System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting an operation log of an employee, a means for storing the collected operation log, a means for analyzing the stored operation log and detecting a common work, a means for generating a script for automating the detected common work, a means for generating an AI worker for executing the generated script, and a means for executing a specific task by the generated AI worker.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 many companies, many employees perform similar or identical tasks multiple times, resulting in reduced work efficiency and wasted resources. Employees are overwhelmed with their daily work, making it difficult to improve work efficiency or implement new ideas. This leads to a lack of resources for new challenges and ideas, resulting in a decline in productivity across the company. Therefore, there is a need for a system that can reduce duplicated work and improve work efficiency. [Means for solving the problem]

[0005] This problem is solved by a system that includes a means for collecting employee operation logs, a means for saving the collected operation logs, a means for analyzing the saved operation logs to detect common tasks, a means for generating scripts to automate the detected common tasks, a means for generating AI workers to execute the generated scripts, and a means for the generated AI workers to perform specific tasks. Specifically, employees' PC operations are monitored in real time, and log data is collected and saved. The saved data is then analyzed using machine learning algorithms and natural language processing technology to detect common tasks. Scripts to automate the detected common tasks are generated, and the AI ​​workers execute the scripts, thereby consolidating duplicated tasks and improving work efficiency. This system allows employees to focus on their regular work and enables them to take on new challenges and implement new ideas.

[0006] An "operation log" is a record of data such as the operations performed by employees on their PCs, the applications used, timestamps, and input content.

[0007] The "storage means" refers to a device or program that stores the collected operation logs in a database and creates an index to facilitate search and analysis.

[0008] "Analysis" is the process of using machine learning algorithms and natural language processing techniques on collected operation logs to identify common tasks and extract frequencies and patterns.

[0009] "Common tasks" are tasks or operations that are similar or performed repeatedly at the same time by multiple employees.

[0010] An "automation script" is program code generated to automate common tasks, and automatically executes specific operational procedures on a system.

[0011] "AI workers" are virtual workers equipped with artificial intelligence that are generated to execute automated scripts to perform specific tasks.

[0012] "Specific tasks" are specific work operations that employees perform on a daily basis, such as data entry, report writing, email sending, and file management. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The system of this invention uses AI to analyze the PC work performed by employees, automatically discover common tasks, and automate them. This system will improve business efficiency and allow employees to focus on new challenges and ideas.

[0035] First, agent software is installed on employees' PCs. This agent software has the function of collecting employees' operation logs in real time. Specifically, it records opened applications, operation details, timestamps, input details, etc., and then encrypts and sends the data to the company's server. By collecting operation logs, the agent software makes it possible to record daily business activities.

[0036] Next, the server receives the operation logs sent from the devices and stores them in a database. The server then analyzes the stored data using machine learning algorithms and natural language processing technology. This analysis makes it possible to automatically detect tasks that are commonly performed by multiple employees, in other words, "common tasks." For example, tasks such as data entry, report creation, and email sending may be detected as common tasks.

[0037] For each common task detected, the server generates an automated script. This script describes a series of steps to perform the common task efficiently. The generated script is tested in a test environment, and after confirming there are no problems, it is implemented in actual business operations.

[0038] The server generates an AI worker to execute the generated script. This AI worker acts as a virtual worker and has the ability to perform specific tasks, such as automatically extracting and inputting data, generating reports, and managing files.

[0039] The generated AI workers run on terminals or remote servers to perform specific tasks. This improves operational efficiency by allowing AI workers to automatically perform common tasks, eliminating the need for employees to perform them manually. Employees are freed from time-consuming, duplicated tasks, allowing them to focus on other important tasks.

[0040] As a concrete example, consider a company that regularly requires large-scale data entry work. Employees spend a lot of time on this work. Agent software collects each employee's operation log, and the server analyzes the data to detect common data entry tasks. It then generates a script to automate the task, and an AI worker executes the script, automatically completing the data entry work. As a result, employees no longer need to manually perform data entry work, allowing them to focus on other tasks.

[0041] In this way, the system of the present invention can significantly improve business efficiency within a company and increase employee productivity.

[0042] The processing flow will be explained below.

[0043] Step 1:

[0044] Terminal

[0045] Agent software is installed on each employee's PC, which monitors the employee's PC operations in real time and collects data such as operations, applications used, timestamps, and input contents.

[0046] Step 2:

[0047] Terminal

[0048] The agent software encrypts the collected log data and sends it to the company's server at regular intervals (for example, every hour).

[0049] Step 3:

[0050] server

[0051] The company's server stores the received operation log data in a database, which stores each employee's operation log in chronological order and creates an index for subsequent analysis.

[0052] Step 4:

[0053] server

[0054] Machine learning algorithms are applied to the saved operation log data. Specifically, frequency analysis and pattern recognition are performed to extract tasks commonly performed by multiple employees. This includes detecting the frequency of use of specific applications and specific operation patterns.

[0055] Step 5:

[0056] server

[0057] Based on patterns and common tasks extracted by machine learning algorithms, a list of common tasks is created, including how many times each task is performed and which employee performed each task.

[0058] Step 6:

[0059] server

[0060] Scripts are automatically generated for the listed common tasks. These scripts contain procedures for efficiently executing common tasks by consolidating them into a single automated process. For example, for a data entry task, the scripts include steps such as extracting the data to be entered, entering the data into the input fields, and confirming and saving the final data.

[0061] Step 7:

[0062] server

[0063] Run the generated script in a test environment and check its operation. If there are any errors or areas for improvement, correct them and confirm that there are no problems.

[0064] Step 8:

[0065] server

[0066] Once the script has been tested, it is deployed in a real-world environment to generate an AI worker, which is then ready to automatically perform specific tasks based on the script.

[0067] Step 9:

[0068] Terminal and Server

[0069] The AI ​​worker performs specific tasks according to a schedule, for example, starting data entry work at a specific time each day, saving the results after completion, and sending the logs to a server.

[0070] Step 10:

[0071] server

[0072] The execution results are recorded in a log and periodically analyzed to evaluate the degree of operational efficiency achieved. Based on these results, if further improvements are needed, the scripts are updated or the AI ​​workers are adjusted.

[0073] Example 1

[0074] 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."

[0075] The problem that this invention aims to solve is to improve business efficiency by automatically detecting duplicate work by employees in a company and efficiently automating it. Conventional systems only support manual work recording and individual automation, making it difficult to optimize the entire business process. In addition, the accuracy of analysis results and the accuracy of automation have also been problematic.

[0076] 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.

[0077] In this invention, the server includes means for collecting employee operation logs, means for saving the collected operation logs, means for analyzing the saved operation logs and detecting common tasks, means for generating scripts to automate the detected common tasks, means for verifying the operation of the generated scripts in a test environment, means for generating AI workers to execute the generated scripts, and means for the generated AI workers to execute specific tasks. This makes it possible to automatically detect duplicate tasks in the daily work performed by employees and to efficiently automate those tasks.

[0078] An "employee operation log" is a history of operations performed by employees on devices such as PCs, and includes the names of applications opened, operation details, timestamps, input details, etc.

[0079] "Log collection means" refers to software or hardware that collects employee operation logs in real time, encrypts them, and sends them to a server.

[0080] "Log storage means" refers to a mechanism for storing collected operation logs in a storage device such as a database.

[0081] "Log analysis means" refers to a method or device for analyzing stored operation logs using machine learning algorithms or natural language processing techniques to detect common tasks.

[0082] "Common tasks" refer to similar or identical tasks performed by multiple employees, such as data entry, report creation, and email sending.

[0083] "Script generator" refers to a method or apparatus for programming and generating, in script form, procedures for automating detected common tasks.

[0084] A "test environment" refers to a virtual or sandbox environment in which generated scripts can be verified to work correctly.

[0085] "AI worker" refers to artificial intelligence that executes generated scripts and automatically performs specific tasks as a virtual worker.

[0086] "Task execution means" refers to a method or device by which an AI worker performs a particular task.

[0087] The system of this invention analyzes the PC work performed by employees, automatically discovers common tasks, and provides a new means of automating those tasks. The aim is to improve business efficiency in companies, allowing employees to focus on new challenges and ideas.

[0088] First, the user (employee) installs agent software on their PC. This agent software has the function of collecting the employee's operation log in real time. Specifically, it collects the names of open applications, operation details, timestamps, input details, etc. This operation log is encrypted and sent to the company's server.

[0089] Next, the server receives the operation log sent from the terminal and stores it in a database. Here, a database management system such as MySQL (registered trademark) or PostgreSQL can be used.

[0090] The server analyzes the saved operation log data. This analysis is performed using the Python libraries TENSORFLOW (registered trademark) and Scikit-learn. First, the data is preprocessed to extract the necessary features. Next, a machine learning algorithm is applied based on the extracted features to detect patterns of common tasks. Natural language processing technology is also used to analyze text information within the log data.

[0091] The server generates scripts to automate the detected common tasks. Specifically, the procedures for the common tasks are written as scripts using Python or RPA tools (UiPath or Automation Anywhere). The generated scripts are first tested in a test environment. A virtual environment or sandbox environment is used to verify that the scripts work correctly.

[0092] The server then generates an AI worker to execute the generated script. This AI worker acts as a virtual worker and performs specific tasks, such as automatically extracting and inputting data, generating reports, and managing files. The AI ​​worker runs on a terminal or a remote server.

[0093] The generated AI workers automatically perform common tasks, freeing users (employees) from duplicated tasks that they would otherwise perform manually, allowing them to focus on other important tasks and improving work efficiency.

[0094] Examples:

[0095] Suppose a company regularly needs to perform large-scale data entry tasks. Employees spend a lot of time on this task. Agent software collects each employee's operation log, and the server analyzes the data to detect common data entry tasks. It then generates a script to automate the task, and an AI worker executes the script, automatically completing the data entry tasks. As a result, employees no longer need to manually perform data entry tasks, allowing them to focus on other tasks.

[0096] Example prompt sentence:

[0097] Analyze employee operation logs to detect common tasks and generate scripts to automate them. Write scripts using Python or RPA tools (UiPath, Automation Anywhere) to generate AI workers to perform the tasks.

[0098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0099] Step 1: Installing the agent software and collecting operation logs

[0100] A user installs agent software on their PC. This agent software has the ability to collect all operation logs in real time. Specifically, it collects information such as the names of applications opened on the PC, operation details, timestamps, and entered data. These operation logs are encrypted and sent to a server in a secure format.

[0101] Input: User operation (application name, operation content, timestamp, input data)

[0102] Output: Encrypted operation log data

[0103] Step 2: Receiving and saving the operation log

[0104] The server receives the operation logs sent from the terminal. The received operation logs are stored in a database. A database management system such as MySQL or PostgreSQL can be used. During this process, data consistency checks and duplicate elimination processes are performed.

[0105] Input: Encrypted operation log data

[0106] Output: Operation log stored in the database

[0107] Step 3: Analyze the operation log

[0108] The server analyzes the saved operation log data. This analysis is performed using the Python libraries TensorFlow and Scikit-learn. The data is preprocessed to extract the necessary features. Next, a machine learning algorithm is applied based on the extracted features to detect patterns of common tasks. Natural language processing technology is also used to analyze the text data.

[0109] Input: Operation logs stored in the database

[0110] Output: Generated common work pattern

[0111] Step 4: Generate and test scripts

[0112] The server generates a script for automation based on the analysis results. Specifically, it uses Python or an RPA tool (e.g., UiPath or Automation Anywhere) to program the procedures for common tasks. The generated script is first tested in a test environment, which can be a virtual environment or a sandbox environment.

[0113] Input: Detected common work patterns

[0114] Output: Generated automation script

[0115] Step 5: Generate AI workers and execute tasks

[0116] The server generates an AI worker to execute the generated script. This AI worker performs specific tasks as a virtual worker. Specifically, it automatically performs business operations such as data extraction and input, report generation, and file management. The AI ​​worker runs on a terminal or a remote server.

[0117] Input: Generated automation script

[0118] Output: The automated task that will be executed

[0119] Step 6: Improve operational efficiency through automation

[0120] Users (employees) are freed from manual, duplicated tasks by having AI workers automatically perform common tasks, allowing employees to focus on other important tasks and improving work efficiency.

[0121] Input: The automated task to be executed

[0122] Output: Streamlined business processes

[0123] (Application example 1)

[0124] 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."

[0125] There is a need to significantly improve operational efficiency by automating common tasks performed by employees on a daily basis. In particular, logistics centers have a large number of manual tasks, such as inventory management and picking, and there is an urgent need to streamline these tasks. In addition, there is a need to reduce the burden on employees by automating tasks using smart devices and promote the smooth progress of operations.

[0126] 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.

[0127] In this invention, the server includes: means for collecting employee operation logs; means for saving the collected operation logs; means for analyzing the saved operation logs and detecting common tasks; means for generating scripts to automate the detected common tasks; means for generating AI workers to execute the generated scripts; means for the generated AI workers to perform specific tasks; means including a smart device for analyzing the operation logs and issuing commands to execute the automation scripts; means for analyzing common tasks from employee operation logs using a machine learning algorithm; means for extracting tasks for improving efficiency from log information using natural language processing technology; means for automatically updating inventory data using the camera function of the smart device; and means for analyzing common tasks and proposing optimal product picking routes. This enables efficient inventory management and picking operations at logistics centers by analyzing employee operation logs in detail and generating automation scripts.

[0128] An "employee operation log" is a record of operations performed by employees, and specifically includes application usage information, operation details, timestamps, input data, and the like.

[0129] "Means for collecting operation logs" refers to software or hardware for collecting and recording employee operation logs in real time.

[0130] The "means for storing operation logs" refers to a database or storage system for appropriately storing collected operation logs.

[0131] A "means for detecting common tasks" is an algorithm or program that analyzes and finds tasks that are commonly performed by multiple employees.

[0132] The "means for generating scripts for automation" is software that generates scripts for automatically executing common tasks based on specific procedures.

[0133] An "artificial intelligence worker" is a virtual worker that automatically executes specific tasks based on a generated script.

[0134] A "smart device" is a device that can connect to the Internet, such as a smartphone, tablet, or smart glasses, and is used to collect operation logs and execute scripts.

[0135] A "machine learning algorithm" is an algorithm that learns patterns from large amounts of data and detects common tasks.

[0136] "Natural language processing technology" is a technology for analyzing text data and understanding the meaning of language.

[0137] The "means for automatically updating inventory data" is a system that uses the camera function of a smart device to scan information about inventory items and automatically update the database.

[0138] The "means for proposing the optimal picking route" is an algorithm that proposes the optimal route for efficiently picking products within a logistics center.

[0139] The system of this invention aims to improve the efficiency of operations at logistics centers. In particular, it is possible to significantly improve the work efficiency of logistics centers by analyzing employee operation logs and automating common tasks.

[0140] The system of the present invention begins with the installation of agent software on employees' smart devices (e.g., smartphones, tablets). This agent software collects operational logs of employees' daily work in real time and stores them in a database. Specifically, application usage information, operation details, timestamps, and other information are collected as logs.

[0141] The server analyzes the collected operation logs using machine learning algorithms and natural language processing technology to automatically detect tasks performed by multiple employees (common tasks), such as inventory checks, data entry, and creating picking lists.

[0142] The server generates an automation script for each common task that is detected. This script describes a series of steps to perform the common task efficiently. The generated script is tested in a test environment, and once no problems are confirmed, it is implemented in the actual business.

[0143] The generated scripts are executed by an AI worker, who has the ability to automatically perform specific tasks, such as automatically updating inventory or suggesting optimal routes for picking lists. The AI ​​worker can also use the camera function of a smart device to scan QR codes on inventory items and automatically update the database.

[0144] As a concrete example, consider inventory management at a logistics center. Employees can scan the QR codes of inventory items with their smart devices, automatically updating inventory data. Furthermore, when picking items, AI workers can suggest optimal picking routes, improving employee efficiency.

[0145] An example of a prompt is "Implement a QR code scanning function to streamline inventory management," which would enable more efficient inventory management using smart devices.

[0146] In this way, the system of the present invention can significantly improve the operational efficiency of a logistics center, reduce the burden on employees, and increase productivity.

[0147] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0148] Step 1:

[0149] A user starts work using a smart device. Agent software is installed on the smart device and collects the user's operation logs in real time. The collected operation logs include application usage information, operation details, timestamps, etc. This log data is encrypted and sent to the server. The input is the user's operation, and the output is the operation log.

[0150] Step 2:

[0151] The server stores the operation logs it receives in a database. The server then converts the operation logs into a format that is easy to analyze and stores them. Specific data processing includes timestamp format conversion and input content classification. The input is encrypted operation logs, and the output is operation log data converted into a standard format for analysis.

[0152] Step 3:

[0153] The server uses a machine learning algorithm to analyze the stored operation logs. It classifies and clusters the data to detect common tasks. Specifically, it identifies patterns of operations frequently performed by employees and recognizes them as common tasks. The input is operation log data in a standard format, and the output is a list of detected common tasks.

[0154] Step 4:

[0155] The server uses natural language processing technology to perform a detailed analysis of common tasks. Specifically, it understands the intent behind the operation procedures and instructions from the text data in the operation log. This analysis generates a script to efficiently automate the common tasks. The input is a list of common tasks, and the output is an automation script.

[0156] Step 5:

[0157] The server builds an AI worker based on the generated script. The AI ​​worker is a program that automatically executes specific tasks based on the generated script. The input is the automation script, and the output is the AI ​​worker program.

[0158] Step 6:

[0159] An AI worker starts working on a smart device. For example, the smart device's camera scans a QR code and automatically updates inventory data. An algorithm is also run to suggest the optimal route for the picking list. The inputs are inventory items and picking data, and the output is the updated inventory data and the suggested picking route.

[0160] An example of a prompt is "Implement a QR code scanning function to streamline inventory management," which would enable efficient inventory management using smart devices.

[0161] The above is the specific processing flow of the system for realizing the application example.

[0162] 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.

[0163] This invention is a system that simultaneously collects and analyzes employees' PC operation logs and emotional states, and automates common work tasks. This system not only improves work efficiency but also reduces employees' stress levels, providing a more comfortable working environment.

[0164] Overall system configuration

[0165] First, agent software is installed on the user's device. This agent software uses an emotion engine to collect emotional data in real time, along with the user's PC operation log. The operation log includes application usage, operation details, timestamps, and input details. Emotional data includes biometric information such as the user's facial expression, voice tone, and heart rate.

[0166] Data collection

[0167] The agent software encrypts the collected operation logs and emotional data and periodically transmits them to the company's server, which stores the received data in a database for subsequent analysis.

[0168] Data analysis

[0169] The server analyzes the stored operation logs and emotional data using machine learning algorithms and natural language processing technology. This analysis detects common tasks performed by multiple employees. Analysis of the emotional data also makes it possible to evaluate the level of stress and fatigue that a particular task causes to the user.

[0170] Generating automation scripts

[0171] Based on the detected common tasks, the server generates an automation script. This script combines the common tasks into a single process and includes instructions for efficient execution. Furthermore, the script can be adjusted based on the user's emotional data. For example, if a particular task causes high stress, the script can be optimized to perform the task in a more efficient manner.

[0172] AI worker generation and execution

[0173] The server generates an AI worker to execute the generated script. This AI worker is a virtual worker that automatically performs specific tasks. The AI ​​worker executes the task according to a schedule and sends the results to the server as a log. This eliminates the need for employees to perform the task manually, improving work efficiency.

[0174] Emotional Feedback

[0175] The server analyzes the user's emotional data and the AI ​​worker's performance results, and provides real-time feedback. For example, it can recommend a break if the user is feeling stressed, or suggest adjustments to the work environment. This feedback is also reflected in the next script generation, further optimizing the entire system.

[0176] Specific examples

[0177] For example, a company regularly creates sales reports and uploads them to a shared folder. Employees spend a lot of time on this task, and they often find it particularly stressful. The agent software collects each employee's operation log and emotional data, such as facial expressions and voice tone, and the server analyzes them. The software then detects common tasks involved in creating sales reports and uploading them to the folder, generating a script to automate the task. This script is optimized to reduce stress, and an AI worker executes it, improving work efficiency while reducing employee stress. Repeating this entire process simultaneously improves the company's operational efficiency and employee satisfaction.

[0178] As described above, the system of the present invention simultaneously improves business efficiency and manages the emotional state of employees, thereby improving productivity across the entire company.

[0179] The processing flow will be explained below.

[0180] Step 1:

[0181] Terminal

[0182] Agent software is installed on each employee's PC. The agent software collects the employee's PC operation log and emotional data in real time. The operation log includes the application used, operation details, timestamp, and input content. Emotional data includes facial expressions, voice tone, heart rate, etc.

[0183] Step 2:

[0184] Terminal

[0185] The agent software encrypts the collected operation logs and emotional data and sends them to the company's server at regular intervals (for example, every hour).

[0186] Step 3:

[0187] server

[0188] The company's server stores the received operation logs and emotion data in a database. The database stores each employee's operation log and emotion data in chronological order and creates an index to facilitate search and analysis.

[0189] Step 4:

[0190] server

[0191] Machine learning algorithms and natural language processing technology are applied to the saved operation logs and emotion data. Based on the operation data, frequency analysis and pattern recognition are performed to detect tasks that are commonly performed by multiple employees (common tasks). At the same time, emotion data is analyzed to evaluate the stress level during specific tasks.

[0192] Step 5:

[0193] server

[0194] Based on the analysis results, a list of identified common tasks is created, and an automation script is generated based on the list. The automation script includes a series of steps to efficiently execute the detected common tasks. Furthermore, optimization is performed to reduce stress levels during work based on emotion data.

[0195] Step 6:

[0196] server

[0197] Run the generated script in a test environment to check its operation. Test whether the script has errors and runs as expected. Fix any defects or areas for improvement that are found.

[0198] Step 7:

[0199] server

[0200] To operate the script in a real-world environment after testing, an AI worker is generated. This AI worker is a virtual worker that automatically performs specific tasks based on the script.

[0201] Step 8:

[0202] Terminal and Server

[0203] An AI worker performs a specific task according to a schedule, for example, starting data entry work at a specific time each day and sending the results as a log to a server after completion.

[0204] Step 9:

[0205] server

[0206] The execution results and emotional data are analyzed again to provide real-time feedback to the user. If the user's stress level is high, the system will recommend taking a break or suggest adjustments to the work environment. The feedback information will also be reflected in the next script generation, optimizing the entire system.

[0207] Step 10:

[0208] server

[0209] Periodically, an analysis report of the execution results and emotional data is generated and provided to users and managers. The report includes information such as how much work efficiency has improved and how stress levels have changed. Based on this, if further improvements are needed, the script can be updated or the AI ​​workers adjusted.

[0210] Example 2

[0211] 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."

[0212] Modern companies are required to improve employee work efficiency while reducing employee stress levels and providing a comfortable work environment. However, conventional systems do not adequately automate work tasks or optimize work processes by taking into account the emotional state of employees. This has resulted in problems such as poor work efficiency and the accumulation of employee stress.

[0213] 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.

[0214] In this invention, the server includes means for collecting employee operation logs and emotional data, means for saving the collected operation logs and emotional data, means for analyzing the saved operation logs and emotional data to detect common tasks and stress levels, means for generating a script to automate the detected common tasks, means for generating an AI worker who executes the generated script, means for the AI ​​worker to perform a specific task, and means for providing feedback in real time based on the emotional data. This makes it possible to efficiently automate employee work tasks while optimizing work processes taking into account the emotional states of employees.

[0215] An "operation log" is data that records the operations performed on devices used by employees, application usage status, timestamps, input content, etc.

[0216] "Emotion data" refers to data including biometric information such as the user's facial expression, voice tone, and heart rate, and represents the user's emotional state.

[0217] "Means for collection" refers to a function or device for acquiring operation logs and emotional data from a terminal and storing them as data.

[0218] "Storage means" refers to a function or device that stores collected operation logs and emotion data in a database or recording device.

[0219] "Means for analysis" refers to algorithms and programs that process saved operation logs and emotional data to detect common tasks and stress levels.

[0220] "Common work" refers to business tasks that are commonly performed by multiple employees.

[0221] "Script generation means" refers to a program or algorithm that generates instructions or code to automate the common tasks detected.

[0222] An "artificial intelligence worker" is a virtual worker that executes the generated automation script and is a system that automatically executes specific tasks.

[0223] "Means for providing feedback in real time" refers to a function or device that provides immediate improvement suggestions or advice to the user based on emotional data or work results.

[0224] This invention is a system that simultaneously collects and analyzes employees' PC operation logs and emotional states, automating common work tasks. This not only improves work efficiency but also reduces employees' stress levels, providing a more comfortable working environment.

[0225] Installing the Agent Software

[0226] First, the user installs agent software on their device. This agent software has the ability to collect PC operation logs and emotional data in real time. Specifically, the operation log records application usage, operation details, timestamps, input details, etc., while the emotional data is collected by using a webcam and microphone to collect biometric information such as the user's facial expressions, voice tone, and heart rate.

[0227] Data collection and transmission

[0228] The device encrypts the operation logs and emotion data collected by the agent software and periodically sends them to the server using powerful encryption technology such as AES-256, with the data being sent in batches, for example, every hour.

[0229] Data storage and analysis

[0230] The server stores the received data in a database. Using a database management system (DBMS), the data is organized into an easily accessible format. The server then uses machine learning algorithms and natural language processing techniques to analyze the stored operation logs and emotion data. Common work tasks are extracted from the operation logs, and the emotion data is used to evaluate the stress and fatigue levels that specific tasks cause to users. Python's scikit-learn and TensorFlow are used for the analysis.

[0231] Generating automation scripts

[0232] Based on the analysis results, the server generates a script for automation. This script contains specific steps for efficiently performing common tasks. For example, a script for automating the creation of sales reports contains instructions for automatically entering data into a template file and automatically uploading it to a specified folder. The following prompt is input into the generative AI model to generate a script: "Please generate an automation script that creates a sales report and uploads it to a specific folder."

[0233] AI worker generation and execution

[0234] The server generates an AI worker to execute the generated script. This AI worker automatically executes specific tasks according to a schedule. For example, it is set to create and upload a sales report every Friday at 10:00 AM. The AI ​​worker executes the task and sends the results to the server as a log.

[0235] Providing emotional feedback

[0236] Finally, the server comprehensively analyzes the user's emotional data and the AI ​​worker's performance results and provides real-time feedback. For example, if the user indicates a high stress level, a notification recommending a break will be sent. This feedback will also be reflected in the next script generation, further optimizing the entire system. For example, a notification saying "Your stress level is high, so we recommend you take a break" will be displayed on the user's screen.

[0237] As described above, the present invention simultaneously improves business efficiency and manages the emotional state of employees, thereby improving productivity across the entire company.

[0238] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0239] Step 1:

[0240] The user installs agent software on their device. This agent software collects operation logs, such as application usage, operation details, timestamps, and input details, as well as emotional data, such as the user's facial expressions, voice tone, and heart rate, in real time using a webcam and microphone. The input is the installation of the agent software, and the output is the start of collection of operation logs and emotional data.

[0241] Step 2:

[0242] The terminal encrypts the operation log and emotion data collected by the agent software. Specifically, it uses a strong encryption technique such as AES-256. The encrypted data is then sent to the server at regular intervals (for example, every hour). The input is the collected operation log and emotion data, and the output is the encrypted data sent to the server.

[0243] Step 3:

[0244] The server receives the encrypted data, decrypts it, and stores it in a database. Specifically, it uses a database management system (DBMS) to organize the data and make it more accessible. The input is the encrypted data, and the output is the raw data stored in the database.

[0245] Step 4:

[0246] The server analyzes the stored operation logs and emotion data. Specific operations include machine learning algorithms such as Python's scikit-learn and TensorFlow, as well as natural language processing technology. Common work tasks are extracted from the operation logs, and the emotion data is used to evaluate the stress and fatigue levels that specific tasks cause to users. The input is the operation logs and emotion data stored in the database, and the output is the detection results of common tasks and stress levels.

[0247] Step 5:

[0248] The server generates an automation script based on the analysis results. The following prompt is input to the generative AI model: "Please generate an automation script to create a sales report and upload it to a specific folder." The output of the generated script contains specific steps for efficiently performing common tasks. The input is the common tasks and stress level detection results, and the output is the automation script.

[0249] Step 6:

[0250] The server generates an AI worker to execute the generated script. This AI worker automatically executes specific tasks according to a schedule. For example, it is set to create and upload a sales report every Friday at 10:00 AM. The AI ​​worker executes the task and sends the results as a log to the server. The input is the automation script, and the output is the task execution results and log.

[0251] Step 7:

[0252] The server comprehensively analyzes the user's emotional data and the AI ​​worker's performance results and provides real-time feedback. Specifically, if stress levels are rising, it sends a notification recommending a break. The input is the emotional data and a log of the performance results, and the output is a feedback notification. For example, a message such as "Your stress level is high, so we recommend you take a break" is displayed on the user's screen.

[0253] Through the above steps, the present invention can simultaneously improve work efficiency and manage the emotional state of employees, thereby improving the productivity of the entire company.

[0254] (Application example 2)

[0255] 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."

[0256] Conventional factory quality inspection processes rely on manual work, resulting in problems such as reduced work efficiency, manual errors, and increased employee stress. Furthermore, improvements to the work environment have not been made with consideration for the emotional state of employees, making it difficult to improve the work environment. Therefore, there is a need for a method to improve the efficiency of the quality inspection process, reduce employee stress, and optimize the work environment.

[0257] 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.

[0258] In this invention, the server includes means for collecting employee operation logs, means for saving the collected operation logs, means for analyzing the saved operation logs and detecting common tasks, means for generating scripts to automate the detected common tasks, means for generating AI workers to execute the generated scripts, means for collecting and encrypting operation logs and employee emotion data related to robots that perform quality inspections in factories and sending them to a cloud server, means for analyzing the operation logs and emotion data using a machine learning algorithm in the cloud server to optimize the quality inspection process, and means for generating optimized automation scripts and for the AI ​​workers to execute the quality inspection process. This enables the automation and optimization of the quality inspection process, reducing employee stress and improving the work environment.

[0259] An "operation log" is a series of operation history recorded when an employee operates a PC or robot, and includes application usage status, input content, and timestamps.

[0260] "Emotional data" refers to data about an employee's emotional state analyzed based on biometric information such as facial expressions, voice tone, and heart rate.

[0261] An "automation script" is a program procedure manual that is generated to automatically execute a specific task based on the analyzed operation log.

[0262] An "AI worker" is a virtual worker that performs work based on an automation script, an artificial intelligence-based system that performs specific tasks automatically.

[0263] A "cloud server" is a remote server that stores and processes data via the Internet, and is used to store and analyze collected operation logs and emotion data.

[0264] "Quality inspection process" refers to a series of work procedures for checking and evaluating the quality of products and services, including inspection work carried out within the factory.

[0265] A "machine learning algorithm" is a computational algorithm that automatically learns patterns and rules from large amounts of data and uses them to make predictions and analyses.

[0266] First, agent software is installed on the robots and the terminals used by workers in the factory. This agent software is responsible for collecting the robot's operation log and the employee's emotional data. The operation log includes the robot's movements, setting values, timestamps, error messages, etc., while the emotional data includes the employee's facial expressions, voice tone, heart rate, and other biometric information.

[0267] The operation logs and emotion data collected by the agent software are encrypted and sent via a local server in the factory to a cloud server, which then stores the received data in a database and uses it for data analysis.

[0268] The cloud server analyzes the stored operation logs and emotion data using machine learning algorithms and natural language processing technology, which enables it to detect common tasks in the quality inspection process and the stress levels of employees associated with those tasks.

[0269] Based on the detected common tasks, the cloud server then generates scripts to automate the quality inspection process, optimizing the efficiency of areas that are particularly stressful for employees, and distributes the scripts to robots that act as AI workers.

[0270] The AI ​​worker robot automatically executes the quality inspection process according to the generated script, and once the quality inspection is complete, the results are sent to the cloud server via the local server and stored in a database.

[0271] The cloud server also provides real-time feedback on employee emotional data and the AI ​​worker's performance. If an employee's stress level increases, the system can recommend a break or adjust the work environment. This feedback is then reflected in the next script generation, further optimizing the overall system.

[0272] As a concrete example, consider a case where a particular inspection in a factory is extremely stressful for employees. In this case, the agent software collects operation logs and emotional data, which are then analyzed by a cloud server. Based on the analysis results, a script is generated to automate the stressful inspection process, which is then executed by an AI worker, reducing the burden on the employees.

[0273] An example of a prompt for a generative AI model is:

[0274] Generate automation scripts to streamline the quality inspection process based on given operation logs and sentiment data, with a particular focus on optimizing areas that cause high levels of stress for employees.

[0275] In this way, it is possible to automate the quality inspection process and optimize the emotional state of employees at the same time.

[0276] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0277] Step 1:

[0278] Installing the Agent Software

[0279] Agent software is installed on factory robots and employee devices, allowing for the collection of operation logs and emotional data.

[0280] Input: Agent software, robots and terminals

[0281] Output: Terminal and robot ready to collect data

[0282] Step 2:

[0283] Starting Data Collection

[0284] The agent software begins collecting the robot's operation logs and employee emotional data. The operation logs include the robot's movements, settings, timestamps, error messages, etc. Emotional data is obtained from facial expressions, voice tone, heart rate, etc.

[0285] Input: Robot operation status, employee emotional state

[0286] Output: Collected operation logs and emotion data

[0287] Step 3:

[0288] Data encryption and transmission

[0289] The agent software encrypts the operation logs and emotional data collected and sends them to a cloud server via a local server in the factory.

[0290] Input: Collected operation logs and emotion data

[0291] Output: Encrypted operation log and emotion data, cloud server

[0292] Step 4:

[0293] Saving to a database

[0294] The cloud server receives the encrypted operation log and emotion data and stores them in a database.

[0295] Input: Encrypted operation log and emotion data

[0296] Output: Operation logs and emotion data stored in a database

[0297] Step 5:

[0298] Data analysis

[0299] The cloud server uses machine learning algorithms and natural language processing technology to analyze the stored operation logs and emotion data, and through this analysis, detects common tasks and stress levels during the quality inspection process.

[0300] Input: Operation log and emotion data

[0301] Output: Analysis results (detection of common tasks, evaluation of stress level)

[0302] Step 6:

[0303] Generating automation scripts

[0304] Based on the analysis results, the cloud server generates scripts to automate the quality inspection process, which are optimized to streamline particularly high-stress areas.

[0305] Input: Analysis results

[0306] Output: Automation script

[0307] Step 7:

[0308] Distributing scripts to AI workers

[0309] The cloud server distributes the generated automation script to the robots, which then function as AI workers.

[0310] Input: Automation script

[0311] Output: A robot that acts as an AI worker

[0312] Step 8:

[0313] Automatic execution of quality inspection processes

[0314] AI workers follow the generated script and automatically carry out the quality inspection process.

[0315] Input: Automation script

[0316] Output: Quality inspection results, robot execution log

[0317] Step 9:

[0318] Sending and saving results

[0319] Once the AI ​​worker completes the quality inspection, the results and execution log are sent to the cloud server via the local server and stored in a database.

[0320] Input: Quality inspection results, robot execution log

[0321] Output: Execution results and logs stored in a database

[0322] Step 10:

[0323] Real-time feedback

[0324] The cloud server analyzes employee emotional data and the AI ​​worker's performance, providing real-time feedback. If an employee's stress level is increasing, the system will recommend taking a break or adjust the work environment.

[0325] Input: Emotion data, execution results

[0326] Output: Feedback (recommendation of breaks, adjustment of work environment)

[0327] This allows for the automation of quality inspection processes and the optimization of the emotional state of employees.

[0328] 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.

[0329] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0330] 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.

[0331] [Second embodiment]

[0332] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0333] 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.

[0334] 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).

[0335] 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.

[0336] 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.

[0337] 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).

[0338] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0339] 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.

[0340] 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.

[0341] 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.

[0342] 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.

[0343] 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."

[0344] The system of this invention uses AI to analyze the PC work performed by employees, automatically discover common tasks, and automate them. This system will improve business efficiency and allow employees to focus on new challenges and ideas.

[0345] First, agent software is installed on employees' PCs. This agent software has the function of collecting employees' operation logs in real time. Specifically, it records opened applications, operation details, timestamps, input details, etc., and then encrypts and sends the data to the company's server. By collecting operation logs, the agent software makes it possible to record daily business activities.

[0346] Next, the server receives the operation logs sent from the devices and stores them in a database. The server then analyzes the stored data using machine learning algorithms and natural language processing technology. This analysis makes it possible to automatically detect tasks that are commonly performed by multiple employees, in other words, "common tasks." For example, tasks such as data entry, report creation, and email sending may be detected as common tasks.

[0347] For each common task detected, the server generates an automated script. This script describes a series of steps to perform the common task efficiently. The generated script is tested in a test environment, and after confirming there are no problems, it is implemented in actual business operations.

[0348] The server generates an AI worker to execute the generated script. This AI worker acts as a virtual worker and has the ability to perform specific tasks, such as automatically extracting and inputting data, generating reports, and managing files.

[0349] The generated AI workers run on terminals or remote servers to perform specific tasks. This improves operational efficiency by allowing AI workers to automatically perform common tasks, eliminating the need for employees to perform them manually. Employees are freed from time-consuming, duplicated tasks, allowing them to focus on other important tasks.

[0350] As a concrete example, consider a company that regularly requires large-scale data entry work. Employees spend a lot of time on this work. Agent software collects each employee's operation log, and the server analyzes the data to detect common data entry tasks. It then generates a script to automate the task, and an AI worker executes the script, automatically completing the data entry work. As a result, employees no longer need to manually perform data entry work, allowing them to focus on other tasks.

[0351] In this way, the system of the present invention can significantly improve business efficiency within a company and increase employee productivity.

[0352] The processing flow will be explained below.

[0353] Step 1:

[0354] Terminal

[0355] Agent software is installed on each employee's PC, which monitors the employee's PC operations in real time and collects data such as operations, applications used, timestamps, and input contents.

[0356] Step 2:

[0357] Terminal

[0358] The agent software encrypts the collected log data and sends it to the company's server at regular intervals (for example, every hour).

[0359] Step 3:

[0360] server

[0361] The company's server stores the received operation log data in a database, which stores each employee's operation log in chronological order and creates an index for subsequent analysis.

[0362] Step 4:

[0363] server

[0364] Machine learning algorithms are applied to the saved operation log data. Specifically, frequency analysis and pattern recognition are performed to extract tasks commonly performed by multiple employees. This includes detecting the frequency of use of specific applications and specific operation patterns.

[0365] Step 5:

[0366] server

[0367] Based on patterns and common tasks extracted by machine learning algorithms, a list of common tasks is created, including how many times each task is performed and which employee performed each task.

[0368] Step 6:

[0369] server

[0370] Scripts are automatically generated for the listed common tasks. These scripts contain procedures for efficiently executing common tasks by consolidating them into a single automated process. For example, for a data entry task, the scripts include steps such as extracting the data to be entered, entering the data into the input fields, and confirming and saving the final data.

[0371] Step 7:

[0372] server

[0373] Run the generated script in a test environment and check its operation. If there are any errors or areas for improvement, correct them and confirm that there are no problems.

[0374] Step 8:

[0375] server

[0376] Once the script has been tested, it is deployed in a real-world environment to generate an AI worker, which is then ready to automatically perform specific tasks based on the script.

[0377] Step 9:

[0378] Terminal and Server

[0379] The AI ​​worker performs specific tasks according to a schedule, for example, starting data entry work at a specific time each day, saving the results after completion, and sending the logs to a server.

[0380] Step 10:

[0381] server

[0382] The execution results are recorded in a log and periodically analyzed to evaluate the degree of operational efficiency achieved. Based on these results, if further improvements are needed, the scripts are updated or the AI ​​workers are adjusted.

[0383] Example 1

[0384] 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."

[0385] The problem that this invention aims to solve is to improve business efficiency by automatically detecting duplicate work by employees in a company and efficiently automating it. Conventional systems only support manual work recording and individual automation, making it difficult to optimize the entire business process. In addition, the accuracy of analysis results and the accuracy of automation have also been problematic.

[0386] 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.

[0387] In this invention, the server includes means for collecting employee operation logs, means for saving the collected operation logs, means for analyzing the saved operation logs and detecting common tasks, means for generating scripts to automate the detected common tasks, means for verifying the operation of the generated scripts in a test environment, means for generating AI workers to execute the generated scripts, and means for the generated AI workers to execute specific tasks. This makes it possible to automatically detect duplicate tasks in the daily work performed by employees and to efficiently automate those tasks.

[0388] An "employee operation log" is a history of operations performed by employees on devices such as PCs, and includes the names of applications opened, operation details, timestamps, input details, etc.

[0389] "Log collection means" refers to software or hardware that collects employee operation logs in real time, encrypts them, and sends them to a server.

[0390] "Log storage means" refers to a mechanism for storing collected operation logs in a storage device such as a database.

[0391] "Log analysis means" refers to a method or device for analyzing stored operation logs using machine learning algorithms or natural language processing techniques to detect common tasks.

[0392] "Common tasks" refer to similar or identical tasks performed by multiple employees, such as data entry, report creation, and email sending.

[0393] "Script generator" refers to a method or apparatus for programming and generating, in script form, procedures for automating detected common tasks.

[0394] A "test environment" refers to a virtual or sandbox environment in which generated scripts can be verified to work correctly.

[0395] "AI worker" refers to artificial intelligence that executes generated scripts and automatically performs specific tasks as a virtual worker.

[0396] "Task execution means" refers to a method or device by which an AI worker performs a particular task.

[0397] The system of this invention analyzes the PC work performed by employees, automatically discovers common tasks, and provides a new means of automating those tasks. The aim is to improve business efficiency in companies, allowing employees to focus on new challenges and ideas.

[0398] First, the user (employee) installs agent software on their PC. This agent software has the function of collecting the employee's operation log in real time. Specifically, it collects the names of open applications, operation details, timestamps, input details, etc. This operation log is encrypted and sent to the company's server.

[0399] Next, the server receives the operation logs sent from the terminals and stores them in a database, which can be managed using a database management system such as MySQL or PostgreSQL.

[0400] The server analyzes the saved operation log data. This analysis is performed using the Python libraries TensorFlow and Scikit-learn. First, the data is preprocessed to extract the necessary features. Next, a machine learning algorithm is applied based on the extracted features to detect patterns of common tasks. Natural language processing technology is also used to analyze text information within the log data.

[0401] The server generates scripts to automate the detected common tasks. Specifically, the procedures for the common tasks are written as scripts using Python or RPA tools (UiPath or Automation Anywhere). The generated scripts are first tested in a test environment. A virtual environment or sandbox environment is used to verify that the scripts work correctly.

[0402] The server then generates an AI worker to execute the generated script. This AI worker acts as a virtual worker and performs specific tasks, such as automatically extracting and inputting data, generating reports, and managing files. The AI ​​worker runs on a terminal or a remote server.

[0403] The generated AI workers automatically perform common tasks, freeing users (employees) from duplicated tasks that they would otherwise perform manually, allowing them to focus on other important tasks and improving work efficiency.

[0404] Examples:

[0405] Suppose a company regularly needs to perform large-scale data entry tasks. Employees spend a lot of time on this task. Agent software collects each employee's operation log, and the server analyzes the data to detect common data entry tasks. It then generates a script to automate the task, and an AI worker executes the script, automatically completing the data entry tasks. As a result, employees no longer need to manually perform data entry tasks, allowing them to focus on other tasks.

[0406] Example prompt sentence:

[0407] Analyze employee operation logs to detect common tasks and generate scripts to automate them. Write scripts using Python or RPA tools (UiPath, Automation Anywhere) to generate AI workers to perform the tasks.

[0408] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0409] Step 1: Installing the agent software and collecting operation logs

[0410] A user installs agent software on their PC. This agent software has the ability to collect all operation logs in real time. Specifically, it collects information such as the names of applications opened on the PC, operation details, timestamps, and entered data. These operation logs are encrypted and sent to a server in a secure format.

[0411] Input: User operation (application name, operation content, timestamp, input data)

[0412] Output: Encrypted operation log data

[0413] Step 2: Receiving and saving the operation log

[0414] The server receives the operation logs sent from the terminal. The received operation logs are stored in a database. A database management system such as MySQL or PostgreSQL can be used. During this process, data consistency checks and duplicate elimination processes are performed.

[0415] Input: Encrypted operation log data

[0416] Output: Operation log stored in the database

[0417] Step 3: Analyze the operation log

[0418] The server analyzes the saved operation log data. This analysis is performed using the Python libraries TensorFlow and Scikit-learn. The data is preprocessed to extract the necessary features. Next, a machine learning algorithm is applied based on the extracted features to detect patterns of common tasks. Natural language processing technology is also used to analyze the text data.

[0419] Input: Operation logs stored in the database

[0420] Output: Generated common work pattern

[0421] Step 4: Generate and test scripts

[0422] The server generates a script for automation based on the analysis results. Specifically, it uses Python or an RPA tool (e.g., UiPath or Automation Anywhere) to program the procedures for common tasks. The generated script is first tested in a test environment, which can be a virtual environment or a sandbox environment.

[0423] Input: Detected common work patterns

[0424] Output: Generated automation script

[0425] Step 5: Generate AI workers and execute tasks

[0426] The server generates an AI worker to execute the generated script. This AI worker performs specific tasks as a virtual worker. Specifically, it automatically performs business operations such as data extraction and input, report generation, and file management. The AI ​​worker runs on a terminal or a remote server.

[0427] Input: Generated automation script

[0428] Output: The automated task that will be executed

[0429] Step 6: Improve operational efficiency through automation

[0430] Users (employees) are freed from manual, duplicated tasks by having AI workers automatically perform common tasks, allowing employees to focus on other important tasks and improving work efficiency.

[0431] Input: The automated task to be executed

[0432] Output: Streamlined business processes

[0433] (Application example 1)

[0434] 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."

[0435] There is a need to significantly improve operational efficiency by automating common tasks performed by employees on a daily basis. In particular, logistics centers have a large number of manual tasks, such as inventory management and picking, and there is an urgent need to streamline these tasks. In addition, there is a need to reduce the burden on employees by automating tasks using smart devices and promote the smooth progress of operations.

[0436] 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.

[0437] In this invention, the server includes: means for collecting employee operation logs; means for saving the collected operation logs; means for analyzing the saved operation logs and detecting common tasks; means for generating scripts to automate the detected common tasks; means for generating AI workers to execute the generated scripts; means for the generated AI workers to perform specific tasks; means including a smart device for analyzing the operation logs and issuing commands to execute the automation scripts; means for analyzing common tasks from employee operation logs using a machine learning algorithm; means for extracting tasks for improving efficiency from log information using natural language processing technology; means for automatically updating inventory data using the camera function of the smart device; and means for analyzing common tasks and proposing optimal product picking routes. This enables efficient inventory management and picking operations at logistics centers by analyzing employee operation logs in detail and generating automation scripts.

[0438] An "employee operation log" is a record of operations performed by employees, and specifically includes application usage information, operation details, timestamps, input data, and the like.

[0439] "Means for collecting operation logs" refers to software or hardware for collecting and recording employee operation logs in real time.

[0440] The "means for storing operation logs" refers to a database or storage system for appropriately storing collected operation logs.

[0441] A "means for detecting common tasks" is an algorithm or program that analyzes and finds tasks that are commonly performed by multiple employees.

[0442] The "means for generating scripts for automation" is software that generates scripts for automatically executing common tasks based on specific procedures.

[0443] An "artificial intelligence worker" is a virtual worker that automatically executes specific tasks based on a generated script.

[0444] A "smart device" is a device that can connect to the Internet, such as a smartphone, tablet, or smart glasses, and is used to collect operation logs and execute scripts.

[0445] A "machine learning algorithm" is an algorithm that learns patterns from large amounts of data and detects common tasks.

[0446] "Natural language processing technology" is a technology for analyzing text data and understanding the meaning of language.

[0447] The "means for automatically updating inventory data" is a system that uses the camera function of a smart device to scan information about inventory items and automatically update the database.

[0448] The "means for proposing the optimal picking route" is an algorithm that proposes the optimal route for efficiently picking products within a logistics center.

[0449] The system of this invention aims to improve the efficiency of operations at logistics centers. In particular, it is possible to significantly improve the work efficiency of logistics centers by analyzing employee operation logs and automating common tasks.

[0450] The system of the present invention begins with the installation of agent software on employees' smart devices (e.g., smartphones, tablets). This agent software collects operational logs of employees' daily work in real time and stores them in a database. Specifically, application usage information, operation details, timestamps, and other information are collected as logs.

[0451] The server analyzes the collected operation logs using machine learning algorithms and natural language processing technology to automatically detect tasks performed by multiple employees (common tasks), such as inventory checks, data entry, and creating picking lists.

[0452] The server generates an automation script for each common task that is detected. This script describes a series of steps to perform the common task efficiently. The generated script is tested in a test environment, and once no problems are confirmed, it is implemented in the actual business.

[0453] The generated scripts are then executed by an AI worker, who has the ability to automatically perform certain tasks, such as automatically updating inventory or suggesting optimal routes for picking lists. The AI ​​worker can also use the camera function of a smart device to scan QR codes on inventory items and automatically update the database.

[0454] As a concrete example, consider inventory management at a logistics center. Employees can scan the QR codes of inventory items with their smart devices, automatically updating inventory data. Furthermore, when picking items, AI workers can suggest optimal picking routes, improving employee efficiency.

[0455] An example of a prompt is "Implement a QR code scanning function to streamline inventory management," which would enable more efficient inventory management using smart devices.

[0456] In this way, the system of the present invention can significantly improve the operational efficiency of a logistics center, reduce the burden on employees, and increase productivity.

[0457] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0458] Step 1:

[0459] A user starts work using a smart device. Agent software is installed on the smart device and collects the user's operation logs in real time. The collected operation logs include application usage information, operation details, timestamps, etc. This log data is encrypted and sent to the server. The input is the user's operation, and the output is the operation log.

[0460] Step 2:

[0461] The server stores the operation logs it receives in a database. The server then converts the operation logs into a format that is easy to analyze and stores them. Specific data processing includes timestamp format conversion and input content classification. The input is encrypted operation logs, and the output is operation log data converted into a standard format for analysis.

[0462] Step 3:

[0463] The server uses a machine learning algorithm to analyze the stored operation logs. It classifies and clusters the data to detect common tasks. Specifically, it identifies patterns of operations frequently performed by employees and recognizes them as common tasks. The input is operation log data in a standard format, and the output is a list of detected common tasks.

[0464] Step 4:

[0465] The server uses natural language processing technology to perform a detailed analysis of common tasks. Specifically, it understands the intent behind the operation procedures and instructions from the text data in the operation log. This analysis generates a script to efficiently automate the common tasks. The input is a list of common tasks, and the output is an automation script.

[0466] Step 5:

[0467] The server builds an AI worker based on the generated script. The AI ​​worker is a program that automatically executes specific tasks based on the generated script. The input is the automation script, and the output is the AI ​​worker program.

[0468] Step 6:

[0469] An AI worker starts working on a smart device. For example, the smart device's camera scans a QR code and automatically updates inventory data. An algorithm is also run to suggest the optimal route for the picking list. The inputs are inventory items and picking data, and the output is the updated inventory data and the suggested picking route.

[0470] An example of a prompt is "Implement a QR code scanning function to streamline inventory management," which would enable efficient inventory management using smart devices.

[0471] The above is the specific processing flow of the system for realizing the application example.

[0472] 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.

[0473] This invention is a system that simultaneously collects and analyzes employees' PC operation logs and emotional states, and automates common work tasks. This system not only improves work efficiency but also reduces employees' stress levels, providing a more comfortable working environment.

[0474] Overall system configuration

[0475] First, agent software is installed on the user's device. This agent software uses an emotion engine to collect emotional data in real time, along with the user's PC operation log. The operation log includes application usage, operation details, timestamps, and input details. Emotional data includes biometric information such as the user's facial expression, voice tone, and heart rate.

[0476] Data collection

[0477] The agent software encrypts the collected operation logs and emotional data and periodically transmits them to the company's server, which stores the received data in a database for subsequent analysis.

[0478] Data analysis

[0479] The server analyzes the stored operation logs and emotional data using machine learning algorithms and natural language processing technology. This analysis detects common tasks performed by multiple employees. Analysis of the emotional data also makes it possible to evaluate the level of stress and fatigue that a particular task causes to the user.

[0480] Generating automation scripts

[0481] Based on the detected common tasks, the server generates an automation script. This script combines the common tasks into a single process and includes instructions for efficient execution. Furthermore, the script can be adjusted based on the user's emotional data. For example, if a particular task causes high stress, the script can be optimized to perform the task in a more efficient manner.

[0482] AI worker generation and execution

[0483] The server generates an AI worker to execute the generated script. This AI worker is a virtual worker that automatically performs specific tasks. The AI ​​worker executes the task according to a schedule and sends the results to the server as a log. This eliminates the need for employees to perform the task manually, improving work efficiency.

[0484] Emotional Feedback

[0485] The server analyzes the user's emotional data and the AI ​​worker's performance results, and provides real-time feedback. For example, it can recommend a break if the user is feeling stressed, or suggest adjustments to the work environment. This feedback is also reflected in the next script generation, further optimizing the entire system.

[0486] Specific examples

[0487] For example, a company regularly creates sales reports and uploads them to a shared folder. Employees spend a lot of time on this task, and they often find it particularly stressful. The agent software collects each employee's operation log and emotional data, such as facial expressions and voice tone, and the server analyzes them. The software then detects common tasks involved in creating sales reports and uploading them to the folder, generating a script to automate the task. This script is optimized to reduce stress, and an AI worker executes it, improving work efficiency while reducing employee stress. Repeating this entire process simultaneously improves the company's operational efficiency and employee satisfaction.

[0488] As described above, the system of the present invention simultaneously improves business efficiency and manages the emotional state of employees, thereby improving productivity across the entire company.

[0489] The processing flow will be explained below.

[0490] Step 1:

[0491] Terminal

[0492] Agent software is installed on each employee's PC. The agent software collects the employee's PC operation log and emotional data in real time. The operation log includes the application used, operation details, timestamp, and input content. Emotional data includes facial expressions, voice tone, heart rate, etc.

[0493] Step 2:

[0494] Terminal

[0495] The agent software encrypts the collected operation logs and emotional data and sends them to the company's server at regular intervals (for example, every hour).

[0496] Step 3:

[0497] server

[0498] The company's server stores the received operation logs and emotion data in a database. The database stores each employee's operation log and emotion data in chronological order and creates an index to facilitate search and analysis.

[0499] Step 4:

[0500] server

[0501] Machine learning algorithms and natural language processing technology are applied to the saved operation logs and emotion data. Based on the operation data, frequency analysis and pattern recognition are performed to detect tasks that are commonly performed by multiple employees (common tasks). At the same time, emotion data is analyzed to evaluate the stress level during specific tasks.

[0502] Step 5:

[0503] server

[0504] Based on the analysis results, a list of identified common tasks is created, and an automation script is generated based on the list. The automation script includes a series of steps to efficiently execute the detected common tasks. Furthermore, optimization is performed to reduce stress levels during work based on emotion data.

[0505] Step 6:

[0506] server

[0507] Run the generated script in a test environment to check its operation. Test whether the script has errors and runs as expected. Fix any defects or areas for improvement that are found.

[0508] Step 7:

[0509] server

[0510] To operate the script in a real-world environment after testing, an AI worker is generated. This AI worker is a virtual worker that automatically performs specific tasks based on the script.

[0511] Step 8:

[0512] Terminal and Server

[0513] An AI worker performs a specific task according to a schedule, for example, starting data entry work at a specific time each day and sending the results as a log to a server after completion.

[0514] Step 9:

[0515] server

[0516] The execution results and emotional data are analyzed again to provide real-time feedback to the user. If the user's stress level is high, the system will recommend taking a break or suggest adjustments to the work environment. The feedback information will also be reflected in the next script generation, optimizing the entire system.

[0517] Step 10:

[0518] server

[0519] Periodically, an analysis report of the execution results and emotional data is generated and provided to users and managers. The report includes information such as how much work efficiency has improved and how stress levels have changed. Based on this, if further improvements are needed, the script can be updated or the AI ​​workers adjusted.

[0520] Example 2

[0521] 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."

[0522] Modern companies are required to improve employee work efficiency while reducing employee stress levels and providing a comfortable work environment. However, conventional systems do not adequately automate work tasks or optimize work processes by taking into account the emotional state of employees. This has resulted in problems such as poor work efficiency and the accumulation of employee stress.

[0523] 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.

[0524] In this invention, the server includes means for collecting employee operation logs and emotional data, means for saving the collected operation logs and emotional data, means for analyzing the saved operation logs and emotional data to detect common tasks and stress levels, means for generating a script to automate the detected common tasks, means for generating an AI worker who executes the generated script, means for the AI ​​worker to perform a specific task, and means for providing feedback in real time based on the emotional data. This makes it possible to efficiently automate employee work tasks while optimizing work processes taking into account the emotional states of employees.

[0525] An "operation log" is data that records the operations performed on devices used by employees, application usage status, timestamps, input content, etc.

[0526] "Emotion data" refers to data including biometric information such as the user's facial expression, voice tone, and heart rate, and represents the user's emotional state.

[0527] "Means for collection" refers to a function or device for acquiring operation logs and emotional data from a terminal and storing them as data.

[0528] "Storage means" refers to a function or device that stores collected operation logs and emotion data in a database or recording device.

[0529] "Means for analysis" refers to algorithms and programs that process saved operation logs and emotional data to detect common tasks and stress levels.

[0530] "Common work" refers to business tasks that are commonly performed by multiple employees.

[0531] "Script generation means" refers to a program or algorithm that generates instructions or code to automate the common tasks detected.

[0532] An "artificial intelligence worker" is a virtual worker that executes the generated automation script and is a system that automatically executes specific tasks.

[0533] "Means for providing feedback in real time" refers to a function or device that provides immediate improvement suggestions or advice to the user based on emotional data or work results.

[0534] This invention is a system that simultaneously collects and analyzes employees' PC operation logs and emotional states, automating common work tasks. This not only improves work efficiency but also reduces employees' stress levels, providing a more comfortable working environment.

[0535] Installing the Agent Software

[0536] First, the user installs agent software on their device. This agent software has the ability to collect PC operation logs and emotional data in real time. Specifically, the operation log records application usage, operation details, timestamps, input details, etc., while the emotional data is collected by using a webcam and microphone to collect biometric information such as the user's facial expressions, voice tone, and heart rate.

[0537] Data collection and transmission

[0538] The device encrypts the operation logs and emotion data collected by the agent software and periodically sends them to the server using powerful encryption technology such as AES-256, with the data being sent in batches, for example, every hour.

[0539] Data storage and analysis

[0540] The server stores the received data in a database. Using a database management system (DBMS), the data is organized into an easily accessible format. The server then uses machine learning algorithms and natural language processing techniques to analyze the stored operation logs and emotion data. Common work tasks are extracted from the operation logs, and the emotion data is used to evaluate the stress and fatigue levels that specific tasks cause to users. Python's scikit-learn and TensorFlow are used for the analysis.

[0541] Generating automation scripts

[0542] Based on the analysis results, the server generates a script for automation. This script contains specific steps for efficiently performing common tasks. For example, a script for automating the creation of sales reports contains instructions for automatically entering data into a template file and automatically uploading it to a specified folder. The following prompt is input into the generative AI model to generate a script: "Please generate an automation script that creates a sales report and uploads it to a specific folder."

[0543] AI worker generation and execution

[0544] The server generates an AI worker to execute the generated script. This AI worker automatically executes specific tasks according to a schedule. For example, it is set to create and upload a sales report every Friday at 10:00 AM. The AI ​​worker executes the task and sends the results to the server as a log.

[0545] Providing emotional feedback

[0546] Finally, the server comprehensively analyzes the user's emotional data and the AI ​​worker's performance results and provides real-time feedback. For example, if the user indicates a high stress level, a notification recommending a break will be sent. This feedback will also be reflected in the next script generation, further optimizing the entire system. For example, a notification saying "Your stress level is high, so we recommend you take a break" will be displayed on the user's screen.

[0547] As described above, the present invention simultaneously improves business efficiency and manages the emotional state of employees, thereby improving productivity across the entire company.

[0548] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0549] Step 1:

[0550] The user installs agent software on their device. This agent software collects operation logs, such as application usage, operation details, timestamps, and input details, as well as emotional data, such as the user's facial expressions, voice tone, and heart rate, in real time using a webcam and microphone. The input is the installation of the agent software, and the output is the start of collection of operation logs and emotional data.

[0551] Step 2:

[0552] The terminal encrypts the operation log and emotion data collected by the agent software. Specifically, it uses a strong encryption technique such as AES-256. The encrypted data is then sent to the server at regular intervals (for example, every hour). The input is the collected operation log and emotion data, and the output is the encrypted data sent to the server.

[0553] Step 3:

[0554] The server receives the encrypted data, decrypts it, and stores it in a database. Specifically, it uses a database management system (DBMS) to organize the data and make it more accessible. The input is the encrypted data, and the output is the raw data stored in the database.

[0555] Step 4:

[0556] The server analyzes the stored operation logs and emotion data. Specific operations include machine learning algorithms such as Python's scikit-learn and TensorFlow, as well as natural language processing technology. Common work tasks are extracted from the operation logs, and the emotion data is used to evaluate the stress and fatigue levels that specific tasks cause to users. The input is the operation logs and emotion data stored in the database, and the output is the detection results of common tasks and stress levels.

[0557] Step 5:

[0558] The server generates an automation script based on the analysis results. The following prompt is input to the generative AI model: "Please generate an automation script to create a sales report and upload it to a specific folder." The output of the generated script contains specific steps for efficiently performing common tasks. The input is the common tasks and stress level detection results, and the output is the automation script.

[0559] Step 6:

[0560] The server generates an AI worker to execute the generated script. This AI worker automatically executes specific tasks according to a schedule. For example, it is set to create and upload a sales report every Friday at 10:00 AM. The AI ​​worker executes the task and sends the results as a log to the server. The input is the automation script, and the output is the task execution results and log.

[0561] Step 7:

[0562] The server comprehensively analyzes the user's emotional data and the AI ​​worker's performance results and provides real-time feedback. Specifically, if stress levels are rising, it sends a notification recommending a break. The input is the emotional data and a log of the performance results, and the output is a feedback notification. For example, a message such as "Your stress level is high, so we recommend you take a break" is displayed on the user's screen.

[0563] Through the above steps, the present invention can simultaneously improve work efficiency and manage the emotional state of employees, thereby improving the productivity of the entire company.

[0564] (Application example 2)

[0565] 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."

[0566] Conventional factory quality inspection processes rely on manual work, resulting in problems such as reduced work efficiency, manual errors, and increased employee stress. Furthermore, improvements to the work environment have not been made with consideration for the emotional state of employees, making it difficult to improve the work environment. Therefore, there is a need for a method to improve the efficiency of the quality inspection process, reduce employee stress, and optimize the work environment.

[0567] 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.

[0568] In this invention, the server includes means for collecting employee operation logs, means for saving the collected operation logs, means for analyzing the saved operation logs and detecting common tasks, means for generating scripts to automate the detected common tasks, means for generating AI workers to execute the generated scripts, means for collecting and encrypting operation logs and employee emotion data related to robots that perform quality inspections in factories and sending them to a cloud server, means for analyzing the operation logs and emotion data using a machine learning algorithm in the cloud server to optimize the quality inspection process, and means for generating optimized automation scripts and for the AI ​​workers to execute the quality inspection process. This enables the automation and optimization of the quality inspection process, reducing employee stress and improving the work environment.

[0569] An "operation log" is a series of operation history recorded when an employee operates a PC or robot, and includes application usage status, input content, and timestamps.

[0570] "Emotional data" refers to data about an employee's emotional state analyzed based on biometric information such as facial expressions, voice tone, and heart rate.

[0571] An "automation script" is a program procedure manual that is generated to automatically execute a specific task based on the analyzed operation log.

[0572] An "AI worker" is a virtual worker that performs work based on an automation script, an artificial intelligence-based system that performs specific tasks automatically.

[0573] A "cloud server" is a remote server that stores and processes data via the Internet, and is used to store and analyze collected operation logs and emotion data.

[0574] "Quality inspection process" refers to a series of work procedures for checking and evaluating the quality of products and services, including inspection work carried out within the factory.

[0575] A "machine learning algorithm" is a computational algorithm that automatically learns patterns and rules from large amounts of data and uses them to make predictions and analyses.

[0576] First, agent software is installed on the robots and the terminals used by workers in the factory. This agent software is responsible for collecting the robot's operation log and the employee's emotional data. The operation log includes the robot's movements, setting values, timestamps, error messages, etc., while the emotional data includes the employee's facial expressions, voice tone, heart rate, and other biometric information.

[0577] The operation logs and emotion data collected by the agent software are encrypted and sent via a local server in the factory to a cloud server, which then stores the received data in a database and uses it for data analysis.

[0578] The cloud server analyzes the stored operation logs and emotion data using machine learning algorithms and natural language processing technology, which enables it to detect common tasks in the quality inspection process and the stress levels of employees associated with those tasks.

[0579] Based on the detected common tasks, the cloud server then generates scripts to automate the quality inspection process, optimizing the efficiency of areas that are particularly stressful for employees, and distributes the scripts to robots that act as AI workers.

[0580] The AI ​​worker robot automatically executes the quality inspection process according to the generated script, and once the quality inspection is complete, the results are sent to the cloud server via the local server and stored in a database.

[0581] The cloud server also provides real-time feedback on employee emotional data and the AI ​​worker's performance. If an employee's stress level increases, the system can recommend a break or adjust the work environment. This feedback is then reflected in the next script generation, further optimizing the overall system.

[0582] As a concrete example, consider a case where a particular inspection in a factory is extremely stressful for employees. In this case, the agent software collects operation logs and emotional data, which are then analyzed by a cloud server. Based on the analysis results, a script is generated to automate the stressful inspection process, which is then executed by an AI worker, reducing the burden on the employees.

[0583] An example of a prompt for a generative AI model is:

[0584] Generate automation scripts to streamline the quality inspection process based on given operation logs and sentiment data, with a particular focus on optimizing areas that cause high levels of stress for employees.

[0585] In this way, it is possible to automate the quality inspection process and optimize the emotional state of employees at the same time.

[0586] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0587] Step 1:

[0588] Installing the Agent Software

[0589] Agent software is installed on factory robots and employee devices, allowing for the collection of operation logs and emotional data.

[0590] Input: Agent software, robots and terminals

[0591] Output: Terminal and robot ready to collect data

[0592] Step 2:

[0593] Starting Data Collection

[0594] The agent software begins collecting the robot's operation logs and employee emotional data. The operation logs include the robot's movements, settings, timestamps, error messages, etc. Emotional data is obtained from facial expressions, voice tone, heart rate, etc.

[0595] Input: Robot operation status, employee emotional state

[0596] Output: Collected operation logs and emotion data

[0597] Step 3:

[0598] Data encryption and transmission

[0599] The agent software encrypts the operation logs and emotional data collected and sends them to a cloud server via a local server in the factory.

[0600] Input: Collected operation logs and emotion data

[0601] Output: Encrypted operation log and emotion data, cloud server

[0602] Step 4:

[0603] Saving to a database

[0604] The cloud server receives the encrypted operation log and emotion data and stores them in a database.

[0605] Input: Encrypted operation log and emotion data

[0606] Output: Operation logs and emotion data stored in a database

[0607] Step 5:

[0608] Data analysis

[0609] The cloud server uses machine learning algorithms and natural language processing technology to analyze the stored operation logs and emotion data, and through this analysis, detects common tasks and stress levels during the quality inspection process.

[0610] Input: Operation log and emotion data

[0611] Output: Analysis results (detection of common tasks, evaluation of stress level)

[0612] Step 6:

[0613] Generating automation scripts

[0614] Based on the analysis results, the cloud server generates scripts to automate the quality inspection process, which are optimized to streamline particularly high-stress areas.

[0615] Input: Analysis results

[0616] Output: Automation script

[0617] Step 7:

[0618] Distributing scripts to AI workers

[0619] The cloud server distributes the generated automation script to the robots, which then function as AI workers.

[0620] Input: Automation script

[0621] Output: A robot that acts as an AI worker

[0622] Step 8:

[0623] Automatic execution of quality inspection processes

[0624] AI workers follow the generated script and automatically carry out the quality inspection process.

[0625] Input: Automation script

[0626] Output: Quality inspection results, robot execution log

[0627] Step 9:

[0628] Sending and saving results

[0629] Once the AI ​​worker completes the quality inspection, the results and execution log are sent to the cloud server via the local server and stored in a database.

[0630] Input: Quality inspection results, robot execution log

[0631] Output: Execution results and logs stored in a database

[0632] Step 10:

[0633] Real-time feedback

[0634] The cloud server analyzes employee emotional data and the AI ​​worker's performance, providing real-time feedback. If an employee's stress level is increasing, the system will recommend taking a break or adjust the work environment.

[0635] Input: Emotion data, execution results

[0636] Output: Feedback (recommendation of breaks, adjustment of work environment)

[0637] This allows for the automation of quality inspection processes and the optimization of the emotional state of employees.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] [Third embodiment]

[0642] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0643] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0644] 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).

[0645] 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.

[0646] 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.

[0647] 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).

[0648] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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."

[0654] The system of this invention uses AI to analyze the PC work performed by employees, automatically discover common tasks, and automate them. This system will improve business efficiency and allow employees to focus on new challenges and ideas.

[0655] First, agent software is installed on employees' PCs. This agent software has the function of collecting employees' operation logs in real time. Specifically, it records opened applications, operation details, timestamps, input details, etc., and then encrypts and sends the data to the company's server. By collecting operation logs, the agent software makes it possible to record daily business activities.

[0656] Next, the server receives the operation logs sent from the devices and stores them in a database. The server then analyzes the stored data using machine learning algorithms and natural language processing technology. This analysis makes it possible to automatically detect tasks that are commonly performed by multiple employees, in other words, "common tasks." For example, tasks such as data entry, report creation, and email sending may be detected as common tasks.

[0657] For each common task detected, the server generates an automated script. This script describes a series of steps to perform the common task efficiently. The generated script is tested in a test environment, and after confirming there are no problems, it is implemented in actual business operations.

[0658] The server generates an AI worker to execute the generated script. This AI worker acts as a virtual worker and has the ability to perform specific tasks, such as automatically extracting and inputting data, generating reports, and managing files.

[0659] The generated AI workers run on terminals or remote servers to perform specific tasks. This improves operational efficiency by allowing AI workers to automatically perform common tasks, eliminating the need for employees to perform them manually. Employees are freed from time-consuming, duplicated tasks, allowing them to focus on other important tasks.

[0660] As a concrete example, consider a company that regularly requires large-scale data entry work. Employees spend a lot of time on this work. Agent software collects each employee's operation log, and the server analyzes the data to detect common data entry tasks. It then generates a script to automate the task, and an AI worker executes the script, automatically completing the data entry work. As a result, employees no longer need to manually perform data entry work, allowing them to focus on other tasks.

[0661] In this way, the system of the present invention can significantly improve business efficiency within a company and increase employee productivity.

[0662] The processing flow will be explained below.

[0663] Step 1:

[0664] Terminal

[0665] Agent software is installed on each employee's PC, which monitors the employee's PC operations in real time and collects data such as operations, applications used, timestamps, and input contents.

[0666] Step 2:

[0667] Terminal

[0668] The agent software encrypts the collected log data and sends it to the company's server at regular intervals (for example, every hour).

[0669] Step 3:

[0670] server

[0671] The company's server stores the received operation log data in a database, which stores each employee's operation log in chronological order and creates an index for subsequent analysis.

[0672] Step 4:

[0673] server

[0674] Machine learning algorithms are applied to the saved operation log data. Specifically, frequency analysis and pattern recognition are performed to extract tasks commonly performed by multiple employees. This includes detecting the frequency of use of specific applications and specific operation patterns.

[0675] Step 5:

[0676] server

[0677] Based on patterns and common tasks extracted by machine learning algorithms, a list of common tasks is created, including how many times each task is performed and which employee performed each task.

[0678] Step 6:

[0679] server

[0680] Scripts are automatically generated for the listed common tasks. These scripts contain procedures for efficiently executing common tasks by consolidating them into a single automated process. For example, for a data entry task, the scripts include steps such as extracting the data to be entered, entering the data into the input fields, and confirming and saving the final data.

[0681] Step 7:

[0682] server

[0683] Run the generated script in a test environment and check its operation. If there are any errors or areas for improvement, correct them and confirm that there are no problems.

[0684] Step 8:

[0685] server

[0686] Once the script has been tested, it is deployed in a real-world environment to generate an AI worker, which is then ready to automatically perform specific tasks based on the script.

[0687] Step 9:

[0688] Terminal and Server

[0689] The AI ​​worker performs specific tasks according to a schedule, for example, starting data entry work at a specific time each day, saving the results after completion, and sending the logs to a server.

[0690] Step 10:

[0691] server

[0692] The execution results are recorded in a log and periodically analyzed to evaluate the degree of operational efficiency achieved. Based on these results, if further improvements are needed, the scripts are updated or the AI ​​workers are adjusted.

[0693] Example 1

[0694] 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."

[0695] The problem that this invention aims to solve is to improve business efficiency by automatically detecting duplicate work by employees in a company and efficiently automating it. Conventional systems only support manual work recording and individual automation, making it difficult to optimize the entire business process. In addition, the accuracy of analysis results and the accuracy of automation have also been problematic.

[0696] 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.

[0697] In this invention, the server includes means for collecting employee operation logs, means for saving the collected operation logs, means for analyzing the saved operation logs and detecting common tasks, means for generating scripts to automate the detected common tasks, means for verifying the operation of the generated scripts in a test environment, means for generating AI workers to execute the generated scripts, and means for the generated AI workers to execute specific tasks. This makes it possible to automatically detect duplicate tasks in the daily work performed by employees and to efficiently automate those tasks.

[0698] An "employee operation log" is a history of operations performed by employees on devices such as PCs, and includes the names of applications opened, operation details, timestamps, input details, etc.

[0699] "Log collection means" refers to software or hardware that collects employee operation logs in real time, encrypts them, and sends them to a server.

[0700] "Log storage means" refers to a mechanism for storing collected operation logs in a storage device such as a database.

[0701] "Log analysis means" refers to a method or device for analyzing stored operation logs using machine learning algorithms or natural language processing techniques to detect common tasks.

[0702] "Common tasks" refer to similar or identical tasks performed by multiple employees, such as data entry, report creation, and email sending.

[0703] "Script generator" refers to a method or apparatus for programming and generating, in script form, procedures for automating detected common tasks.

[0704] A "test environment" refers to a virtual or sandbox environment in which generated scripts can be verified to work correctly.

[0705] "AI worker" refers to artificial intelligence that executes generated scripts and automatically performs specific tasks as a virtual worker.

[0706] "Task execution means" refers to a method or device by which an AI worker performs a particular task.

[0707] The system of this invention analyzes the PC work performed by employees, automatically discovers common tasks, and provides a new means of automating those tasks. The aim is to improve business efficiency in companies, allowing employees to focus on new challenges and ideas.

[0708] First, the user (employee) installs agent software on their PC. This agent software has the function of collecting the employee's operation log in real time. Specifically, it collects the names of open applications, operation details, timestamps, input details, etc. This operation log is encrypted and sent to the company's server.

[0709] Next, the server receives the operation logs sent from the terminals and stores them in a database, which can be managed using a database management system such as MySQL or PostgreSQL.

[0710] The server analyzes the saved operation log data. This analysis is performed using the Python libraries TensorFlow and Scikit-learn. First, the data is preprocessed to extract the necessary features. Next, a machine learning algorithm is applied based on the extracted features to detect patterns of common tasks. Natural language processing technology is also used to analyze text information within the log data.

[0711] The server generates scripts to automate the detected common tasks. Specifically, the procedures for the common tasks are written as scripts using Python or RPA tools (UiPath or Automation Anywhere). The generated scripts are first tested in a test environment. A virtual environment or sandbox environment is used to verify that the scripts work correctly.

[0712] The server then generates an AI worker to execute the generated script. This AI worker acts as a virtual worker and performs specific tasks, such as automatically extracting and inputting data, generating reports, and managing files. The AI ​​worker runs on a terminal or a remote server.

[0713] The generated AI workers automatically perform common tasks, freeing users (employees) from duplicated tasks that they would otherwise perform manually, allowing them to focus on other important tasks and improving work efficiency.

[0714] Examples:

[0715] Suppose a company regularly needs to perform large-scale data entry tasks. Employees spend a lot of time on this task. Agent software collects each employee's operation log, and the server analyzes the data to detect common data entry tasks. It then generates a script to automate the task, and an AI worker executes the script, automatically completing the data entry tasks. As a result, employees no longer need to manually perform data entry tasks, allowing them to focus on other tasks.

[0716] Example prompt sentence:

[0717] Analyze employee operation logs to detect common tasks and generate scripts to automate them. Write scripts using Python or RPA tools (UiPath, Automation Anywhere) to generate AI workers to perform the tasks.

[0718] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0719] Step 1: Installing the agent software and collecting operation logs

[0720] A user installs agent software on their PC. This agent software has the ability to collect all operation logs in real time. Specifically, it collects information such as the names of applications opened on the PC, operation details, timestamps, and entered data. These operation logs are encrypted and sent to a server in a secure format.

[0721] Input: User operation (application name, operation content, timestamp, input data)

[0722] Output: Encrypted operation log data

[0723] Step 2: Receiving and saving the operation log

[0724] The server receives the operation logs sent from the terminal. The received operation logs are stored in a database. A database management system such as MySQL or PostgreSQL can be used. During this process, data consistency checks and duplicate elimination processes are performed.

[0725] Input: Encrypted operation log data

[0726] Output: Operation log stored in the database

[0727] Step 3: Analyze the operation log

[0728] The server analyzes the saved operation log data. This analysis is performed using the Python libraries TensorFlow and Scikit-learn. The data is preprocessed to extract the necessary features. Next, a machine learning algorithm is applied based on the extracted features to detect patterns of common tasks. Natural language processing technology is also used to analyze the text data.

[0729] Input: Operation logs stored in the database

[0730] Output: Generated common work pattern

[0731] Step 4: Generate and test scripts

[0732] The server generates a script for automation based on the analysis results. Specifically, it uses Python or an RPA tool (e.g., UiPath or Automation Anywhere) to program the procedures for common tasks. The generated script is first tested in a test environment, which can be a virtual environment or a sandbox environment.

[0733] Input: Detected common work patterns

[0734] Output: Generated automation script

[0735] Step 5: Generate AI workers and execute tasks

[0736] The server generates an AI worker to execute the generated script. This AI worker performs specific tasks as a virtual worker. Specifically, it automatically performs business operations such as data extraction and input, report generation, and file management. The AI ​​worker runs on a terminal or a remote server.

[0737] Input: Generated automation script

[0738] Output: The automated task that will be executed

[0739] Step 6: Improve operational efficiency through automation

[0740] Users (employees) are freed from manual, duplicated tasks by having AI workers automatically perform common tasks, allowing employees to focus on other important tasks and improving work efficiency.

[0741] Input: The automated task to be executed

[0742] Output: Streamlined business processes

[0743] (Application example 1)

[0744] 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."

[0745] There is a need to significantly improve operational efficiency by automating common tasks performed by employees on a daily basis. In particular, logistics centers have a large number of manual tasks, such as inventory management and picking, and there is an urgent need to streamline these tasks. In addition, there is a need to reduce the burden on employees by automating tasks using smart devices and promote the smooth progress of operations.

[0746] 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.

[0747] In this invention, the server includes: means for collecting employee operation logs; means for saving the collected operation logs; means for analyzing the saved operation logs and detecting common tasks; means for generating scripts to automate the detected common tasks; means for generating AI workers to execute the generated scripts; means for the generated AI workers to perform specific tasks; means including a smart device for analyzing the operation logs and issuing commands to execute the automation scripts; means for analyzing common tasks from employee operation logs using a machine learning algorithm; means for extracting tasks for improving efficiency from log information using natural language processing technology; means for automatically updating inventory data using the camera function of the smart device; and means for analyzing common tasks and proposing optimal product picking routes. This enables efficient inventory management and picking operations at logistics centers by analyzing employee operation logs in detail and generating automation scripts.

[0748] An "employee operation log" is a record of operations performed by employees, and specifically includes application usage information, operation details, timestamps, input data, and the like.

[0749] "Means for collecting operation logs" refers to software or hardware for collecting and recording employee operation logs in real time.

[0750] The "means for storing operation logs" refers to a database or storage system for appropriately storing collected operation logs.

[0751] A "means for detecting common tasks" is an algorithm or program that analyzes and finds tasks that are commonly performed by multiple employees.

[0752] The "means for generating scripts for automation" is software that generates scripts for automatically executing common tasks based on specific procedures.

[0753] An "artificial intelligence worker" is a virtual worker that automatically executes specific tasks based on a generated script.

[0754] A "smart device" is a device that can connect to the Internet, such as a smartphone, tablet, or smart glasses, and is used to collect operation logs and execute scripts.

[0755] A "machine learning algorithm" is an algorithm that learns patterns from large amounts of data and detects common tasks.

[0756] "Natural language processing technology" is a technology for analyzing text data and understanding the meaning of language.

[0757] The "means for automatically updating inventory data" is a system that uses the camera function of a smart device to scan information about inventory items and automatically update the database.

[0758] The "means for proposing the optimal picking route" is an algorithm that proposes the optimal route for efficiently picking products within a logistics center.

[0759] The system of this invention aims to improve the efficiency of operations at logistics centers. In particular, it is possible to significantly improve the work efficiency of logistics centers by analyzing employee operation logs and automating common tasks.

[0760] The system of the present invention begins with the installation of agent software on employees' smart devices (e.g., smartphones, tablets). This agent software collects operational logs of employees' daily work in real time and stores them in a database. Specifically, application usage information, operation details, timestamps, and other information are collected as logs.

[0761] The server analyzes the collected operation logs using machine learning algorithms and natural language processing technology to automatically detect tasks performed by multiple employees (common tasks), such as inventory checks, data entry, and creating picking lists.

[0762] The server generates an automation script for each common task that is detected. This script describes a series of steps to perform the common task efficiently. The generated script is tested in a test environment, and once no problems are confirmed, it is implemented in the actual business.

[0763] The generated scripts are then executed by an AI worker, who has the ability to automatically perform certain tasks, such as automatically updating inventory or suggesting optimal routes for picking lists. The AI ​​worker can also use the camera function of a smart device to scan QR codes on inventory items and automatically update the database.

[0764] As a concrete example, consider inventory management at a logistics center. Employees can scan the QR codes of inventory items with their smart devices, automatically updating inventory data. Furthermore, when picking items, AI workers can suggest optimal picking routes, improving employee efficiency.

[0765] An example of a prompt is "Implement a QR code scanning function to streamline inventory management," which would enable more efficient inventory management using smart devices.

[0766] In this way, the system of the present invention can significantly improve the operational efficiency of a logistics center, reduce the burden on employees, and increase productivity.

[0767] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0768] Step 1:

[0769] A user starts work using a smart device. Agent software is installed on the smart device and collects the user's operation logs in real time. The collected operation logs include application usage information, operation details, timestamps, etc. This log data is encrypted and sent to the server. The input is the user's operation, and the output is the operation log.

[0770] Step 2:

[0771] The server stores the operation logs it receives in a database. The server then converts the operation logs into a format that is easy to analyze and stores them. Specific data processing includes timestamp format conversion and input content classification. The input is encrypted operation logs, and the output is operation log data converted into a standard format for analysis.

[0772] Step 3:

[0773] The server uses a machine learning algorithm to analyze the stored operation logs. It classifies and clusters the data to detect common tasks. Specifically, it identifies patterns of operations frequently performed by employees and recognizes them as common tasks. The input is operation log data in a standard format, and the output is a list of detected common tasks.

[0774] Step 4:

[0775] The server uses natural language processing technology to perform a detailed analysis of common tasks. Specifically, it understands the intent behind the operation procedures and instructions from the text data in the operation log. This analysis generates a script to efficiently automate the common tasks. The input is a list of common tasks, and the output is an automation script.

[0776] Step 5:

[0777] The server builds an AI worker based on the generated script. The AI ​​worker is a program that automatically executes specific tasks based on the generated script. The input is the automation script, and the output is the AI ​​worker program.

[0778] Step 6:

[0779] An AI worker starts working on a smart device. For example, the smart device's camera scans a QR code and automatically updates inventory data. An algorithm is also run to suggest the optimal route for the picking list. The inputs are inventory items and picking data, and the output is the updated inventory data and the suggested picking route.

[0780] An example of a prompt is "Implement a QR code scanning function to streamline inventory management," which would enable efficient inventory management using smart devices.

[0781] The above is the specific processing flow of the system for realizing the application example.

[0782] 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.

[0783] This invention is a system that simultaneously collects and analyzes employees' PC operation logs and emotional states, and automates common work tasks. This system not only improves work efficiency but also reduces employees' stress levels, providing a more comfortable working environment.

[0784] Overall system configuration

[0785] First, agent software is installed on the user's device. This agent software uses an emotion engine to collect emotional data in real time, along with the user's PC operation log. The operation log includes application usage, operation details, timestamps, and input details. Emotional data includes biometric information such as the user's facial expression, voice tone, and heart rate.

[0786] Data collection

[0787] The agent software encrypts the collected operation logs and emotional data and periodically transmits them to the company's server, which stores the received data in a database for subsequent analysis.

[0788] Data analysis

[0789] The server analyzes the stored operation logs and emotional data using machine learning algorithms and natural language processing technology. This analysis detects common tasks performed by multiple employees. Analysis of the emotional data also makes it possible to evaluate the level of stress and fatigue that a particular task causes to the user.

[0790] Generating automation scripts

[0791] Based on the detected common tasks, the server generates an automation script. This script combines the common tasks into a single process and includes instructions for efficient execution. Furthermore, the script can be adjusted based on the user's emotional data. For example, if a particular task causes high stress, the script can be optimized to perform the task in a more efficient manner.

[0792] AI worker generation and execution

[0793] The server generates an AI worker to execute the generated script. This AI worker is a virtual worker that automatically performs specific tasks. The AI ​​worker executes the task according to a schedule and sends the results to the server as a log. This eliminates the need for employees to perform the task manually, improving work efficiency.

[0794] Emotional Feedback

[0795] The server analyzes the user's emotional data and the AI ​​worker's performance results, and provides real-time feedback. For example, it can recommend a break if the user is feeling stressed, or suggest adjustments to the work environment. This feedback is also reflected in the next script generation, further optimizing the entire system.

[0796] Specific examples

[0797] For example, a company regularly creates sales reports and uploads them to a shared folder. Employees spend a lot of time on this task, and they often find it particularly stressful. The agent software collects each employee's operation log and emotional data, such as facial expressions and voice tone, and the server analyzes them. The software then detects common tasks involved in creating sales reports and uploading them to the folder, generating a script to automate the task. This script is optimized to reduce stress, and an AI worker executes it, improving work efficiency while reducing employee stress. Repeating this entire process simultaneously improves the company's operational efficiency and employee satisfaction.

[0798] As described above, the system of the present invention simultaneously improves business efficiency and manages the emotional state of employees, thereby improving productivity across the entire company.

[0799] The processing flow will be explained below.

[0800] Step 1:

[0801] Terminal

[0802] Agent software is installed on each employee's PC. The agent software collects the employee's PC operation log and emotional data in real time. The operation log includes the application used, operation details, timestamp, and input content. Emotional data includes facial expressions, voice tone, heart rate, etc.

[0803] Step 2:

[0804] Terminal

[0805] The agent software encrypts the collected operation logs and emotional data and sends them to the company's server at regular intervals (for example, every hour).

[0806] Step 3:

[0807] server

[0808] The company's server stores the received operation logs and emotion data in a database. The database stores each employee's operation log and emotion data in chronological order and creates an index to facilitate search and analysis.

[0809] Step 4:

[0810] server

[0811] Machine learning algorithms and natural language processing technology are applied to the saved operation logs and emotion data. Based on the operation data, frequency analysis and pattern recognition are performed to detect tasks that are commonly performed by multiple employees (common tasks). At the same time, emotion data is analyzed to evaluate the stress level during specific tasks.

[0812] Step 5:

[0813] server

[0814] Based on the analysis results, a list of identified common tasks is created, and an automation script is generated based on the list. The automation script includes a series of steps to efficiently execute the detected common tasks. Furthermore, optimization is performed to reduce stress levels during work based on emotion data.

[0815] Step 6:

[0816] server

[0817] Run the generated script in a test environment to check its operation. Test whether the script has errors and runs as expected. Fix any defects or areas for improvement that are found.

[0818] Step 7:

[0819] server

[0820] To operate the script in a real-world environment after testing, an AI worker is generated. This AI worker is a virtual worker that automatically performs specific tasks based on the script.

[0821] Step 8:

[0822] Terminal and Server

[0823] An AI worker performs a specific task according to a schedule, for example, starting data entry work at a specific time each day and sending the results as a log to a server after completion.

[0824] Step 9:

[0825] server

[0826] The execution results and emotional data are analyzed again to provide real-time feedback to the user. If the user's stress level is high, the system will recommend taking a break or suggest adjustments to the work environment. The feedback information will also be reflected in the next script generation, optimizing the entire system.

[0827] Step 10:

[0828] server

[0829] Periodically, an analysis report of the execution results and emotional data is generated and provided to users and managers. The report includes information such as how much work efficiency has improved and how stress levels have changed. Based on this, if further improvements are needed, the script can be updated or the AI ​​workers adjusted.

[0830] Example 2

[0831] 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."

[0832] Modern companies are required to improve employee work efficiency while reducing employee stress levels and providing a comfortable work environment. However, conventional systems do not adequately automate work tasks or optimize work processes by taking into account the emotional state of employees. This has resulted in problems such as poor work efficiency and the accumulation of employee stress.

[0833] 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.

[0834] In this invention, the server includes means for collecting employee operation logs and emotional data, means for saving the collected operation logs and emotional data, means for analyzing the saved operation logs and emotional data to detect common tasks and stress levels, means for generating a script to automate the detected common tasks, means for generating an AI worker who executes the generated script, means for the AI ​​worker to perform a specific task, and means for providing feedback in real time based on the emotional data. This makes it possible to efficiently automate employee work tasks while optimizing work processes taking into account the emotional states of employees.

[0835] An "operation log" is data that records the operations performed on devices used by employees, application usage status, timestamps, input content, etc.

[0836] "Emotion data" refers to data including biometric information such as the user's facial expression, voice tone, and heart rate, and represents the user's emotional state.

[0837] "Means for collection" refers to a function or device for acquiring operation logs and emotional data from a terminal and storing them as data.

[0838] "Storage means" refers to a function or device that stores collected operation logs and emotion data in a database or recording device.

[0839] "Means for analysis" refers to algorithms and programs that process saved operation logs and emotional data to detect common tasks and stress levels.

[0840] "Common work" refers to business tasks that are commonly performed by multiple employees.

[0841] "Script generation means" refers to a program or algorithm that generates instructions or code to automate the common tasks detected.

[0842] An "artificial intelligence worker" is a virtual worker that executes the generated automation script and is a system that automatically executes specific tasks.

[0843] "Means for providing feedback in real time" refers to a function or device that provides immediate improvement suggestions or advice to the user based on emotional data or work results.

[0844] This invention is a system that simultaneously collects and analyzes employees' PC operation logs and emotional states, automating common work tasks. This not only improves work efficiency but also reduces employees' stress levels, providing a more comfortable working environment.

[0845] Installing the Agent Software

[0846] First, the user installs agent software on their device. This agent software has the ability to collect PC operation logs and emotional data in real time. Specifically, the operation log records application usage, operation details, timestamps, input details, etc., while the emotional data is collected by using a webcam and microphone to collect biometric information such as the user's facial expressions, voice tone, and heart rate.

[0847] Data collection and transmission

[0848] The device encrypts the operation logs and emotion data collected by the agent software and periodically sends them to the server using powerful encryption technology such as AES-256, with the data being sent in batches, for example, every hour.

[0849] Data storage and analysis

[0850] The server stores the received data in a database. Using a database management system (DBMS), the data is organized into an easily accessible format. The server then uses machine learning algorithms and natural language processing techniques to analyze the stored operation logs and emotion data. Common work tasks are extracted from the operation logs, and the emotion data is used to evaluate the stress and fatigue levels that specific tasks cause to users. Python's scikit-learn and TensorFlow are used for the analysis.

[0851] Generating automation scripts

[0852] Based on the analysis results, the server generates a script for automation. This script contains specific steps for efficiently performing common tasks. For example, a script for automating the creation of sales reports contains instructions for automatically entering data into a template file and automatically uploading it to a specified folder. The following prompt is input into the generative AI model to generate a script: "Please generate an automation script that creates a sales report and uploads it to a specific folder."

[0853] AI worker generation and execution

[0854] The server generates an AI worker to execute the generated script. This AI worker automatically executes specific tasks according to a schedule. For example, it is set to create and upload a sales report every Friday at 10:00 AM. The AI ​​worker executes the task and sends the results to the server as a log.

[0855] Providing emotional feedback

[0856] Finally, the server comprehensively analyzes the user's emotional data and the AI ​​worker's performance results and provides real-time feedback. For example, if the user indicates a high stress level, a notification recommending a break will be sent. This feedback will also be reflected in the next script generation, further optimizing the entire system. For example, a notification saying "Your stress level is high, so we recommend you take a break" will be displayed on the user's screen.

[0857] As described above, the present invention simultaneously improves business efficiency and manages the emotional state of employees, thereby improving productivity across the entire company.

[0858] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0859] Step 1:

[0860] The user installs agent software on their device. This agent software collects operation logs, such as application usage, operation details, timestamps, and input details, as well as emotional data, such as the user's facial expressions, voice tone, and heart rate, in real time using a webcam and microphone. The input is the installation of the agent software, and the output is the start of collection of operation logs and emotional data.

[0861] Step 2:

[0862] The terminal encrypts the operation log and emotion data collected by the agent software. Specifically, it uses a strong encryption technique such as AES-256. The encrypted data is then sent to the server at regular intervals (for example, every hour). The input is the collected operation log and emotion data, and the output is the encrypted data sent to the server.

[0863] Step 3:

[0864] The server receives the encrypted data, decrypts it, and stores it in a database. Specifically, it uses a database management system (DBMS) to organize the data and make it more accessible. The input is the encrypted data, and the output is the raw data stored in the database.

[0865] Step 4:

[0866] The server analyzes the stored operation logs and emotion data. Specific operations include machine learning algorithms such as Python's scikit-learn and TensorFlow, as well as natural language processing technology. Common work tasks are extracted from the operation logs, and the emotion data is used to evaluate the stress and fatigue levels that specific tasks cause to users. The input is the operation logs and emotion data stored in the database, and the output is the detection results of common tasks and stress levels.

[0867] Step 5:

[0868] The server generates an automation script based on the analysis results. The following prompt is input to the generative AI model: "Please generate an automation script to create a sales report and upload it to a specific folder." The output of the generated script contains specific steps for efficiently performing common tasks. The input is the common tasks and stress level detection results, and the output is the automation script.

[0869] Step 6:

[0870] The server generates an AI worker to execute the generated script. This AI worker automatically executes specific tasks according to a schedule. For example, it is set to create and upload a sales report every Friday at 10:00 AM. The AI ​​worker executes the task and sends the results as a log to the server. The input is the automation script, and the output is the task execution results and log.

[0871] Step 7:

[0872] The server comprehensively analyzes the user's emotional data and the AI ​​worker's performance results and provides real-time feedback. Specifically, if stress levels are rising, it sends a notification recommending a break. The input is the emotional data and a log of the performance results, and the output is a feedback notification. For example, a message such as "Your stress level is high, so we recommend you take a break" is displayed on the user's screen.

[0873] Through the above steps, the present invention can simultaneously improve work efficiency and manage the emotional state of employees, thereby improving the productivity of the entire company.

[0874] (Application example 2)

[0875] 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."

[0876] Conventional factory quality inspection processes rely on manual work, resulting in problems such as reduced work efficiency, manual errors, and increased employee stress. Furthermore, improvements to the work environment have not been made with consideration for the emotional state of employees, making it difficult to improve the work environment. Therefore, there is a need for a method to improve the efficiency of the quality inspection process, reduce employee stress, and optimize the work environment.

[0877] 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.

[0878] In this invention, the server includes means for collecting employee operation logs, means for saving the collected operation logs, means for analyzing the saved operation logs and detecting common tasks, means for generating scripts to automate the detected common tasks, means for generating AI workers to execute the generated scripts, means for collecting and encrypting operation logs and employee emotion data related to robots that perform quality inspections in factories and sending them to a cloud server, means for analyzing the operation logs and emotion data using a machine learning algorithm in the cloud server to optimize the quality inspection process, and means for generating optimized automation scripts and for the AI ​​workers to execute the quality inspection process. This enables the automation and optimization of the quality inspection process, reducing employee stress and improving the work environment.

[0879] An "operation log" is a series of operation history recorded when an employee operates a PC or robot, and includes application usage status, input content, and timestamps.

[0880] "Emotional data" refers to data about an employee's emotional state analyzed based on biometric information such as facial expressions, voice tone, and heart rate.

[0881] An "automation script" is a program procedure manual that is generated to automatically execute a specific task based on the analyzed operation log.

[0882] An "AI worker" is a virtual worker that performs work based on an automation script, an artificial intelligence-based system that performs specific tasks automatically.

[0883] A "cloud server" is a remote server that stores and processes data via the Internet, and is used to store and analyze collected operation logs and emotion data.

[0884] "Quality inspection process" refers to a series of work procedures for checking and evaluating the quality of products and services, including inspection work carried out within the factory.

[0885] A "machine learning algorithm" is a computational algorithm that automatically learns patterns and rules from large amounts of data and uses them to make predictions and analyses.

[0886] First, agent software is installed on the robots and the terminals used by workers in the factory. This agent software is responsible for collecting the robot's operation log and the employee's emotional data. The operation log includes the robot's movements, setting values, timestamps, error messages, etc., while the emotional data includes the employee's facial expressions, voice tone, heart rate, and other biometric information.

[0887] The operation logs and emotion data collected by the agent software are encrypted and sent via a local server in the factory to a cloud server, which then stores the received data in a database and uses it for data analysis.

[0888] The cloud server analyzes the stored operation logs and emotion data using machine learning algorithms and natural language processing technology, which enables it to detect common tasks in the quality inspection process and the stress levels of employees associated with those tasks.

[0889] Based on the detected common tasks, the cloud server then generates scripts to automate the quality inspection process, optimizing the efficiency of areas that are particularly stressful for employees, and distributes the scripts to robots that act as AI workers.

[0890] The AI ​​worker robot automatically executes the quality inspection process according to the generated script, and once the quality inspection is complete, the results are sent to the cloud server via the local server and stored in a database.

[0891] The cloud server also provides real-time feedback on employee emotional data and the AI ​​worker's performance. If an employee's stress level increases, the system can recommend a break or adjust the work environment. This feedback is then reflected in the next script generation, further optimizing the overall system.

[0892] As a concrete example, consider a case where a particular inspection in a factory is extremely stressful for employees. In this case, the agent software collects operation logs and emotional data, which are then analyzed by a cloud server. Based on the analysis results, a script is generated to automate the stressful inspection process, which is then executed by an AI worker, reducing the burden on the employees.

[0893] An example of a prompt for a generative AI model is:

[0894] Generate automation scripts to streamline the quality inspection process based on given operation logs and sentiment data, with a particular focus on optimizing areas that cause high levels of stress for employees.

[0895] In this way, it is possible to automate the quality inspection process and optimize the emotional state of employees at the same time.

[0896] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0897] Step 1:

[0898] Installing the Agent Software

[0899] Agent software is installed on factory robots and employee devices, allowing for the collection of operation logs and emotional data.

[0900] Input: Agent software, robots and terminals

[0901] Output: Terminal and robot ready to collect data

[0902] Step 2:

[0903] Starting Data Collection

[0904] The agent software begins collecting the robot's operation logs and employee emotional data. The operation logs include the robot's movements, settings, timestamps, error messages, etc. Emotional data is obtained from facial expressions, voice tone, heart rate, etc.

[0905] Input: Robot operation status, employee emotional state

[0906] Output: Collected operation logs and emotion data

[0907] Step 3:

[0908] Data encryption and transmission

[0909] The agent software encrypts the operation logs and emotional data collected and sends them to a cloud server via a local server in the factory.

[0910] Input: Collected operation logs and emotion data

[0911] Output: Encrypted operation log and emotion data, cloud server

[0912] Step 4:

[0913] Saving to a database

[0914] The cloud server receives the encrypted operation log and emotion data and stores them in a database.

[0915] Input: Encrypted operation log and emotion data

[0916] Output: Operation logs and emotion data stored in a database

[0917] Step 5:

[0918] Data analysis

[0919] The cloud server uses machine learning algorithms and natural language processing technology to analyze the stored operation logs and emotion data, and through this analysis, detects common tasks and stress levels during the quality inspection process.

[0920] Input: Operation log and emotion data

[0921] Output: Analysis results (detection of common tasks, evaluation of stress level)

[0922] Step 6:

[0923] Generating automation scripts

[0924] Based on the analysis results, the cloud server generates scripts to automate the quality inspection process, which are optimized to streamline particularly high-stress areas.

[0925] Input: Analysis results

[0926] Output: Automation script

[0927] Step 7:

[0928] Distributing scripts to AI workers

[0929] The cloud server distributes the generated automation script to the robots, which then function as AI workers.

[0930] Input: Automation script

[0931] Output: A robot that acts as an AI worker

[0932] Step 8:

[0933] Automatic execution of quality inspection processes

[0934] AI workers follow the generated script and automatically carry out the quality inspection process.

[0935] Input: Automation script

[0936] Output: Quality inspection results, robot execution log

[0937] Step 9:

[0938] Sending and saving results

[0939] Once the AI ​​worker completes the quality inspection, the results and execution log are sent to the cloud server via the local server and stored in a database.

[0940] Input: Quality inspection results, robot execution log

[0941] Output: Execution results and logs stored in a database

[0942] Step 10:

[0943] Real-time feedback

[0944] The cloud server analyzes employee emotional data and the AI ​​worker's performance, providing real-time feedback. If an employee's stress level is increasing, the system will recommend taking a break or adjust the work environment.

[0945] Input: Emotion data, execution results

[0946] Output: Feedback (recommendation of breaks, adjustment of work environment)

[0947] This allows for the automation of quality inspection processes and the optimization of the emotional state of employees.

[0948] 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.

[0949] 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.

[0950] 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.

[0951] [Fourth embodiment]

[0952] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0953] 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.

[0954] 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).

[0955] 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.

[0956] 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.

[0957] 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).

[0958] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0959] 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.

[0960] 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.

[0961] 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.

[0962] 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.

[0963] 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.

[0964] 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."

[0965] The system of this invention uses AI to analyze the PC work performed by employees, automatically discover common tasks, and automate them. This system will improve business efficiency and allow employees to focus on new challenges and ideas.

[0966] First, agent software is installed on employees' PCs. This agent software has the function of collecting employees' operation logs in real time. Specifically, it records opened applications, operation details, timestamps, input details, etc., and then encrypts and sends the data to the company's server. By collecting operation logs, the agent software makes it possible to record daily business activities.

[0967] Next, the server receives the operation logs sent from the devices and stores them in a database. The server then analyzes the stored data using machine learning algorithms and natural language processing technology. This analysis makes it possible to automatically detect tasks that are commonly performed by multiple employees, in other words, "common tasks." For example, tasks such as data entry, report creation, and email sending may be detected as common tasks.

[0968] For each common task detected, the server generates an automated script. This script describes a series of steps to perform the common task efficiently. The generated script is tested in a test environment, and after confirming there are no problems, it is implemented in actual business operations.

[0969] The server generates an AI worker to execute the generated script. This AI worker acts as a virtual worker and has the ability to perform specific tasks, such as automatically extracting and inputting data, generating reports, and managing files.

[0970] The generated AI workers run on terminals or remote servers to perform specific tasks. This improves operational efficiency by allowing AI workers to automatically perform common tasks, eliminating the need for employees to perform them manually. Employees are freed from time-consuming, duplicated tasks, allowing them to focus on other important tasks.

[0971] As a concrete example, consider a company that regularly requires large-scale data entry work. Employees spend a lot of time on this work. Agent software collects each employee's operation log, and the server analyzes the data to detect common data entry tasks. It then generates a script to automate the task, and an AI worker executes the script, automatically completing the data entry work. As a result, employees no longer need to manually perform data entry work, allowing them to focus on other tasks.

[0972] In this way, the system of the present invention can significantly improve business efficiency within a company and increase employee productivity.

[0973] The processing flow will be explained below.

[0974] Step 1:

[0975] Terminal

[0976] Agent software is installed on each employee's PC, which monitors the employee's PC operations in real time and collects data such as operations, applications used, timestamps, and input contents.

[0977] Step 2:

[0978] Terminal

[0979] The agent software encrypts the collected log data and sends it to the company's server at regular intervals (for example, every hour).

[0980] Step 3:

[0981] server

[0982] The company's server stores the received operation log data in a database, which stores each employee's operation log in chronological order and creates an index for subsequent analysis.

[0983] Step 4:

[0984] server

[0985] Machine learning algorithms are applied to the saved operation log data. Specifically, frequency analysis and pattern recognition are performed to extract tasks commonly performed by multiple employees. This includes detecting the frequency of use of specific applications and specific operation patterns.

[0986] Step 5:

[0987] server

[0988] Based on patterns and common tasks extracted by machine learning algorithms, a list of common tasks is created, including how many times each task is performed and which employee performed each task.

[0989] Step 6:

[0990] server

[0991] Scripts are automatically generated for the listed common tasks. These scripts contain procedures for efficiently executing common tasks by consolidating them into a single automated process. For example, for a data entry task, the scripts include steps such as extracting the data to be entered, entering the data into the input fields, and confirming and saving the final data.

[0992] Step 7:

[0993] server

[0994] Run the generated script in a test environment and check its operation. If there are any errors or areas for improvement, correct them and confirm that there are no problems.

[0995] Step 8:

[0996] server

[0997] Once the script has been tested, it is deployed in a real-world environment to generate an AI worker, which is then ready to automatically perform specific tasks based on the script.

[0998] Step 9:

[0999] Terminal and Server

[1000] The AI ​​worker performs specific tasks according to a schedule, for example, starting data entry work at a specific time each day, saving the results after completion, and sending the logs to a server.

[1001] Step 10:

[1002] server

[1003] The execution results are recorded in a log and periodically analyzed to evaluate the degree of operational efficiency achieved. Based on these results, if further improvements are needed, the scripts are updated or the AI ​​workers are adjusted.

[1004] Example 1

[1005] 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."

[1006] The problem that this invention aims to solve is to improve business efficiency by automatically detecting duplicate work by employees in a company and efficiently automating it. Conventional systems only support manual work recording and individual automation, making it difficult to optimize the entire business process. In addition, the accuracy of analysis results and the accuracy of automation have also been problematic.

[1007] 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.

[1008] In this invention, the server includes means for collecting employee operation logs, means for saving the collected operation logs, means for analyzing the saved operation logs and detecting common tasks, means for generating scripts to automate the detected common tasks, means for verifying the operation of the generated scripts in a test environment, means for generating AI workers to execute the generated scripts, and means for the generated AI workers to execute specific tasks. This makes it possible to automatically detect duplicate tasks in the daily work performed by employees and to efficiently automate those tasks.

[1009] An "employee operation log" is a history of operations performed by employees on devices such as PCs, and includes the names of applications opened, operation details, timestamps, input details, etc.

[1010] "Log collection means" refers to software or hardware that collects employee operation logs in real time, encrypts them, and sends them to a server.

[1011] "Log storage means" refers to a mechanism for storing collected operation logs in a storage device such as a database.

[1012] "Log analysis means" refers to a method or device for analyzing stored operation logs using machine learning algorithms or natural language processing techniques to detect common tasks.

[1013] "Common tasks" refer to similar or identical tasks performed by multiple employees, such as data entry, report creation, and email sending.

[1014] "Script generator" refers to a method or apparatus for programming and generating, in script form, procedures for automating detected common tasks.

[1015] A "test environment" refers to a virtual or sandbox environment in which generated scripts can be verified to work correctly.

[1016] "AI worker" refers to artificial intelligence that executes generated scripts and automatically performs specific tasks as a virtual worker.

[1017] "Task execution means" refers to a method or device by which an AI worker performs a particular task.

[1018] The system of this invention analyzes the PC work performed by employees, automatically discovers common tasks, and provides a new means of automating those tasks. The aim is to improve business efficiency in companies, allowing employees to focus on new challenges and ideas.

[1019] First, the user (employee) installs agent software on their PC. This agent software has the function of collecting the employee's operation log in real time. Specifically, it collects the names of open applications, operation details, timestamps, input details, etc. This operation log is encrypted and sent to the company's server.

[1020] Next, the server receives the operation logs sent from the terminals and stores them in a database, which can be managed using a database management system such as MySQL or PostgreSQL.

[1021] The server analyzes the saved operation log data. This analysis is performed using the Python libraries TensorFlow and Scikit-learn. First, the data is preprocessed to extract the necessary features. Next, a machine learning algorithm is applied based on the extracted features to detect patterns of common tasks. Natural language processing technology is also used to analyze text information within the log data.

[1022] The server generates scripts to automate the detected common tasks. Specifically, the procedures for the common tasks are written as scripts using Python or RPA tools (UiPath or Automation Anywhere). The generated scripts are first tested in a test environment. A virtual environment or sandbox environment is used to verify that the scripts work correctly.

[1023] The server then generates an AI worker to execute the generated script. This AI worker acts as a virtual worker and performs specific tasks, such as automatically extracting and inputting data, generating reports, and managing files. The AI ​​worker runs on a terminal or a remote server.

[1024] The generated AI workers automatically perform common tasks, freeing users (employees) from duplicated tasks that they would otherwise perform manually, allowing them to focus on other important tasks and improving work efficiency.

[1025] Examples:

[1026] Suppose a company regularly needs to perform large-scale data entry tasks. Employees spend a lot of time on this task. Agent software collects each employee's operation log, and the server analyzes the data to detect common data entry tasks. It then generates a script to automate the task, and an AI worker executes the script, automatically completing the data entry tasks. As a result, employees no longer need to manually perform data entry tasks, allowing them to focus on other tasks.

[1027] Example prompt sentence:

[1028] Analyze employee operation logs to detect common tasks and generate scripts to automate them. Write scripts using Python or RPA tools (UiPath, Automation Anywhere) to generate AI workers to perform the tasks.

[1029] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1030] Step 1: Installing the agent software and collecting operation logs

[1031] A user installs agent software on their PC. This agent software has the ability to collect all operation logs in real time. Specifically, it collects information such as the names of applications opened on the PC, operation details, timestamps, and entered data. These operation logs are encrypted and sent to a server in a secure format.

[1032] Input: User operation (application name, operation content, timestamp, input data)

[1033] Output: Encrypted operation log data

[1034] Step 2: Receiving and saving the operation log

[1035] The server receives the operation logs sent from the terminal. The received operation logs are stored in a database. A database management system such as MySQL or PostgreSQL can be used. During this process, data consistency checks and duplicate elimination processes are performed.

[1036] Input: Encrypted operation log data

[1037] Output: Operation log stored in the database

[1038] Step 3: Analyze the operation log

[1039] The server analyzes the saved operation log data. This analysis is performed using the Python libraries TensorFlow and Scikit-learn. The data is preprocessed to extract the necessary features. Next, a machine learning algorithm is applied based on the extracted features to detect patterns of common tasks. Natural language processing technology is also used to analyze the text data.

[1040] Input: Operation logs stored in the database

[1041] Output: Generated common work pattern

[1042] Step 4: Generate and test scripts

[1043] The server generates a script for automation based on the analysis results. Specifically, it uses Python or an RPA tool (e.g., UiPath or Automation Anywhere) to program the procedures for common tasks. The generated script is first tested in a test environment, which can be a virtual environment or a sandbox environment.

[1044] Input: Detected common work patterns

[1045] Output: Generated automation script

[1046] Step 5: Generate AI workers and execute tasks

[1047] The server generates an AI worker to execute the generated script. This AI worker performs specific tasks as a virtual worker. Specifically, it automatically performs business operations such as data extraction and input, report generation, and file management. The AI ​​worker runs on a terminal or a remote server.

[1048] Input: Generated automation script

[1049] Output: The automated task that will be executed

[1050] Step 6: Improve operational efficiency through automation

[1051] Users (employees) are freed from manual, duplicated tasks by having AI workers automatically perform common tasks, allowing employees to focus on other important tasks and improving work efficiency.

[1052] Input: The automated task to be executed

[1053] Output: Streamlined business processes

[1054] (Application example 1)

[1055] 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."

[1056] There is a need to significantly improve operational efficiency by automating common tasks performed by employees on a daily basis. In particular, logistics centers have a large number of manual tasks, such as inventory management and picking, and there is an urgent need to streamline these tasks. In addition, there is a need to reduce the burden on employees by automating tasks using smart devices and promote the smooth progress of operations.

[1057] 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.

[1058] In this invention, the server includes: means for collecting employee operation logs; means for saving the collected operation logs; means for analyzing the saved operation logs and detecting common tasks; means for generating scripts to automate the detected common tasks; means for generating AI workers to execute the generated scripts; means for the generated AI workers to perform specific tasks; means including a smart device for analyzing the operation logs and issuing commands to execute the automation scripts; means for analyzing common tasks from employee operation logs using a machine learning algorithm; means for extracting tasks for improving efficiency from log information using natural language processing technology; means for automatically updating inventory data using the camera function of the smart device; and means for analyzing common tasks and proposing optimal product picking routes. This enables efficient inventory management and picking operations at logistics centers by analyzing employee operation logs in detail and generating automation scripts.

[1059] An "employee operation log" is a record of operations performed by employees, and specifically includes application usage information, operation details, timestamps, input data, and the like.

[1060] "Means for collecting operation logs" refers to software or hardware for collecting and recording employee operation logs in real time.

[1061] The "means for storing operation logs" refers to a database or storage system for appropriately storing collected operation logs.

[1062] A "means for detecting common tasks" is an algorithm or program that analyzes and finds tasks that are commonly performed by multiple employees.

[1063] The "means for generating scripts for automation" is software that generates scripts for automatically executing common tasks based on specific procedures.

[1064] An "artificial intelligence worker" is a virtual worker that automatically executes specific tasks based on a generated script.

[1065] A "smart device" is a device that can connect to the Internet, such as a smartphone, tablet, or smart glasses, and is used to collect operation logs and execute scripts.

[1066] A "machine learning algorithm" is an algorithm that learns patterns from large amounts of data and detects common tasks.

[1067] "Natural language processing technology" is a technology for analyzing text data and understanding the meaning of language.

[1068] The "means for automatically updating inventory data" is a system that uses the camera function of a smart device to scan information about inventory items and automatically update the database.

[1069] The "means for proposing the optimal picking route" is an algorithm that proposes the optimal route for efficiently picking products within a logistics center.

[1070] The system of this invention aims to improve the efficiency of operations at logistics centers. In particular, it is possible to significantly improve the work efficiency of logistics centers by analyzing employee operation logs and automating common tasks.

[1071] The system of the present invention begins with the installation of agent software on employees' smart devices (e.g., smartphones, tablets). This agent software collects operational logs of employees' daily work in real time and stores them in a database. Specifically, application usage information, operation details, timestamps, and other information are collected as logs.

[1072] The server analyzes the collected operation logs using machine learning algorithms and natural language processing technology to automatically detect tasks performed by multiple employees (common tasks), such as inventory checks, data entry, and creating picking lists.

[1073] The server generates an automation script for each common task that is detected. This script describes a series of steps to perform the common task efficiently. The generated script is tested in a test environment, and once no problems are confirmed, it is implemented in the actual business.

[1074] The generated scripts are then executed by an AI worker, who has the ability to automatically perform certain tasks, such as automatically updating inventory or suggesting optimal routes for picking lists. The AI ​​worker can also use the camera function of a smart device to scan QR codes on inventory items and automatically update the database.

[1075] As a concrete example, consider inventory management at a logistics center. Employees can scan the QR codes of inventory items with their smart devices, automatically updating inventory data. Furthermore, when picking items, AI workers can suggest optimal picking routes, improving employee efficiency.

[1076] An example of a prompt is "Implement a QR code scanning function to streamline inventory management," which would enable more efficient inventory management using smart devices.

[1077] In this way, the system of the present invention can significantly improve the operational efficiency of a logistics center, reduce the burden on employees, and increase productivity.

[1078] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1079] Step 1:

[1080] A user starts work using a smart device. Agent software is installed on the smart device and collects the user's operation logs in real time. The collected operation logs include application usage information, operation details, timestamps, etc. This log data is encrypted and sent to the server. The input is the user's operation, and the output is the operation log.

[1081] Step 2:

[1082] The server stores the operation logs it receives in a database. The server then converts the operation logs into a format that is easy to analyze and stores them. Specific data processing includes timestamp format conversion and input content classification. The input is encrypted operation logs, and the output is operation log data converted into a standard format for analysis.

[1083] Step 3:

[1084] The server uses a machine learning algorithm to analyze the stored operation logs. It classifies and clusters the data to detect common tasks. Specifically, it identifies patterns of operations frequently performed by employees and recognizes them as common tasks. The input is operation log data in a standard format, and the output is a list of detected common tasks.

[1085] Step 4:

[1086] The server uses natural language processing technology to perform a detailed analysis of common tasks. Specifically, it understands the intent behind the operation procedures and instructions from the text data in the operation log. This analysis generates a script to efficiently automate the common tasks. The input is a list of common tasks, and the output is an automation script.

[1087] Step 5:

[1088] The server builds an AI worker based on the generated script. The AI ​​worker is a program that automatically executes specific tasks based on the generated script. The input is the automation script, and the output is the AI ​​worker program.

[1089] Step 6:

[1090] An AI worker starts working on a smart device. For example, the smart device's camera scans a QR code and automatically updates inventory data. An algorithm is also run to suggest the optimal route for the picking list. The inputs are inventory items and picking data, and the output is the updated inventory data and the suggested picking route.

[1091] An example of a prompt is "Implement a QR code scanning function to streamline inventory management," which would enable efficient inventory management using smart devices.

[1092] The above is the specific processing flow of the system for realizing the application example.

[1093] 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.

[1094] This invention is a system that simultaneously collects and analyzes employees' PC operation logs and emotional states, and automates common work tasks. This system not only improves work efficiency but also reduces employees' stress levels, providing a more comfortable working environment.

[1095] Overall system configuration

[1096] First, agent software is installed on the user's device. This agent software uses an emotion engine to collect emotional data in real time, along with the user's PC operation log. The operation log includes application usage, operation details, timestamps, and input details. Emotional data includes biometric information such as the user's facial expression, voice tone, and heart rate.

[1097] Data collection

[1098] The agent software encrypts the collected operation logs and emotional data and periodically transmits them to the company's server, which stores the received data in a database for subsequent analysis.

[1099] Data analysis

[1100] The server analyzes the stored operation logs and emotional data using machine learning algorithms and natural language processing technology. This analysis detects common tasks performed by multiple employees. Analysis of the emotional data also makes it possible to evaluate the level of stress and fatigue that a particular task causes to the user.

[1101] Generating automation scripts

[1102] Based on the detected common tasks, the server generates an automation script. This script combines the common tasks into a single process and includes instructions for efficient execution. Furthermore, the script can be adjusted based on the user's emotional data. For example, if a particular task causes high stress, the script can be optimized to perform the task in a more efficient manner.

[1103] AI worker generation and execution

[1104] The server generates an AI worker to execute the generated script. This AI worker is a virtual worker that automatically performs specific tasks. The AI ​​worker executes the task according to a schedule and sends the results to the server as a log. This eliminates the need for employees to perform the task manually, improving work efficiency.

[1105] Emotional Feedback

[1106] The server analyzes the user's emotional data and the AI ​​worker's performance results, and provides real-time feedback. For example, it can recommend a break if the user is feeling stressed, or suggest adjustments to the work environment. This feedback is also reflected in the next script generation, further optimizing the entire system.

[1107] Specific examples

[1108] For example, a company regularly creates sales reports and uploads them to a shared folder. Employees spend a lot of time on this task, and they often find it particularly stressful. The agent software collects each employee's operation log and emotional data, such as facial expressions and voice tone, and the server analyzes them. The software then detects common tasks involved in creating sales reports and uploading them to the folder, generating a script to automate the task. This script is optimized to reduce stress, and an AI worker executes it, improving work efficiency while reducing employee stress. Repeating this entire process simultaneously improves the company's operational efficiency and employee satisfaction.

[1109] As described above, the system of the present invention simultaneously improves business efficiency and manages the emotional state of employees, thereby improving productivity across the entire company.

[1110] The processing flow will be explained below.

[1111] Step 1:

[1112] Terminal

[1113] Agent software is installed on each employee's PC. The agent software collects the employee's PC operation log and emotional data in real time. The operation log includes the application used, operation details, timestamp, and input content. Emotional data includes facial expressions, voice tone, heart rate, etc.

[1114] Step 2:

[1115] Terminal

[1116] The agent software encrypts the collected operation logs and emotional data and sends them to the company's server at regular intervals (for example, every hour).

[1117] Step 3:

[1118] server

[1119] The company's server stores the received operation logs and emotion data in a database. The database stores each employee's operation log and emotion data in chronological order and creates an index to facilitate search and analysis.

[1120] Step 4:

[1121] server

[1122] Machine learning algorithms and natural language processing technology are applied to the saved operation logs and emotion data. Based on the operation data, frequency analysis and pattern recognition are performed to detect tasks that are commonly performed by multiple employees (common tasks). At the same time, emotion data is analyzed to evaluate the stress level during specific tasks.

[1123] Step 5:

[1124] server

[1125] Based on the analysis results, a list of identified common tasks is created, and an automation script is generated based on the list. The automation script includes a series of steps to efficiently execute the detected common tasks. Furthermore, optimization is performed to reduce stress levels during work based on emotion data.

[1126] Step 6:

[1127] server

[1128] Run the generated script in a test environment to check its operation. Test whether the script has errors and runs as expected. Fix any defects or areas for improvement that are found.

[1129] Step 7:

[1130] server

[1131] To operate the script in a real-world environment after testing, an AI worker is generated. This AI worker is a virtual worker that automatically performs specific tasks based on the script.

[1132] Step 8:

[1133] Terminal and Server

[1134] An AI worker performs a specific task according to a schedule, for example, starting data entry work at a specific time each day and sending the results as a log to a server after completion.

[1135] Step 9:

[1136] server

[1137] The execution results and emotional data are analyzed again to provide real-time feedback to the user. If the user's stress level is high, the system will recommend taking a break or suggest adjustments to the work environment. The feedback information will also be reflected in the next script generation, optimizing the entire system.

[1138] Step 10:

[1139] server

[1140] Periodically, an analysis report of the execution results and emotional data is generated and provided to users and managers. The report includes information such as how much work efficiency has improved and how stress levels have changed. Based on this, if further improvements are needed, the script can be updated or the AI ​​workers adjusted.

[1141] Example 2

[1142] 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."

[1143] Modern companies are required to improve employee work efficiency while reducing employee stress levels and providing a comfortable work environment. However, conventional systems do not adequately automate work tasks or optimize work processes by taking into account the emotional state of employees. This has resulted in problems such as poor work efficiency and the accumulation of employee stress.

[1144] 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.

[1145] In this invention, the server includes means for collecting employee operation logs and emotional data, means for saving the collected operation logs and emotional data, means for analyzing the saved operation logs and emotional data to detect common tasks and stress levels, means for generating a script to automate the detected common tasks, means for generating an AI worker who executes the generated script, means for the AI ​​worker to perform a specific task, and means for providing feedback in real time based on the emotional data. This makes it possible to efficiently automate employee work tasks while optimizing work processes taking into account the emotional states of employees.

[1146] An "operation log" is data that records the operations performed on devices used by employees, application usage status, timestamps, input content, etc.

[1147] "Emotion data" refers to data including biometric information such as the user's facial expression, voice tone, and heart rate, and represents the user's emotional state.

[1148] "Means for collection" refers to a function or device for acquiring operation logs and emotional data from a terminal and storing them as data.

[1149] "Storage means" refers to a function or device that stores collected operation logs and emotion data in a database or recording device.

[1150] "Means for analysis" refers to algorithms and programs that process saved operation logs and emotional data to detect common tasks and stress levels.

[1151] "Common work" refers to business tasks that are commonly performed by multiple employees.

[1152] "Script generation means" refers to a program or algorithm that generates instructions or code to automate the common tasks detected.

[1153] An "artificial intelligence worker" is a virtual worker that executes the generated automation script and is a system that automatically executes specific tasks.

[1154] "Means for providing feedback in real time" refers to a function or device that provides immediate improvement suggestions or advice to the user based on emotional data or work results.

[1155] This invention is a system that simultaneously collects and analyzes employees' PC operation logs and emotional states, automating common work tasks. This not only improves work efficiency but also reduces employees' stress levels, providing a more comfortable working environment.

[1156] Installing the Agent Software

[1157] First, the user installs agent software on their device. This agent software has the ability to collect PC operation logs and emotional data in real time. Specifically, the operation log records application usage, operation details, timestamps, input details, etc., while the emotional data is collected by using a webcam and microphone to collect biometric information such as the user's facial expressions, voice tone, and heart rate.

[1158] Data collection and transmission

[1159] The device encrypts the operation logs and emotion data collected by the agent software and periodically sends them to the server using powerful encryption technology such as AES-256, with the data being sent in batches, for example, every hour.

[1160] Data storage and analysis

[1161] The server stores the received data in a database. Using a database management system (DBMS), the data is organized into an easily accessible format. The server then uses machine learning algorithms and natural language processing techniques to analyze the stored operation logs and emotion data. Common work tasks are extracted from the operation logs, and the emotion data is used to evaluate the stress and fatigue levels that specific tasks cause to users. Python's scikit-learn and TensorFlow are used for the analysis.

[1162] Generating automation scripts

[1163] Based on the analysis results, the server generates a script for automation. This script contains specific steps for efficiently performing common tasks. For example, a script for automating the creation of sales reports contains instructions for automatically entering data into a template file and automatically uploading it to a specified folder. The following prompt is input into the generative AI model to generate a script: "Please generate an automation script that creates a sales report and uploads it to a specific folder."

[1164] AI worker generation and execution

[1165] The server generates an AI worker to execute the generated script. This AI worker automatically executes specific tasks according to a schedule. For example, it is set to create and upload a sales report every Friday at 10:00 AM. The AI ​​worker executes the task and sends the results to the server as a log.

[1166] Providing emotional feedback

[1167] Finally, the server comprehensively analyzes the user's emotional data and the AI ​​worker's performance results and provides real-time feedback. For example, if the user indicates a high stress level, a notification recommending a break will be sent. This feedback will also be reflected in the next script generation, further optimizing the entire system. For example, a notification saying "Your stress level is high, so we recommend you take a break" will be displayed on the user's screen.

[1168] As described above, the present invention simultaneously improves business efficiency and manages the emotional state of employees, thereby improving productivity across the entire company.

[1169] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1170] Step 1:

[1171] The user installs agent software on their device. This agent software collects operation logs, such as application usage, operation details, timestamps, and input details, as well as emotional data, such as the user's facial expressions, voice tone, and heart rate, in real time using a webcam and microphone. The input is the installation of the agent software, and the output is the start of collection of operation logs and emotional data.

[1172] Step 2:

[1173] The terminal encrypts the operation log and emotion data collected by the agent software. Specifically, it uses a strong encryption technique such as AES-256. The encrypted data is then sent to the server at regular intervals (for example, every hour). The input is the collected operation log and emotion data, and the output is the encrypted data sent to the server.

[1174] Step 3:

[1175] The server receives the encrypted data, decrypts it, and stores it in a database. Specifically, it uses a database management system (DBMS) to organize the data and make it more accessible. The input is the encrypted data, and the output is the raw data stored in the database.

[1176] Step 4:

[1177] The server analyzes the stored operation logs and emotion data. Specific operations include machine learning algorithms such as Python's scikit-learn and TensorFlow, as well as natural language processing technology. Common work tasks are extracted from the operation logs, and the emotion data is used to evaluate the stress and fatigue levels that specific tasks cause to users. The input is the operation logs and emotion data stored in the database, and the output is the detection results of common tasks and stress levels.

[1178] Step 5:

[1179] The server generates an automation script based on the analysis results. The following prompt is input to the generative AI model: "Please generate an automation script to create a sales report and upload it to a specific folder." The output of the generated script contains specific steps for efficiently performing common tasks. The input is the common tasks and stress level detection results, and the output is the automation script.

[1180] Step 6:

[1181] The server generates an AI worker to execute the generated script. This AI worker automatically executes specific tasks according to a schedule. For example, it is set to create and upload a sales report every Friday at 10:00 AM. The AI ​​worker executes the task and sends the results as a log to the server. The input is the automation script, and the output is the task execution results and log.

[1182] Step 7:

[1183] The server comprehensively analyzes the user's emotional data and the AI ​​worker's performance results and provides real-time feedback. Specifically, if stress levels are rising, it sends a notification recommending a break. The input is the emotional data and a log of the performance results, and the output is a feedback notification. For example, a message such as "Your stress level is high, so we recommend you take a break" is displayed on the user's screen.

[1184] Through the above steps, the present invention can simultaneously improve work efficiency and manage the emotional state of employees, thereby improving the productivity of the entire company.

[1185] (Application example 2)

[1186] 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."

[1187] Conventional factory quality inspection processes rely on manual work, resulting in problems such as reduced work efficiency, manual errors, and increased employee stress. Furthermore, improvements to the work environment have not been made with consideration for the emotional state of employees, making it difficult to improve the work environment. Therefore, there is a need for a method to improve the efficiency of the quality inspection process, reduce employee stress, and optimize the work environment.

[1188] 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.

[1189] In this invention, the server includes means for collecting employee operation logs, means for saving the collected operation logs, means for analyzing the saved operation logs and detecting common tasks, means for generating scripts to automate the detected common tasks, means for generating AI workers to execute the generated scripts, means for collecting and encrypting operation logs and employee emotion data related to robots that perform quality inspections in factories and sending them to a cloud server, means for analyzing the operation logs and emotion data using a machine learning algorithm in the cloud server to optimize the quality inspection process, and means for generating optimized automation scripts and for the AI ​​workers to execute the quality inspection process. This enables the automation and optimization of the quality inspection process, reducing employee stress and improving the work environment.

[1190] An "operation log" is a series of operation history recorded when an employee operates a PC or robot, and includes application usage status, input content, and timestamps.

[1191] "Emotional data" refers to data about an employee's emotional state analyzed based on biometric information such as facial expressions, voice tone, and heart rate.

[1192] An "automation script" is a program procedure manual that is generated to automatically execute a specific task based on the analyzed operation log.

[1193] An "AI worker" is a virtual worker that performs work based on an automation script, an artificial intelligence-based system that performs specific tasks automatically.

[1194] A "cloud server" is a remote server that stores and processes data via the Internet, and is used to store and analyze collected operation logs and emotion data.

[1195] "Quality inspection process" refers to a series of work procedures for checking and evaluating the quality of products and services, including inspection work carried out within the factory.

[1196] A "machine learning algorithm" is a computational algorithm that automatically learns patterns and rules from large amounts of data and uses them to make predictions and analyses.

[1197] First, agent software is installed on the robots and the terminals used by workers in the factory. This agent software is responsible for collecting the robot's operation log and the employee's emotional data. The operation log includes the robot's movements, setting values, timestamps, error messages, etc., while the emotional data includes the employee's facial expressions, voice tone, heart rate, and other biometric information.

[1198] The operation logs and emotion data collected by the agent software are encrypted and sent via a local server in the factory to a cloud server, which then stores the received data in a database and uses it for data analysis.

[1199] The cloud server analyzes the stored operation logs and emotion data using machine learning algorithms and natural language processing technology, which enables it to detect common tasks in the quality inspection process and the stress levels of employees associated with those tasks.

[1200] Based on the detected common tasks, the cloud server then generates scripts to automate the quality inspection process, optimizing the efficiency of areas that are particularly stressful for employees, and distributes the scripts to robots that act as AI workers.

[1201] The AI ​​worker robot automatically executes the quality inspection process according to the generated script, and once the quality inspection is complete, the results are sent to the cloud server via the local server and stored in a database.

[1202] The cloud server also provides real-time feedback on employee emotional data and the AI ​​worker's performance. If an employee's stress level increases, the system can recommend a break or adjust the work environment. This feedback is then reflected in the next script generation, further optimizing the overall system.

[1203] As a concrete example, consider a case where a particular inspection in a factory is extremely stressful for employees. In this case, the agent software collects operation logs and emotional data, which are then analyzed by a cloud server. Based on the analysis results, a script is generated to automate the stressful inspection process, which is then executed by an AI worker, reducing the burden on the employees.

[1204] An example of a prompt for a generative AI model is:

[1205] Generate automation scripts to streamline the quality inspection process based on given operation logs and sentiment data, with a particular focus on optimizing areas that cause high levels of stress for employees.

[1206] In this way, it is possible to automate the quality inspection process and optimize the emotional state of employees at the same time.

[1207] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1208] Step 1:

[1209] Installing the Agent Software

[1210] Agent software is installed on factory robots and employee devices, allowing for the collection of operation logs and emotional data.

[1211] Input: Agent software, robots and terminals

[1212] Output: Terminal and robot ready to collect data

[1213] Step 2:

[1214] Starting Data Collection

[1215] The agent software begins collecting the robot's operation logs and employee emotional data. The operation logs include the robot's movements, settings, timestamps, error messages, etc. Emotional data is obtained from facial expressions, voice tone, heart rate, etc.

[1216] Input: Robot operation status, employee emotional state

[1217] Output: Collected operation logs and emotion data

[1218] Step 3:

[1219] Data encryption and transmission

[1220] The agent software encrypts the operation logs and emotional data collected and sends them to a cloud server via a local server in the factory.

[1221] Input: Collected operation logs and emotion data

[1222] Output: Encrypted operation log and emotion data, cloud server

[1223] Step 4:

[1224] Saving to a database

[1225] The cloud server receives the encrypted operation log and emotion data and stores them in a database.

[1226] Input: Encrypted operation log and emotion data

[1227] Output: Operation logs and emotion data stored in a database

[1228] Step 5:

[1229] Data analysis

[1230] The cloud server uses machine learning algorithms and natural language processing technology to analyze the stored operation logs and emotion data, and through this analysis, detects common tasks and stress levels during the quality inspection process.

[1231] Input: Operation log and emotion data

[1232] Output: Analysis results (detection of common tasks, evaluation of stress level)

[1233] Step 6:

[1234] Generating automation scripts

[1235] Based on the analysis results, the cloud server generates scripts to automate the quality inspection process, which are optimized to streamline particularly high-stress areas.

[1236] Input: Analysis results

[1237] Output: Automation script

[1238] Step 7:

[1239] Distributing scripts to AI workers

[1240] The cloud server distributes the generated automation script to the robots, which then function as AI workers.

[1241] Input: Automation script

[1242] Output: A robot that acts as an AI worker

[1243] Step 8:

[1244] Automatic execution of quality inspection processes

[1245] AI workers follow the generated script and automatically carry out the quality inspection process.

[1246] Input: Automation script

[1247] Output: Quality inspection results, robot execution log

[1248] Step 9:

[1249] Sending and saving results

[1250] Once the AI ​​worker completes the quality inspection, the results and execution log are sent to the cloud server via the local server and stored in a database.

[1251] Input: Quality inspection results, robot execution log

[1252] Output: Execution results and logs stored in a database

[1253] Step 10:

[1254] Real-time feedback

[1255] The cloud server analyzes employee emotional data and the AI ​​worker's performance, providing real-time feedback. If an employee's stress level is increasing, the system will recommend taking a break or adjust the work environment.

[1256] Input: Emotion data, execution results

[1257] Output: Feedback (recommendation of breaks, adjustment of work environment)

[1258] This allows for the automation of quality inspection processes and the optimization of the emotional state of employees.

[1259] 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.

[1260] 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.

[1261] 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.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] 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).

[1266] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1267] 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."

[1268] 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.

[1269] 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).

[1270] 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.

[1271] 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.

[1272] 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.

[1273] 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.

[1274] 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.

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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.

[1280] The following is further disclosed regarding the above embodiment.

[1281] (Claim 1)

[1282] A means for collecting employee operation logs;

[1283] A means for storing the collected operation logs;

[1284] A means for analyzing the saved operation log and detecting common operations;

[1285] means for generating scripts to automate the detected common tasks;

[1286] means for generating an AI worker that executes the generated script;

[1287] A system that includes a means for the generated AI worker to perform specific tasks.

[1288] (Claim 2)

[1289] 2. The system according to claim 1, wherein natural language processing technology is used to analyze the operation log.

[1290] (Claim 3)

[1291] 10. The system of claim 1, wherein the system uses a machine learning algorithm to detect common tasks.

[1292] "Example 1"

[1293] (Claim 1)

[1294] A means for collecting employee operation logs;

[1295] A means for storing the collected operation logs;

[1296] A means for analyzing the saved operation log and detecting common operations;

[1297] means for generating scripts to automate the detected common tasks;

[1298] A means to test the generated script in a test environment,

[1299] means for generating an AI worker that executes the generated script;

[1300] A system that includes a means for the generated AI worker to perform specific tasks.

[1301] (Claim 2)

[1302] 2. The system according to claim 1, wherein natural language processing technology is used to analyze the operation log.

[1303] (Claim 3)

[1304] 10. The system of claim 1, wherein the system uses a machine learning algorithm to detect common tasks.

[1305] "Application Example 1"

[1306] (Claim 1)

[1307] A means for collecting employee operation logs;

[1308] A means for storing the collected operation logs;

[1309] A means for analyzing the saved operation log and detecting common operations;

[1310] means for generating scripts to automate the detected common tasks;

[1311] means for generating an artificial intelligence worker that executes the generated script;

[1312] A means for the generated AI worker to perform a specific task;

[1313] a means including a smart device that analyzes an operation log and issues a command to execute an automation script;

[1314] A means for analyzing common tasks from employee operation logs using machine learning algorithms;

[1315] A method for extracting tasks for efficiency from log information using natural language processing technology, and

[1316] A means to automatically update inventory data using the camera function of smart devices,

[1317] A system that includes a means for analyzing common tasks and proposing optimal routes for picking products.

[1318] (Claim 2)

[1319] 2. The system according to claim 1, wherein natural language processing technology is used to analyze the operation log.

[1320] (Claim 3)

[1321] 10. The system of claim 1, wherein the system uses a machine learning algorithm to detect common tasks.

[1322] "Example 2: Combining Emotion Engines"

[1323] (Claim 1)

[1324] A means of collecting employee operation logs and emotion data;

[1325] A means for storing the collected operation logs and emotion data;

[1326] A means for analyzing the saved operation log and emotion data to detect common tasks and stress levels;

[1327] means for generating scripts to automate the detected common tasks;

[1328] means for generating an artificial intelligence worker that executes the generated script;

[1329] The means by which the AI ​​worker performs a specific task;

[1330] A system including a means for providing real-time feedback based on emotional data.

[1331] (Claim 2)

[1332] The system according to claim 1, wherein natural language processing technology is used to analyze the operation log and emotion data.

[1333] (Claim 3)

[1334] 10. The system of claim 1, wherein the system uses machine learning algorithms to detect common tasks and analyze sentiment data.

[1335] "Application example 2 when combining emotion engines"

[1336] (Claim 1)

[1337] A means for collecting employee operation logs;

[1338] A means for storing the collected operation logs;

[1339] A means for analyzing the saved operation log and detecting common operations;

[1340] means for generating scripts to automate the detected common tasks;

[1341] means for generating an AI worker that executes the generated script;

[1342] A means for collecting, encrypting, and transmitting to a cloud server operation logs and employee emotional data related to robots that perform quality inspections within factories;

[1343] A method for optimizing the quality inspection process by analyzing operation logs and emotion data using machine learning algorithms on a cloud server;

[1344] A system that generates optimized automation scripts and includes a means for AI workers to execute quality inspection processes.

[1345] (Claim 2)

[1346] 2. The system according to claim 1, wherein natural language processing technology is used to analyze the operation log.

[1347] (Claim 3)

[1348] 10. The system of claim 1, wherein the system uses a machine learning algorithm to detect common tasks. [Explanation of symbols]

[1349] 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 for collecting employee operation logs; A means for storing the collected operation logs; A means for analyzing the saved operation log and detecting common operations; means for generating scripts to automate the detected common tasks; means for generating an AI worker that executes the generated script; A system that includes a means for the generated AI worker to perform specific tasks.

2. 2. The system according to claim 1, wherein natural language processing technology is used to analyze the operation log.

3. The system of claim 1 , wherein the system uses a machine learning algorithm to detect common tasks.

Images