model and the analysis results of the emotion engine. For example, it generates specific advice such as, "Based on your emotion data, your current stress level is high. We recommend that you take paid vacation next Friday." The input is the prediction model and stress level, and the output is the generated vacation advice.

[1134] Step 7:

[1135] The server notifies the generated advice to the employee's device. Reminders and notifications are sent using email or internal chat tools. For example, an employee's email address can be used to send a message saying, "Based on your emotional data, your current stress level is high. We recommend that you take vacation next Friday." The input is the generated vacation advice and the employee's contact information, and the output is the sent notification.

[1136] These steps enable the system to provide personalized leave advice that takes into account an employee's emotional state and stress level.

[1137] 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.

[1138] 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.

[1139] 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.

[1140] [Fourth embodiment]

[1141] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1142] 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.

[1143] 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).

[1144] 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.

[1145] 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.

[1146] 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).

[1147] 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. 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.

[1148] 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.

[1149] 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.

[1150] 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.

[1151] 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.

[1152] 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.

[1153] 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."

[1154] The present invention relates to a system for supporting employees in taking paid leave at an appropriate time. This system is implemented in the following manner.

[1155] Collecting employee vacation history data

[1156] The server has a means for collecting employee's past vacation acquisition data from the company's internal database, including information such as the date and duration of each employee's paid vacation.

[1157] Example: The server uses an SQL query to retrieve vacation data for employee ID "B456" for the past year. This data is stored in a temporary data store.

[1158] Data Preprocessing

[1159] The server performs pre-processing on the collected leave-taking data, including imputing missing values ​​and detecting and correcting outliers.

[1160] For example: If the collected data contains missing values, the server will perform reasonable imputation and correct any values ​​that are found to be significantly outside of normal holiday periods.

[1161] Pattern Analysis and Model Generation

[1162] The server uses generation AI to analyze vacation-taking patterns from past vacation-taking data and generate a predictive model.

[1163] Example: The server uses generative AI to identify patterns, such as a tendency to take vacation every three months, based on vacation-taking data. This generates a predictive model.

[1164] Generating Advice

[1165] The server uses the generated predictive model to generate vacation advice for each employee, which is optimized taking into account workload data.

[1166] Example: The server retrieves the latest business data and generates specific advice based on that data, such as "We recommend that you take paid vacation on next Friday, December 8, 2023."

[1167] User Notification

[1168] The server then sends the generated advice to the employee's device via email, internal chat tools, etc.

[1169] Example: The server obtains employee B's email address and sends the generated vacation advice by email, saying, "We recommend that you take paid vacation next Friday, December 8, 2023. There has been a recent peak in workload, so you need to refresh yourself."

[1170] The system of the present invention can be implemented by following the above steps. Using this system makes it easier for employees to take paid leave at appropriate times, reducing stress, improving work efficiency, and creating a healthy working environment.

[1171] The processing flow will be explained below.

[1172] Step 1:

[1173] The server executes an SQL query to collect employee's past vacation data from the company database. For example, for employee ID "B456", retrieve data including vacation dates and duration for the past year. The collected data is stored in a temporary data store.

[1174] Step 2:

[1175] The server performs pre-processing on the collected leave taking data, which specifically includes the following actions:

[1176] Detecting and imputing missing values, for example, inserting reasonable approximations when data are missing for a period.

[1177] Detecting and correcting outliers, for example, correcting periods that significantly exceed normal vacation periods.

[1178] Step 3:

[1179] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[1180] Step 4:

[1181] The server runs additional database queries to retrieve up-to-date workload data, which indicates employee workload and workload levels and is used to inform vacation advice.

[1182] Step 5:

[1183] The server predicts the optimal time to take vacation for each employee based on the trained generative AI model and the latest workload data, generating specific advice such as, "We recommend taking paid vacation on next Friday, December 8, 2023."

[1184] Step 6:

[1185] The server obtains the employee's contact information (e.g., email address) to notify them of the generated vacation advice, constructs a notification message, and sends it to the employee's device.

[1186] Step 7:

[1187] The user (employee) receives a notification from the server and considers taking paid leave at the recommended time. Based on this notification, the user incorporates the leave into their schedule.

[1188] Example 1

[1189] 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."

[1190] Currently, many companies face the problem of employees being unable to take paid leave at the appropriate time. This increases employee stress, reduces work efficiency, and risks health problems. Furthermore, typical systems recommend taking leave without considering individual employees' workloads or past leave-taking patterns, making it difficult to ensure that leave is appropriate for actual work situations. A system that can solve this problem is needed.

[1191] 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.

[1192] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the generated advice to employee terminals, and means for notifying the employees via email or an internal chat tool. This allows employees to take vacation at appropriate times, which is expected to reduce stress and improve work efficiency.

[1193] "Employee's past vacation data" refers to information about the dates and duration of paid vacation taken by an employee in the past.

[1194] "Preprocessing" refers to the process of complementing missing values ​​and correcting outliers in collected data.

[1195] "Vacation patterns" are data patterns that indicate the tendency and frequency of employees taking paid vacation.

[1196] A "predictive model" is a model for predicting future vacation time taken based on past data.

[1197] "Vacation Advice" means advice provided to employees regarding recommended timing for taking vacation based on predictive models.

[1198] "Notification" refers to the act of informing employees of the generated vacation advice.

[1199] "Email" is a communication method for sending text messages over the Internet.

[1200] An "internal chat tool" is a real-time messaging system used for communication between employees within a company.

[1201] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate models.

[1202] "Work volume data" refers to data relating to the volume and progress of an employee's work.

[1203] The present invention relates to a system for supporting employees in taking paid leave at the appropriate time, and this system is implemented using various hardware and software.

[1204] Hardware and Software Configuration

[1205] 1. Server: The server, which is the core of the system, accesses the database and is responsible for the series of processes of collection, analysis, and notification. The server has the computing power to run a high-performance database management system (DBMS) and generative AI models.

[1206] 2. Devices: The devices used by employees are devices that receive the vacation advice sent from the server. These include PCs, tablets, smartphones, etc.

[1207] 3. Network: The Internet or an internal company network is used for communication between the server and the terminal.

[1208] Program processing

[1209] The main program processing in this system is carried out as follows.

[1210] 1. Collect employee vacation history data

[1211] The server collects employee's past vacation data from the company's database, including important information such as the date and duration of vacation.

[1212] 2. Data Preprocessing

[1213] The server performs preprocessing on the collected data, including missing value imputation and outlier detection and correction.

[1214] 3. Pattern Analysis and Model Generation

[1215] The server uses generative AI to analyze vacation-taking patterns from past data and generate a predictive model.

[1216] 4. Generating Advice

[1217] The server generates vacation advice for each employee based on the predictive model, which is optimized by taking into account workload data.

[1218] 5. Notice to Users

[1219] The server then sends the generated advice to employees' devices via email or internal chat tools.

[1220] Specific examples

[1221] For example, the server uses an SQL query to collect vacation data for employee ID "B456" over the past year, analyzes patterns using this data, and then generates advice, such as "We recommend taking paid vacation on next Friday, December 8, 2023," taking into account workload data. This advice is then sent to the employee via email and internal chat tools.

[1222] Prompt Sentence Examples

[1223] Below are some example prompts to input to a generative AI model:

[1224] Analyze leave taking patterns based on the leave taking data for employee ID "B456" over the past year. Next, preprocess this data to correct missing values ​​and outliers. Next, use generative AI to analyze leave taking patterns and generate leave taking advice. Optimize this advice by taking into account the latest workload data. Finally, notify the generated advice to the employee's device.

[1225] As described above, the system of the present invention implements a series of precisely designed processes to enable employees to take paid leave at the optimal timing for them. This system is expected to solve the problem we are aiming for.

[1226] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1227] Step 1: Collect employee leave history data

[1228] The server accesses the company database to collect employee leave history data. The input for this process is parameters such as employee ID and the period of leave. The server runs an SQL query to extract data such as the date and period of leave taken. This data is temporarily stored in a data store. Specifically, the following SQL query is used:

[1229] sql

[1230] SELECT leave_date, leave_duration FROM employee_leave WHERE employee_id = 'B456' AND leave_date >= '2022-01-01';

[1231] The output is the collected leave taking data in a predefined format.

[1232] Step 2: Preprocessing the data

[1233] The server performs preprocessing on the collected data. The input for this process is the raw data collected in step 1. The server performs imputation of missing values ​​and correction of outliers. For example, it imputes missing values ​​with the mean value and detects and corrects outliers. Specifically, it executes the following:

[1234] python

[1235] df['leave_duration'].fillna(df['leave_duration'].mean(), inplace=True)

[1236] if df['leave_duration'].sum() > 30:

[1237] df['leave_duration'] = 30

[1238] The output is pre-processed, clean data.

[1239] Step 3: Pattern analysis and model generation

[1240] The server uses the preprocessed data to analyze leave-taking patterns using a generative AI model and generate a predictive model. The input to this process is the preprocessed data from step 2. The server inputs prompts to the generative AI to identify patterns. For example, the following prompts can be used:

[1241] Analyze the vacation pattern based on the vacation data for employee ID "B456" over the past year.

[1242] The output is the generated leave taking prediction model.

[1243] Step 4: Generating Advice

[1244] The server uses the generated predictive model to generate vacation advice for each employee. The inputs to this process are the predictive model generated in step 3 and the latest workload data. The server considers past patterns and current workload data to suggest specific vacation timings. For example, the server generates advice as follows:

[1245] I recommend taking paid leave next Friday, December 8, 2023. My workload has recently peaked, so I need a break.

[1246] The output is specific vacation advice.

[1247] Step 5: Notify users

[1248] The server notifies the generated advice to the employee's device. The input for this process is the vacation advice generated in step 4 and the employee's contact information. The server sends the notification via email or an internal chat tool. Specifically, it sends an email as follows:

[1249] python

[1250] send_email(to="employeeB@example.com", subject="Vacation Advice", body=advice)

[1251] The output is a notification of the leave advice sent to the employee.

[1252] Through these steps, the system provides employees with advice on how to take paid leave at the appropriate time and efficiently notifies them.

[1253] (Application example 1)

[1254] 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."

[1255] While conventional employee vacation support systems have been effective in optimizing the timing of individual employees' vacations, they have limited functionality for monitoring on-site workers' workloads in real time and providing appropriate vacation advice. Furthermore, they lack the seamless integration required for installing predictive models on work support devices. This has created a need for optimization of the work environment's efficiency and worker health management.

[1256] 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.

[1257] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the generated advice to the employee's terminal, and means for notifying the advice to a work support device and for the device to monitor the workload in real time. This makes it possible to not only optimize the timing of each employee's vacation, but also to propose appropriate vacations that take into account the workload of field workers.

[1258] "Employee's past vacation data" refers to information such as the date, duration, and frequency of paid vacation taken by an employee in the past.

[1259] "Means of collection" refers to the functionality for obtaining and aggregating employee's past vacation data from internal databases and other sources.

[1260] "Preprocessing means" refers to the process of filling in missing values ​​and correcting outliers in the collected data.

[1261] "Means for analyzing vacation-taking patterns and generating predictive models" refers to a function that analyzes vacation-taking trends and patterns based on past vacation-taking data and creates a model that predicts future vacation taking based on that information.

[1262] "Means for generating vacation advice" refers to a function that uses predictive models to suggest optimal vacation dates and durations to employees.

[1263] "Means of notification" refers to the function for sending the generated vacation advice to employees' devices such as smartphones, PCs, and tablets.

[1264] "Work support equipment" refers to devices, including robots and computing units, installed in factories and work sites.

[1265] "Means for monitoring workload in real time" refers to a function for measuring and monitoring the workload and load of on-site workers in real time.

[1266] This invention is a system for supporting employees in taking paid leave at the appropriate time. This system is implemented using the following methods and means.

[1267] The server first collects employee's past vacation data. Specifically, it uses SQL queries to retrieve information such as the dates and periods of paid vacation taken for each employee from the company's database. For example, it retrieves vacation data for employee ID "B456" over the past year and stores it in a temporary data store.

[1268] The server then performs preprocessing on the collected data, including imputing missing values ​​and correcting outliers using Pandas. For example, if the collected data contains missing values, it performs rational imputation and corrects any values ​​that significantly exceed the normal holiday period.

[1269] Based on the preprocessed data, the server uses a generative AI model to analyze vacation-taking patterns and generate a predictive model. Specifically, it uses scikit-learn's Linear Regression to create a model based on past vacation-taking patterns. This model identifies patterns such as "people tend to take vacation every three months."

[1270] Using the generated predictive model, the server generates vacation advice for employees, taking into account workload data to optimize the timing of vacation. For example, it generates specific advice such as "We recommend taking paid vacation on next Friday, December 8, 2023."

[1271] The generated advice is sent by the server to the employee's device (smartphone, tablet, PC, etc.). Notifications are sent via email or internal chat tools. For example, a message is sent to employee B's email address saying, "We recommend that you take paid leave next Friday, December 8, 2023. Your workload has peaked recently, so you need to take a break."

[1272] Furthermore, this system also notifies the work support device of the advice, which has the function of monitoring the workload in real time. This function makes it possible to measure the workload and load of on-site workers in real time and provide appropriate advice on vacation.

[1273] As a specific example, after analyzing the vacation data for employee ID "B456" over the past year, it is predicted that the next vacation recommendation will be on December 8, 2023, and this information is notified to the employee and the work support device.

[1274] Example prompt sentence:

[1275] Based on the vacation data for employee ID "B456" over the past year, please predict the next appropriate vacation date and notify the employee.

[1276] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1277] Step 1:

[1278] The server collects employees' past vacation data. Specifically, it uses an SQL query to filter by employee ID from the company's database and retrieves information such as vacation dates and periods over the course of a year. For example, it collects data for employee ID "B456" and stores it in a temporary data store. The input is the employee ID and the vacation database, and the output is the filtered vacation data.

[1279] Step 2:

[1280] The server performs preprocessing on the collected data. The input data may contain missing values ​​or outliers, so these are imputed and corrected using Pandas. For example, if the data contains missing values, they are imputed with reasonable values, and if an outlier value that significantly exceeds the normal holiday period is detected, it is corrected to an appropriate range. The input is the collected raw data, and the output is preprocessed, clean data.

[1281] Step 3:

[1282] The server analyzes vacation-taking patterns based on the preprocessed data and generates a predictive model using generative AI. Specifically, it uses scikit-learn's Linear Regression to predict when an employee should take their next vacation based on their past vacation data. For example, it identifies a pattern such as "Employee B456 tends to take vacation every three months." The input is the preprocessed data, and the output is the vacation-taking pattern and predictive model.

[1283] Step 4:

[1284] The server uses the generated predictive model to generate vacation advice for employees. It also acquires and takes into account workload data for the current day and future periods. For example, it generates specific advice such as "We recommend that you take paid vacation on next Friday, December 8, 2023." The input is the predictive model and the latest workload data, and the output is the generated vacation advice.

[1285] Step 5:

[1286] The server notifies the employee of the generated vacation advice on their device. The advice is communicated to the employee via email or internal chat tools. For example, a notification may say, "We recommend that you take paid vacation next Friday, December 8, 2023. There has been a recent peak in workload, so you need to take a break." The input is the generated advice and the employee's contact information, and the output is the notification that arrives on the employee's device.

[1287] Step 6:

[1288] The advice is also sent to the work support device, allowing the device to monitor the workload in real time. This makes it possible to measure the workload and load of on-site workers in real time and provide appropriate vacation advice. The input is the generated advice and the on-site work support device, and the output is the device's real-time load data.

[1289] 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.

[1290] The present invention relates to a system for supporting employees in taking paid leave at the appropriate time. This system provides more personalized advice on taking leave by combining an employee emotion recognition engine.

[1291] Collecting employee vacation history data

[1292] The server has a means for collecting employee's past vacation acquisition data from the company's internal database, including information such as the date and duration of each employee's paid vacation.

[1293] Example: The server uses an SQL query to retrieve vacation data for employee ID "B789" for the past year. This data is stored in a temporary data store.

[1294] Data Preprocessing

[1295] The server performs pre-processing on the collected leave-taking data, including imputing missing values ​​and detecting and correcting outliers.

[1296] For example: If the collected data contains missing values, the server will perform reasonable imputation and correct any values ​​that are found to be significantly outside of normal holiday periods.

[1297] Pattern Analysis and Model Generation

[1298] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[1299] Collecting and analyzing emotional data

[1300] The server acquires data from various sources such as emails, chat logs, and voice data to collect user (employee) emotion data using an emotion engine.

[1301] Example: The server uses an emotion engine to analyze emails, chat logs, and audio data from meetings sent and received during employees' daily work to assess their stress levels. For example, the server may produce an evaluation result such as, "Your recent emails show a tendency toward emotional instability."

[1302] Generating Advice

[1303] The server generates optimal vacation advice for each employee based on the analysis results of the generated AI model and emotion engine, and also takes into account workload data to predict more personalized vacation timing.

[1304] Example: Based on the latest work data and emotional data, the server generates specific advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation next Friday, December 8, 2023."

[1305] User Notification

[1306] The server then sends the generated advice to the employee's device via email, internal chat tools, etc.

[1307] Example: The server obtains employee B's email address and sends the generated vacation advice by email, saying, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation on next Friday, December 8, 2023."

[1308] The system of the present invention can be implemented using the above steps. Using this system makes it easier for employees to take paid leave at the appropriate time, reducing stress, improving work efficiency, and creating a healthy working environment. Furthermore, by utilizing emotional data, more accurate advice can be provided, reducing the psychological burden on employees.

[1309] The processing flow will be explained below.

[1310] Step 1:

[1311] The server executes an SQL query to retrieve employee's past vacation data from the company database. For example, for employee ID "B789," retrieve data including vacation dates and durations for the past year. The retrieved data is stored in a temporary data store.

[1312] Step 2:

[1313] The server performs pre-processing on the collected leave taking data, which specifically includes the following actions:

[1314] Detecting and imputing missing values, for example, inserting reasonable approximations when data are missing for a period.

[1315] Detecting and correcting outliers, for example, periods that significantly exceed normal vacation periods.

[1316] Step 3:

[1317] The server loads the generative AI model and feeds the preprocessed data into the model, which then learns vacation-taking patterns from historical data—for example, identifying that employees tend to take vacation every three months.

[1318] Step 4:

[1319] The server uses an emotion engine to collect emotion data from users (employees), including methods for acquiring data from various sources such as email, chat logs, and voice data.

[1320] Example: The server collects messages sent by employee B during his or her daily work from the company's internal email system and chat tools, and passes them to the emotion engine. The emotion engine analyzes the content of the messages and evaluates their stress level.

[1321] Step 5:

[1322] The server uses the emotion engine to analyze the emotional data and identify the user's stress level and emotional state. For example, the analysis may yield results such as, "Your recent messages have been expressing more negative emotions."

[1323] Step 6:

[1324] The server performs additional database queries to obtain up-to-date workload data, which includes information indicating employee workload and workload levels.

[1325] Example: The server retrieves the progress of business tasks and cases for the current month from the database and uses it for analysis.

[1326] Step 7:

[1327] The server predicts the optimal time for each employee to take leave based on the analysis results of the generative AI model and emotion engine, as well as workload data, and generates specific advice.

[1328] Example: The server generates advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid vacation next Friday, December 8, 2023."

[1329] Step 8:

[1330] The server obtains the employee's contact information (e.g., email address) to notify them of the generated vacation advice, constructs a notification message, and sends it to the employee's device.

[1331] Example: The server obtains the email address of employee B and sends the generated vacation advice by email, saying, "Your current stress level is high, so we recommend that you take paid vacation on next Friday, December 8, 2023."

[1332] Step 9:

[1333] The user (employee) receives a notification from the server and considers taking paid leave at the recommended time. Based on this notification, the user incorporates the leave into their schedule.

[1334] Example 2

[1335] 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."

[1336] With traditional paid leave systems, employees must manage when to take their own leave, often resulting in employees being unable to take leave at the appropriate time. Furthermore, they rarely provide advice on taking leave that takes into account employees' emotional state and workload, and do not attempt to reduce stress or improve work efficiency. If this situation continues, it could increase the psychological burden on employees and result in a decline in the quality of their work.

[1337] 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.

[1338] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for collecting and analyzing employee emotion data, means for generating vacation advice for employees using the prediction model and the emotion data, and means for notifying the generated advice to the employee's terminal. This allows employees to take paid vacation at the appropriate time, which is expected to reduce stress and improve work efficiency. Furthermore, by utilizing emotion data, more accurate advice can be provided, reducing the psychological burden on employees.

[1339] "Employee's past vacation data" refers to data including the dates and duration of paid vacation time taken by an employee, as well as other related vacation usage information.

[1340] "Preprocessing" refers to processes such as filling in missing values ​​in collected data, correcting outliers, and formatting data.

[1341] "Vacation patterns" refer to the timing, frequency, and pattern of when a particular employee has taken paid vacation time in the past.

[1342] "Predictive model" refers to a model for predicting future vacation timing based on collected data and the results of its analysis.

[1343] "Emotional data" refers to data that indicates stress levels and emotional states extracted from emails, chat logs, audio data, etc. sent by employees during their daily work.

[1344] An "emotion recognition engine" refers to technology that analyzes collected emotional data and assesses employees' emotional state and stress levels.

[1345] "Vacation advice" refers to advice that suggests appropriate times for employees to take vacation based on collected data and predictive models.

[1346] "Employee devices" refers to devices such as computers, smartphones, and tablets used by employees for work.

[1347] "Workload data" refers to data that shows the status of the work that an employee is responsible for, such as the employee's current workload, project progress, and task list.

[1348] The present invention relates to a system that supports employees in taking paid leave at the appropriate time. This system provides more personalized advice on taking leave by combining an employee emotion recognition engine.

[1349] Collecting employee vacation history data

[1350] The server has the function of collecting employee's past vacation data from the company database, specifically, collecting information such as the date and period of paid vacation taken by each employee.

[1351] Specific behavior:

[1352] The server retrieves data from the company's internal database using SQL queries.

[1353] For example, run the query "SELECT FROM employee_leave WHERE employee_id = 'B789' AND date >= DATE_SUB(CURDATE(), INTERVAL 1 YEAR);".

[1354] This data is stored in a temporary data store (e.g., a memory cache).

[1355] Data Preprocessing

[1356] The server performs pre-processing on the collected data, including missing value imputation and outlier detection and correction.

[1357] Specific behavior:

[1358] The server detects data with missing values ​​and performs the imputation.

[1359] The server detects abnormal values ​​and corrects them to appropriate values.

[1360] Pattern Analysis and Model Generation

[1361] The server loads the generative AI model and feeds the preprocessed data into the model, which learns vacation-taking patterns from historical data.

[1362] Specific behavior:

[1363] The server loads a generative AI model (e.g., a model built with TensorFlow or PyTorch).

[1364] The preprocessed data is fed into the model to learn vacation-taking patterns.

[1365] For example, it learns patterns such as "employees tend to take vacation every three months."

[1366] Collecting and analyzing emotional data

[1367] The server uses an emotion recognition engine to collect emotional data from users (employees). Data sources include emails, chat logs, and voice data.

[1368] Specific behavior:

[1369] The server filters emails and chat logs sent and received during employees' daily work and sends them to an emotion recognition engine.

[1370] Use a speech analysis module (e.g., Google Cloud Speech-to-Text API) to analyze audio data during meetings in real time.

[1371] An emotion recognition engine analyzes this data and assesses the employee's emotional state (e.g., high stress levels).

[1372] Generating Advice

[1373] The server generates optimal vacation advice for each employee based on the analysis results of the generated AI model and emotion recognition engine, taking into account workload data as well.

[1374] Specific behavior:

[1375] The server obtains the latest business data.

[1376] Emotional and business data are fed into a generative AI model to generate personalized vacation advice.

[1377] For example, it generates specific advice such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[1378] User Notification

[1379] The server then sends the generated advice to the employee's device via email or an internal chat tool.

[1380] Specific behavior:

[1381] The server obtains the employee's email address and uses an SMTP server to send the advice via email.

[1382] For example, you could send an email that reads, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[1383] Similarly, notifications can be sent using internal chat tools (e.g., Slack, Microsoft Teams).

[1384] An example of a prompt sentence for the system of the present invention:

[1385] Employee ID: B789

[1386] Past vacation dates: 2022-11-10, 2023-02-15, 2023-05-20

[1387] Current mood assessment: High stress level

[1388] Workload: High

[1389] This system allows employees to take paid leave in a timely manner, improving the overall working environment.

[1390] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1391] Step 1: Collect employee leave history data

[1392] The server collects employee vacation history data from the company's internal database, including the dates and durations of paid vacation taken by each employee.

[1393] input:

[1394] Employee ID (e.g. B789)

[1395] Data processing and calculation:

[1396] The server executes an SQL query to extract the leave data for the corresponding employee ID. An example query would be "SELECT FROM employee_leave WHERE employee_id = 'B789' AND date >= DATE_SUB(CURDATE(), INTERVAL 1 YEAR);".

[1397] Stores the extracted data in a temporary data store.

[1398] Specific behavior:

[1399] Use an SQL query to retrieve vacation data for the past year corresponding to the employee ID from the database.

[1400] output:

[1401] Data on vacation taken over the past year (e.g., vacation date, duration)

[1402] Step 2: Preprocessing the data

[1403] The server pre-processes the collected leave-taking data, which includes imputing missing values ​​and detecting and correcting outliers.

[1404] input:

[1405] Collected leave taking data

[1406] Data processing and calculation:

[1407] The server detects missing values ​​and imputes them with the mean or median.

[1408] Detect outliers (values ​​significantly exceeding normal holiday periods) and correct them to appropriate values.

[1409] Specific behavior:

[1410] Find data with missing values ​​and impute them with reasonable values.

[1411] Detecting abnormal vacation duration data and correcting these with the average vacation duration.

[1412] output:

[1413] Preprocessed leave taking data

[1414] Step 3: Pattern analysis and model generation

[1415] The server inputs the pre-processed data using a generative AI model to learn leave-taking patterns.

[1416] input:

[1417] Preprocessed leave taking data

[1418] Data processing and calculation:

[1419] The server loads a generative AI model (e.g., a model built with TensorFlow or PyTorch).

[1420] The preprocessed data is fed into the model to learn vacation-taking patterns.

[1421] Specific behavior:

[1422] Load the generative AI model into memory.

[1423] Input data is fed into the model and a learning process is run to analyze vacation-taking trends.

[1424] output:

[1425] Predictive model based on vacation patterns

[1426] Step 4: Collect and analyze sentiment data

[1427] The server uses an emotion recognition engine to collect and analyze the emotion data of users (employees).

[1428] input:

[1429] Emails, chat logs, and voice data

[1430] Data processing and calculation:

[1431] The server collects emails and chat logs and sends them to an emotion recognition engine.

[1432] The voice data is converted into text using a voice analysis module (e.g., Google Cloud Speech-to-Text API) and then analyzed using an emotion recognition engine.

[1433] An emotion recognition engine analyzes the emotional data and assesses the employee's emotional state.

[1434] Specific behavior:

[1435] Filter and collect emails and chat logs during daily work.

[1436] Audio data during meetings is converted into text and analyzed in real time.

[1437] output:

[1438] Employee emotional state (e.g., stress level)

[1439] Step 5: Generating Advice

[1440] The server generates vacation advice for each employee based on the results of the analysis of the predictive model and emotion data, taking into account workload data.

[1441] input:

[1442] Predictive Model

[1443] Emotion data analysis results

[1444] Workload data

[1445] Data processing and calculation:

[1446] The server retrieves the latest business data.

[1447] Feed business and emotional data into a generative AI model to predict when to take vacation.

[1448] Specific behavior:

[1449] Collect workload and project progress data.

[1450] Emotional data and work data are input into an AI model to generate the timing for taking vacation.

[1451] output:

[1452] Vacation advice (e.g., "We recommend that you take paid vacation next Friday, December 8, 2023.")

[1453] Step 6: Notify users

[1454] The server then sends the generated advice to the employee's device via email or an internal chat tool.

[1455] input:

[1456] Generated leave advice

[1457] Employee contact information

[1458] Data processing and calculation:

[1459] The server obtains the employee's email address and sends the email using the SMTP server.

[1460] Advice is shared using internal chat tools (e.g., Slack or Microsoft Teams).

[1461] Specific behavior:

[1462] Capture employee contact information and send notifications via email or chat tools.

[1463] For example, you could send an email stating, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday, December 8, 2023."

[1464] output:

[1465] Vacation advice displayed on employees' devices

[1466] (Application example 2)

[1467] 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."

[1468] In today's work environment, managing employee stress and encouraging appropriate vacation time are key issues. However, traditional vacation time systems do not take into account employees' emotional states or individual stress levels, making it difficult to ensure that vacation time is taken at the appropriate time. This increases employees' psychological burden and leads to problems with a declining work environment. In response, a new system is needed that utilizes multifaceted information, including emotional data, to improve employee health and efficiency.

[1469] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1470] In this invention, the server includes means for collecting employee past vacation data, means for preprocessing the collected data, means for analyzing vacation patterns based on the preprocessed data and generating a prediction model, means for generating vacation advice for employees using the prediction model, means for notifying the employees of the advice to their terminals, means for collecting and analyzing emotional data in real time, means for assessing the employees' stress levels using the emotional data, and means for optimizing the timing of vacation time based on the stress levels. This enables personalized vacation advice that takes into account the employees' emotional states and stress levels, and encourages them to take vacation time at appropriate times.

[1471] "Employee" refers to an individual who belongs to a company or organization and is engaged in its work.

[1472] "Leave Taken Data" means information regarding the dates, duration and frequency of leave taken by an Employee.

[1473] "Emotional data" refers to information about an employee's emotional state extracted from email, chat, and voice data.

[1474] "Preprocessing" refers to the process of filling in missing values ​​and correcting outliers in collected data.

[1475] "Leave taking patterns" refer to regular or characteristic vacation taking tendencies extracted from employees' past vacation taking data.

[1476] "Predictive model" refers to the algorithm used to learn from past data and predict future leave taking.

[1477] "Vacation Advice" refers to appropriate vacation recommendations for employees that are generated based on the results of predictive models and analysis of sentiment data.

[1478] "Notification" refers to the act of sending the generated vacation advice to an employee's device.

[1479] "Real-time collection" refers to obtaining emotional data instantly while employees are engaged in their activities.

[1480] "Stress level" refers to the degree of psychological stress an employee experiences, assessed based on the analysis of emotional data.

[1481] "Optimization" refers to adjusting employees' vacation timing to make it the most effective based on collected data.

[1482] MODE FOR CARRYING OUT THE INVENTION

[1483] To implement this invention, the system has the following procedures and components: First, the server has a means for collecting employee's past vacation data. This data includes the date and duration of vacation taken by the employee. The server uses SQL queries to collect this data from the company's internal database.

[1484] The server performs preprocessing on the collected data to impute missing values ​​and correct outliers. For example, if there are missing values ​​in the collected data, the server will impute them rationally, and if values ​​that significantly exceed the normal holiday period are detected, they will be corrected.

[1485] The server then analyzes vacation patterns based on the preprocessed data and generates a predictive model. Specifically, the server loads a generative AI model and learns vacation patterns from past data. For example, the server identifies that employees tend to take vacation every three months.

[1486] In addition, emotional data is collected and analyzed. The server uses an emotion engine to collect employee emotional data, retrieving data from emails, chat logs, and voice data. This data is used to evaluate an employee's stress level during their daily work. For example, if recent emails show a tendency toward emotional instability, the system will evaluate the employee's "current stress level is high."

[1487] The server then generates personalized vacation advice based on the analysis results of the generated AI model and emotion engine. This advice also takes workload data into account, allowing for more accurate recommendations. For example, specific advice could be generated such as, "Based on your emotion data, your current stress level is high. We recommend that you take paid vacation next Friday."

[1488] The generated advice is ultimately sent to the employee's device. The server then sends reminders and notifications via email or internal chat tools. For example, the server could obtain an employee's email address and send a notification such as, "Based on your emotional data, your current stress level is high. We recommend that you take paid leave next Friday."

[1489] Examples:

[1490] Assume that employees at a physical store wear smartphones or smart glasses. An application installed on this device collects and analyzes the employee's emotional and work data in real time, and recommends taking time off at the appropriate time. The server collects the employee's past vacation data and analyzes the emotional data using an emotion engine. For example, if the stress level is determined to be high, the server will notify the employee, "We recommend taking time off next Friday."

[1491] Example prompt sentence:

[1492] "Please calculate the recommended date for the next paid vacation based on the vacation data taken by employee ID 'B789' over the past year. Using past data and the employee's emotional data (email, chat, voice) during daily work, if the employee's stress level is high, please suggest the best vacation date in the near future."

[1493] In this way, the system can provide personalized leave advice that takes into account employees' emotional state and stress levels, which will encourage timely leave taking and reduce the psychological burden on employees.

[1494] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1495] Step 1:

[1496] The server collects employee's past vacation data from the company database. Specifically, it uses SQL queries to retrieve information such as vacation dates and durations corresponding to employee IDs, and stores this information in a temporary data store. The input is the employee ID and database connection information, and the output is the vacation data.

[1497] Step 2:

[1498] The server performs preprocessing on the collected vacation data. This preprocessing includes imputing missing values ​​and detecting and correcting outliers. First, if missing values ​​exist, it imputes the most reasonable value. Second, it detects outliers that significantly exceed the normal vacation period and corrects them to an appropriate range. The input is the collected vacation data, and the output is the preprocessed data.

[1499] Step 3:

[1500] The server analyzes vacation-taking patterns based on the preprocessed data and generates a predictive model. To do this, it loads a generative AI model and inputs the preprocessed data into the model. The model learns vacation-taking patterns from the data and outputs a pattern for predicting future vacation taking. The input is the preprocessed data, and the output is the generated predictive model.

[1501] Step 4:

[1502] The server uses an emotion engine to collect employee emotion data. Data is obtained from a variety of sources, including emails, chat logs, and voice data, and analyzed by the emotion engine. Specifically, it collects emails and chat logs sent and received during daily work, as well as voice data during meetings. The input is employee activity data, and the output is analyzed emotion data.

[1503] Step 5:

[1504] The server evaluates the employee's stress level based on the obtained emotional data. Using the analysis results of the emotion engine, the stress level of the employee during daily work is quantified and evaluated. For example, the evaluation may be "Your recent emails show a tendency toward emotional instability." The input is the analyzed emotional data, and the output is the evaluated stress level.

[1505] Step 6:

[1506] The server generates optimal vacation advice for each employee based on the generated AI model and the analysis results of the emotion engine. For example, it generates specific advice such as, "Based on your emotion data, your current stress level is high. We recommend that you take paid vacation next Friday." The input is the prediction model and stress level, and the output is the generated vacation advice.

[1507] Step 7:

[1508] The server notifies the generated advice to the employee's device. Reminders and notifications are sent using email or internal chat tools. For example, an employee's email address can be used to send a message saying, "Based on your emotional data, your current stress level is high. We recommend that you take vacation next Friday." The input is the generated vacation advice and the employee's contact information, and the output is the sent notification.

[1509] These steps enable the system to provide personalized leave advice that takes into account an employee's emotional state and stress level.

[1510] 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.

[1511] 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.

[1512] 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 robot 414.

[1513] 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.

[1514] 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.

[1515] 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.

[1516] 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).

[1517] 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, motorcycles, and other devices, 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.

[1518] 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."

[1519] 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.

[1520] 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).

[1521] 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.

[1522] 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.

[1523] 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.

[1524] 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.

[1525] 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.

[1526] 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 resource that executes the specific processing may be a single processor.

[1527] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1528] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1529] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1530] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1531] The following is further disclosed regarding the above embodiment.

[1532] (Claim 1)

[1533] A means of collecting employee past leave data;

[1534] means for pre-processing the collected data;

[1535] means for analyzing vacation taking patterns based on the pre-processed data and generating a predictive model;

[1536] means for generating leave advice for employees using the predictive model;

[1537] means for notifying the generated advice to an employee terminal;

[1538] A system including:

[1539] (Claim 2)

[1540] 2. The system according to claim 1, wherein the means for generating vacation advice adjusts vacation timing in consideration of workload data.

[1541] (Claim 3)

[1542] The system of claim 1, wherein the means for analyzing vacation-taking patterns uses a generation AI to learn the frequency and timing of vacation taking for each employee.

[1543] "Example 1"

[1544] (Claim 1)

[1545] A means of collecting employee past leave data;

[1546] means for pre-processing the collected data;

[1547] means for analyzing vacation taking patterns based on the pre-processed data and generating a predictive model;

[1548] means for generating leave advice for employees using the predictive model;

[1549] means for notifying the generated advice to an employee terminal;

[1550] The notification will be made by email or an internal chat tool.

[1551] A system including:

[1552] (Claim 2)

[1553] 2. The system according to claim 1, wherein the means for generating vacation advice adjusts vacation timing in consideration of workload data.

[1554] (Claim 3)

[1555] The system of claim 1, wherein the means for analyzing vacation-taking patterns uses a generation AI to learn the frequency and timing of vacation taking for each employee.

[1556] "Application Example 1"

[1557] (Claim 1)

[1558] A means of collecting employee past leave data;

[1559] means for pre-processing the collected data;

[1560] means for analyzing vacation taking patterns based on the pre-processed data and generating a predictive model;

[1561] means for generating leave advice for employees using the predictive model;

[1562] means for notifying the generated advice to an employee terminal;

[1563] means for notifying a device that supports the work of the advice, and for the device to monitor the workload in real time;

[1564] A system including:

[1565] (Claim 2)

[1566] 2. The system according to claim 1, wherein the means for generating vacation advice adjusts the timing of vacation taking in consideration workload data, and notifies the generated advice through a workload monitoring device.

[1567] (Claim 3)

[1568] The system of claim 1, wherein the means for analyzing vacation-taking patterns uses a generation AI to learn the frequency and timing of vacation taking for each employee, and executes the generated model in an application installed on the work support device.

[1569] "Example 2: Combining Emotion Engines"

[1570] (Claim 1)

[1571] A means of collecting employee past leave data;

[1572] means for pre-processing the collected data;

[1573] means for analyzing vacation taking patterns based on the pre-processed data and generating a predictive model;

[1574] A means of collecting and analyzing employee emotional data;

[1575] means for generating vacation advice for employees using the predictive model and emotion data;

[1576] means for notifying the generated advice to an employee terminal;

[1577] A system including:

[1578] (Claim 2)

[1579] 2. The system according to claim 1, wherein the means for generating vacation advice adjusts vacation timing in consideration of workload data.

[1580] (Claim 3)

[1581] The system of claim 1, wherein the means for analyzing vacation-taking patterns uses a generation AI to learn the frequency and timing of vacation taking for each employee.

[1582] (Claim 4)

[1583] 10. The system of claim 1, wherein the means for collecting and analyzing emotion data obtains data from multiple sources, including email, chat logs, and voice data, and uses an emotion recognition engine to assess the employee's emotional state.

[1584] "Application example 2 when combining emotion engines"

[1585] (Claim 1)

[1586] A means of collecting employee past leave data;

[1587] means for pre-processing the collected data;

[1588] means for analyzing vacation taking patterns based on the pre-processed data and generating a predictive model;

[1589] means for generating leave advice for employees using the predictive model;

[1590] means for notifying said advice to an employee's terminal;

[1591] A means of collecting and analyzing emotion data in real time;

[1592] means for assessing the stress level of employees using said emotion data;

[1593] means for optimizing vacation timing based on said stress level;

[1594] A system including:

[1595] (Claim 2)

[1596] 2. The system according to claim 1, wherein the means for generating vacation advice adjusts vacation timing in consideration of workload data and emotion data.

[1597] (Claim 3)

[1598] 2. The system of claim 1, wherein the means for analyzing vacation-taking patterns uses a generative AI model to learn the frequency and timing of vacation taking for each employee. [Explanation of symbols]

[1599] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting employee past leave data; means for pre-processing the collected data; means for analyzing vacation taking patterns based on the pre-processed data and generating a predictive model; means for generating leave advice for employees using the predictive model; means for notifying the generated advice to an employee terminal; A system including:

2. 2. The system according to claim 1, wherein the means for generating vacation advice adjusts vacation timing in consideration of workload data.

3. The system according to claim 1, wherein the means for analyzing vacation taking patterns uses a generation AI to learn the frequency and timing of vacation taking for each employee.

Images