system

Abstract

We provide the system. [Solution] Means of collecting log data, A means for analyzing the aforementioned log data to identify error patterns, A means for predicting the probability of an error occurring based on the aforementioned error pattern, A means for automatically adjusting system settings based on the aforementioned prediction, A means of notifying a warning when an error occurs, A means of performing self-learning using feedback data and updating the analysis model, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a business environment using RPA, errors or process stops occur, resulting in a decrease in business efficiency and an adverse impact on productivity. In addition, before an error occurs, its possibility cannot be predicted in advance and responded to quickly, resulting in an increase in operation costs and a loss of user convenience as a result. Therefore, it is desired to provide a system that can continue efficient operation while preventing business interruption.

Means for Solving the Problems

[0005] [[ID=4少]] This invention provides a means for collecting and analyzing log data to identify error patterns, thereby monitoring the occurrence of errors during business operations. Furthermore, it aims to prevent errors by introducing a means for predicting the probability of error occurrence based on the error patterns. In addition, it prevents business interruptions by incorporating a means for automatically adjusting system settings based on the predictions. Moreover, it provides a means for promptly notifying warnings when errors occur, facilitating immediate response. Furthermore, it continuously improves accuracy by using a means for self-learning with feedback data and updating the analysis model. In this way, it provides a system that significantly improves the efficiency and productivity of business operations.

[0006] "Log data" refers to information that records the operating status and error messages of an RPA system.

[0007] "Analysis" is the process of analyzing collected log data to identify error patterns and abnormal behavior.

[0008] An "error pattern" refers to a common error occurrence or malfunction trend identified from log data.

[0009] "Error probability" is a predicted value, based on analysis, that indicates the likelihood of a specific error occurring in the future.

[0010] "Adjusting system settings" refers to the action of making changes to optimize the parameters and processes of the RPA system based on the prediction results.

[0011] "Warning notifications" is a function that sends alerts to relevant parties when an error occurs or is predicted.

[0012] "Feedback data" refers to data used to improve a self-learning model by inputting system execution results and new log information.

[0013] "Self-learning" is the process by which an AI model autonomously improves its accuracy and performance based on feedback data.

[0014] "Updating the analysis model" is a procedure that revises the analysis algorithm through self-learning, enabling more accurate predictions and control. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0017] First, the language used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is implemented as a system that uses AI to automatically monitor and control an RPA system. This system is constructed as software that includes multiple modules executed by a server.

[0037] First, the server collects operation logs of the RPA system in real time. The collected log data is stored in a database on the server and used for later analysis.

[0038] The collected log data is processed by the server's analysis module. This analysis module combines machine learning and natural language processing techniques to identify error messages and anomalous patterns within the logs. The server analyzes these patterns to identify error patterns. The results of the analysis are used to predict the likelihood of future errors.

[0039] The prediction module calculates the probability of an error occurring based on past analysis results and real-time log data. Based on this prediction, the server automatically selects how to adjust the system settings. This helps the RPA system avoid expected errors.

[0040] Furthermore, if an error occurs, the server will immediately issue a warning alert. This alert will be sent to terminals and user devices, prompting administrators to take prompt action.

[0041] Furthermore, the server acquires feedback data and uses it to perform self-learning. This learning process improves accuracy over time by continuously updating the analysis model. In this way, the system always maintains an up-to-date state, enabling more accurate and efficient control.

[0042] As a concrete example, suppose a company is using RPA to automate routine data processing tasks. This company's servers constantly monitor the log data generated daily, and if they detect any signs of errors in the database connection, they proactively change the connection method or take preventative measures to increase the necessary resources. This ensures that the company's data processing operations continue uninterrupted, leading to increased productivity.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server collects log data from the RPA system in real time. This includes retrieving log information using an API. The collected logs are temporarily stored in storage for later analysis.

[0046] Step 2:

[0047] The server sends the collected log data to an analysis module. The analysis module uses natural language processing technology to extract keywords from error messages and machine learning algorithms to identify anomalous patterns.

[0048] Step 3:

[0049] The server predicts the probability of an error occurring based on the analysis results. The prediction module uses a statistical model to calculate the probability that a specific error will occur within a specified time.

[0050] Step 4:

[0051] The server automatically adjusts system settings based on the predicted likelihood of errors occurring. This includes changing process priorities and optimizing resource allocation.

[0052] Step 5:

[0053] The terminal receives warning alerts from the server. When an error occurs or the probability of an error increases, a notification is immediately sent to the relevant parties.

[0054] Step 6:

[0055] The server receives the execution results as feedback data and starts a self-learning process. In this process, the analysis model is updated, improving the accuracy of future predictions.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] Conventional systems suffer from a lack of real-time detection and prediction of abnormal behavior and errors, resulting in reduced system reliability and efficiency. Furthermore, they lack adequate warnings and automatic adjustments to system settings when errors occur, making rapid and appropriate responses difficult. Additionally, existing analysis methods suffer from insufficient self-learning of analysis algorithms through feedback, making long-term accuracy improvement challenging.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for collecting data signals, means for analyzing the data signals to identify abnormal patterns, means for predicting the probability of failure based on the abnormal patterns, means for automatically adjusting protocol settings, means for sending warnings when a failure occurs, and means for self-learning using evaluation data to update the analysis algorithm. As a result, the system can rapidly detect and predict anomalies, and its reliability and efficiency are further improved through appropriate responses and automatic adjustments. In addition, the accuracy of the analysis model can be improved through self-learning.

[0061] A "data signal" is a flow of electrical or electronic information that indicates the operating status or events of a system.

[0062] An "abnormal pattern" is a collection of phenomena that deviate from normal operation and exhibit reproducible behavior or states.

[0063] "Failure probability" is a statistically significant value indicating the likelihood that a system will enter an abnormal state within a specific period of time.

[0064] "Protocol configuration" refers to the arrangement of a set of procedures and rules concerning communication and operation within a system.

[0065] A "warning" is a notification method that informs users and administrators of abnormalities or conditions requiring attention within a system.

[0066] "Evaluation data" refers to information generated for comparison and measurement based on the system's operating results and feedback.

[0067] "Self-learning" is the process by which a system independently improves its data analysis algorithms based on its experience.

[0068] An "analysis algorithm" is a set of calculation procedures or formulas used in a system to detect patterns in data and interpret the results.

[0069] In this invention, a server centrally manages and controls the entire system. The server first uses sensors and log collection software to collect data signals in real time. This utilizes encryption technologies such as SSL / TLS to ensure efficient data communication. The collected data signals are stored in a database on the server. At this stage, the database software functions, for example, as an SQL-based database management system.

[0070] Next, the server utilizes machine learning and natural language processing technologies in its analysis module. Specifically, it analyzes data using Python's TENSORFLOW® library and NLTK to identify anomalous patterns. Because the machine learning model is pre-trained, it is possible to extract data features with high accuracy. Once anomalous patterns are identified, the server calculates the probability of failure based on this. Statistical methods such as the ARIMA model are introduced for time series data analysis.

[0071] The server automatically adjusts protocol settings based on the obtained failure probability. This dynamic adjustment is performed by changing the system configuration via a REST API. Furthermore, if an error occurs, the server immediately issues a warning and notifies terminals and user devices. This is achieved by using SMTP for email sending and utilizing a push notification service to enable rapid warnings to users.

[0072] Furthermore, the server aggregates evaluation data and evolves the analysis algorithm through a self-learning process. This aims to improve the model's accuracy over the long term. For data analysis, Jupyter Notebook is used to evaluate the model's performance and incorporate feedback data.

[0073] As a concrete example, consider a case where a company manages data processing using a system. The server monitors log data and detects early signs of abnormal database connections. By changing the protocol settings at that time, it is possible to prevent interruptions to data processing operations. An example of a prompt message based on this invention would be, "Please tell me specific examples of error messages that frequently occur in RPA systems and how to deal with them."

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server collects data signals in real time through sensors and log collection software. The input is the operation logs of the RPA system, which become the data signals. Specifically, the log data is securely transferred to the server using SSL / TLS encryption. The output is the securely stored log data.

[0077] Step 2:

[0078] The server stores the collected log data in a database. The input for this step is the log data collected in step 1. Database software, such as an SQL-based system, is used to structure the data and format it for fast searching. The output is the formatted database entry.

[0079] Step 3:

[0080] The server analyzes data using machine learning techniques. The input is stored log data. The analysis module uses Python's TensorFlow library and NLTK to identify anomalous patterns and error messages. The output is the identified anomalous patterns. Specifically, it automatically runs a model based on the identified features.

[0081] Step 4:

[0082] The server calculates the probability of failure based on the analysis results. The anomaly pattern, which is the output of Step 3, becomes the input. The ARIMA model is used for time series data analysis and probability calculations. Specifically, it generates and records predicted values. The output is the calculated probability of failure.

[0083] Step 5:

[0084] The server dynamically adjusts the protocol settings based on the calculated failure probability. The input for this step is the failure probability. The system configuration is modified via a REST API, allowing for flexible configuration updates. The output is the updated protocol configuration.

[0085] Step 6:

[0086] The server sends a warning to the user's terminal or device if a malfunction is detected. The input is the result of the anomaly detection. Alerts are quickly sent via SMTP email notifications or push notification services. The output is the sent warning message.

[0087] Step 7:

[0088] The server collects evaluation data during operation and updates its analysis algorithm through self-learning. Input includes user feedback data. Specifically, it uses Jupyter Notebook for analysis and makes improvements based on the feedback. The output is the updated analysis algorithm.

[0089] (Application Example 1)

[0090] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0091] In modern manufacturing environments, the stable operation of robotic process automation (RPA) systems is crucial. However, detecting system anomalies and responding to error messages still largely rely on manual processes, making efficient monitoring difficult. Furthermore, when an anomaly occurs, immediate action is required to minimize its impact. To address this, a means of understanding the situation in real time and providing workers with visual information is necessary.

[0092] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0093] In this invention, the server includes means for collecting log data, means for analyzing the log data to identify error patterns, means for predicting the probability of error occurrence based on the error patterns, means for automatically adjusting system settings, means for notifying warnings when errors occur, means for self-learning using feedback data to update the analysis model, and a display device that visually displays the analysis results and assists in monitoring the operation. This makes it possible to quickly and efficiently detect abnormalities in the RPA system within the factory and provide information to workers in real time.

[0094] "Means for collecting log data" refers to a function that records and saves all actions, error messages, and other information that occur within the system in real time.

[0095] "Methods for identifying error patterns" refer to algorithms that analyze collected log data and identify signs of specific errors or abnormal patterns based on past data.

[0096] "Methods for predicting the probability of error occurrence" refer to technologies that calculate the probability of future errors occurring based on identified error patterns, thereby assisting in the stable operation of the system.

[0097] "Means for automatically adjusting system settings" refers to a function that changes system settings in advance according to the predicted probability of error occurrence, in order to avoid errors or mitigate their impact.

[0098] "Means of notifying warnings when errors occur" refers to an alert function that enables a quick response by immediately notifying relevant parties of detected errors.

[0099] "A means of updating the analysis model through self-learning using feedback data" refers to a process of continuously improving the model and enhancing the system's performance in order to improve the accuracy of the analysis by utilizing past data.

[0100] A "display device that visually displays analysis results and supports monitoring of operation" is a device that provides workers with visually analyzed information, enabling them to easily understand the system status and take necessary actions.

[0101] In this invention, a server-centered system plays a major role. The server first collects various log data in real time and stores it in a database. This log data includes the system's operating status and error messages, which are used for later analysis.

[0102] The server processes the collected log data using an analysis module. This analysis combines machine learning and natural language processing techniques, making it possible to detect specific error patterns. The results of the analysis are used to predict future error occurrences, and the server automatically adjusts system settings based on these predictions.

[0103] Furthermore, the analysis results are visually displayed on a display device. This display device is a terminal such as a smart device, and it notifies the user of the system status and warnings in real time. For example, a worker using smart glasses can check the error predictions and warnings displayed on the device and take appropriate action immediately.

[0104] For self-learning purposes, the server acquires feedback data and continuously updates its analysis model using that data. This allows the system to perform more precise and efficient control.

[0105] As a concrete example, if implemented in a factory, workers wearing smart glasses would visually monitor production line operation information, and if an anomaly is predicted, a warning would be displayed on the glasses. This would enable stable operation of the production line and rapid problem resolution. An example of input to the generated AI model could be a prompt message such as, "Create a step-by-step guide for developing a smart glasses application that analyzes log data from an RPA system, identifies error patterns, and issues warnings to factory workers."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server collects log data from the RPA system in real time. This input data includes operation logs and error messages. The collected data is stored in a database and used as the basis for analysis.

[0109] Step 2:

[0110] The server sends log data stored in the database to the analysis module. The analysis module applies machine learning models and natural language processing techniques to this input data to identify error patterns. Specifically, it performs data calculations aimed at identifying specific abnormal patterns by analyzing the content and frequency of error messages. A list of error patterns is generated as output.

[0111] Step 3:

[0112] The server uses a prediction module to calculate the probability of an error occurring based on the error patterns identified by the analysis module. Past error pattern data and current log data are used as input. The prediction algorithm processes this data and performs calculations based on system error messages and operational characteristics. As a result, the probability of an error occurring is output.

[0113] Step 4:

[0114] The server automatically adjusts the system settings based on the predicted error probability. This input includes probability information calculated by the prediction module. The server makes appropriate configuration changes and performs processes to ensure system stability. As a result, a system environment with fewer errors is output.

[0115] Step 5:

[0116] The server issues a warning to the terminal and notifies the user if an error occurs or is highly likely to occur. Inputs for this warning include the probability of the error occurring and a specific error pattern. The application on the terminal receives this notification in real time and displays a visual warning message to the user.

[0117] Step 6:

[0118] The user reviews the warning message displayed on the terminal and considers appropriate action. The specific input is the warning message from the system. Based on this information, the user decides on a course of action, supporting the efficient operation of the production line.

[0119] Step 7:

[0120] The server collects feedback data and initiates a self-learning process. This input includes user responses and feedback data on system operation. The server uses this data to update its machine learning algorithms and perform data calculations to build a more precise analytical model. The output of this process is the updated analytical model.

[0121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0122] This invention is implemented as a system that uses AI to automatically monitor and control an RPA system, and further combines it with an emotion engine that recognizes user emotions. In this system, a server is central, and processing is carried out through multiple modules.

[0123] First, the server collects log data related to the operation of the RPA system in real time. The collected data is stored in a database and used for analysis later.

[0124] Next, the server uses an analysis module to identify error patterns from the collected log data. This process employs machine learning and natural language processing techniques to analyze error messages and pinpoint the root cause of the problem. The results of the analysis are then used to predict future error occurrences.

[0125] Subsequently, the server uses a prediction module to calculate the probability of an error occurring. Based on the prediction results, the server automatically adjusts the system settings to prevent errors from occurring.

[0126] The server analyzes the user's emotional state using an emotion engine. This analysis can then be used to adjust system settings and processes, thereby providing a user-optimized operating environment.

[0127] Furthermore, if an error occurs, the device will receive a warning alert and immediately notify the administrator or responsible person.

[0128] The server uses feedback data to self-learn and sequentially updates its analysis model. The emotion engine also incorporates user emotion data as feedback, integrating it into the analysis model to improve the system's accuracy and efficiency.

[0129] As a concrete example, let's consider a company that uses RPA. This company's servers analyze log data obtained from daily operations and constantly monitor the system's operating status. One day, a user experiences system lag and expresses negative emotions. This emotion data is analyzed by an emotion engine, and the server dynamically adjusts resource allocation and takes immediate action to improve the user experience. As a result, business disruption can be minimized.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The server collects log data from the RPA system in real time. The logs stored in the database include process start times, end times, error messages, and more.

[0133] Step 2:

[0134] The server sends the collected log data to an analysis module. Here, error messages are analyzed using natural language processing, and error patterns are identified using machine learning models.

[0135] Step 3:

[0136] The server predicts the probability of errors occurring based on the analysis results. The prediction module calculates the likelihood of each error recurring, and uses this information to assess system risk.

[0137] Step 4:

[0138] The server automatically adjusts system settings based on predictions. These adjustments include schedule changes and resource allocation for load balancing.

[0139] Step 5:

[0140] The server uses an emotion engine to analyze the user's emotional state. It extracts emotional patterns from user input and feedback data and evaluates the user's current emotions.

[0141] Step 6:

[0142] The server optimizes the system based on the analysis results of the emotion engine. Based on the emotional state, it makes configuration changes to make the user's work environment more comfortable.

[0143] Step 7:

[0144] The terminal receives warning alerts from the server. If an error occurs or a high probability of error is detected, the relevant administrator or user is immediately notified.

[0145] Step 8:

[0146] The server updates the machine learning model using the execution results and feedback data. Sentiment data is also incorporated into the feedback to improve the model's accuracy and efficiency.

[0147] (Example 2)

[0148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0149] The present invention aims to provide a method for detecting unexpected system failures in advance and effectively addressing them in a robotic process automation (RPA) system. Furthermore, it addresses the challenge of improving the user experience by providing an optimized operating environment that takes into account the user's emotional state.

[0150] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0151] In this invention, the server includes means for collecting operational data, means for analyzing the operational data to identify abnormal patterns, means for predicting the probability of a problem occurring based on the abnormal patterns, and means for analyzing emotional states to adjust the operating environment. This enables the system to prevent problems while simultaneously providing a comfortable operating environment for the user.

[0152] "Operational data" refers to all information about operations and activities generated during the execution of a system.

[0153] An "abnormal pattern" refers to an event in a system that exhibits characteristic behavior, such as actions or error messages, that deviate from normal operation.

[0154] "Probability of problem occurrence" refers to a numerical evaluation of the likelihood of problems or errors occurring in a system.

[0155] "Configuration" refers to the setting, placement, or resource allocation of a system or service.

[0156] "Feedback information" refers to evaluations and re-entry information based on results and data obtained during system operation.

[0157] An "analytical model" refers to a mathematical or algorithmic framework or method for detecting, predicting, and solving problems based on collected data.

[0158] "Emotional state" refers to the state that represents the user's psychological response and emotions.

[0159] "Operating environment" refers to the interface and settings provided when a user interacts with the system.

[0160] This invention is implemented as an automated system for highly monitoring and controlling robotic process automation (RPA) systems. The system aims to detect system anomalies through the collection and analysis of operational data, and further optimize the operating environment by utilizing the user's emotional state.

[0161] The server first collects operational data from the RPA system in real time. This data collection is performed using standard data collection software, and the data is stored in a database. The stored data includes operation logs, error information, and user operation history.

[0162] Next, the server uses machine learning algorithms to analyze the collected operational data and identify abnormal patterns. This analysis applies anomaly detection algorithms and natural language processing techniques, and calculates the probability of a problem occurring based on what it has learned from past data.

[0163] Based on the predicted probability of problems occurring, the server automatically adjusts the system configuration. Specifically, the server changes resource allocation and prioritizes processes to prevent problems from occurring.

[0164] Furthermore, the server uses an emotion analysis engine to analyze the user's emotional state. This analysis measures user dissatisfaction and stress, and improves the user experience by making changes to the operating environment.

[0165] When an error occurs, the device receives a warning and immediately notifies the administrator or responsible person. This enables a quick response.

[0166] The server uses feedback information to self-learn and sequentially updates its analysis model. This continuously improves the system's accuracy and efficiency.

[0167] As a concrete example, suppose a user experiences system delays during work in a company's RPA system. When the user's negative reaction is analyzed by an emotion analysis engine, the server adjusts resource allocation and takes immediate action to improve the user experience.

[0168] As an example of a prompt to be input into the generating AI model, you can use the format: "List the system errors that are expected in the next task and suggest solutions, including sentiment responses, for each error."

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The server collects operational data from the RPA system in real time. Inputs include various log data (operation logs, error information, user operation history). Specifically, log collection software is used to organize the data and store it in a database. This process allows for a detailed record of what operations and events occurred.

[0172] Step 2:

[0173] The server feeds the collected operational data into the analysis module. The input is the log data collected in step 1. Using machine learning algorithms, the data is analyzed to identify anomalous patterns. Anomaly detection and clustering techniques are applied to extract patterns that deviate from normal operation. The output of this analysis lists anomalous patterns and potential problem areas.

[0174] Step 3:

[0175] The server operates a prediction module based on the analysis results to calculate the probability of a problem occurring. The anomaly patterns identified in step 2 are used as input. This module utilizes a statistical model to predict the probability of a problem occurring. The output of this process is the probability value of the error occurring.

[0176] Step 4:

[0177] The server automatically adjusts the system configuration based on the predicted probability of the problem occurring. The input is the probability of the problem occurring, obtained in step 3. This adjustment involves changing resource allocation and process priorities to take specific actions to prevent the problem from occurring. The output is the improved system configuration.

[0178] Step 5:

[0179] The server analyzes the user's emotional state using an emotion analysis engine. User input data (comments and feedback) is used as input. Natural language processing is used to identify emotions and analyze the user's psychological state. As output, optimization suggestions for the operating environment are made, leading to an improvement in the user experience.

[0180] Step 6:

[0181] The terminal receives a warning when an error occurs and notifies the administrator. The input for this step is the error message generated by the system. The terminal displays a visual alert and immediately notifies relevant parties via email or phone call notification. The output is the state in which the error notification was sent.

[0182] Step 7:

[0183] The server collects feedback information after the system goes live and updates the analysis model. The feedback data is used as input, and self-learning is performed based on it. The machine learning algorithm improves the model, and an analysis model with improved accuracy and effectiveness of the system is output.

[0184] (Application Example 2)

[0185] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0186] Many current automation systems focus on predicting and preventing errors, but they are not adequately equipped to optimize work instructions based on the emotional state of workers. As a result, this leads to increased worker stress and decreased overall work efficiency and satisfaction. Therefore, flexible system settings that take workers' emotional states into account are necessary.

[0187] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0188] In this invention, the server includes means for collecting log data, means for analyzing the log data to identify error patterns, and means for recognizing and analyzing the emotional state of the worker. This makes it possible to optimize work instructions according to the emotional state of the worker.

[0189] "Log data" refers to data that records information about the operation of a system and is used to monitor the normal operation of the system and the occurrence of errors.

[0190] An "error pattern" is a pattern that describes the characteristics of errors that occur during system operation, and is a collection of errors that share common characteristics identified from past data.

[0191] "Error probability" is a numerical representation of the likelihood of a system making an error, and it is predicted through analysis based on past error data.

[0192] "Automatic system setting adjustment" is an operation that automatically changes system settings to optimize system operation and performance based on the predicted probability of errors occurring.

[0193] "Feedback data" refers to information including performance data obtained during system operation, as well as user feedback and evaluations, and is used to improve system performance.

[0194] "Self-learning" is the process by which a system uses machine learning algorithms to improve its own analytical model and increase its accuracy.

[0195] "Worker's emotional state" refers to the mental and emotional conditions and reactions exhibited by those engaged in work, and is a factor that influences work efficiency and satisfaction.

[0196] An "analytical model" is a computational model designed to make predictions and classifications based on data, and it serves as a foundation for understanding and judging the operation of a system.

[0197] In the system implementing this invention, a server is central to the operation and functions in the following configuration. First, the server collects log data generated from each process within the system in real time. The log data contains information about the progress of the work and the occurrence of errors. Based on this data, the server uses an analysis module to identify error patterns and predicts the probability of error occurrence using a machine learning model (for example, a model using TensorFlow).

[0198] The server further collects the worker's emotional state via devices such as smart glasses using an emotion analysis module, and analyzes the emotional data. This analysis is performed using natural language processing technology (e.g., Google® Cloud Natural Language API). The results of the emotion analysis are reflected in the automatic adjustment of system settings, providing work instructions that are appropriate for the worker.

[0199] If an error occurs, the terminal receives an alert, enabling a quick response. Furthermore, the server has a self-learning function, improving accuracy by updating the analysis model based on feedback data. This could potentially utilize edge AI processors (e.g., NVIDIA Jetson).

[0200] A concrete example is a virtual assistant in a logistics center. By using this system, workers can receive appropriate work instructions in real time, even when they are feeling stressed, which ultimately improves work efficiency. An example of a prompt sentence to be input to the generative AI model used in this case would be: "Explain how smart glasses used in a logistics center can analyze employees' emotions in real time and improve work efficiency."

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The server collects log data generated from each process within the logistics center in real time. It uses log data acquired from each work station and sensor as input. This data is stored in a database and processed into a format usable for subsequent analysis. The output is statistical data accumulated in a management database.

[0204] Step 2:

[0205] The server uses the collected log data to identify error patterns in its analysis module. The stored log data is passed to the analysis module as input. During this process, machine learning techniques are used to scan the log data and identify sections that match past error patterns. A list of error patterns is generated as output.

[0206] Step 3:

[0207] The server predicts the probability of an error occurring based on identified error patterns. The input is a list of error patterns. The prediction module applies machine learning algorithms and uses natural language processing techniques to analyze the incoming error message data. The output is a predicted value for the probability of an error occurring.

[0208] Step 4:

[0209] The server automatically adjusts system settings based on the generated error probability. It uses predicted values ​​as input to optimize each system parameter. This adjustment reduces the risk of errors. The updated system settings are output.

[0210] Step 5:

[0211] The server notifies the terminal of an error when it occurs. The input consists of the error message and alarm information. Based on this, it generates a notification message and outputs an alert to the display device on the terminal.

[0212] Step 6:

[0213] The server uses feedback data to self-learn and update its analysis model. It applies feedback data and the current model as input. Machine learning algorithms are used to refine the model and improve its accuracy. The output is an improved analysis model.

[0214] Step 7:

[0215] The server analyzes the worker's emotional state data acquired from smart glasses. It uses emotional data from the smart glasses' camera and microphone as input. Natural language processing is used to analyze the emotions, and data representing the emotional state is generated as output.

[0216] Step 8:

[0217] The server optimizes work instructions based on the results of an emotional analysis of the worker. It uses emotional state data and information about the current work environment as input. It generates instructions to reduce worker stress and outputs them to the appropriate device.

[0218] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0219] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0220] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0224] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0225] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0226] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0227] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0228] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0229] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0230] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0231] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0232] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0233] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0234] This invention is implemented as a system that uses AI to automatically monitor and control an RPA system. This system is constructed as software that includes multiple modules executed by a server.

[0235] First, the server collects operation logs of the RPA system in real time. The collected log data is stored in a database on the server and used for later analysis.

[0236] The collected log data is processed by the server's analysis module. This analysis module combines machine learning and natural language processing techniques to identify error messages and anomalous patterns within the logs. The server analyzes these patterns to identify error patterns. The results of the analysis are used to predict the likelihood of future errors.

[0237] The prediction module calculates the probability of an error occurring based on past analysis results and real-time log data. Based on this prediction, the server automatically selects how to adjust the system settings. This helps the RPA system avoid expected errors.

[0238] Furthermore, if an error occurs, the server will immediately issue a warning alert. This alert will be sent to terminals and user devices, prompting administrators to take prompt action.

[0239] Furthermore, the server acquires feedback data and uses it to perform self-learning. This learning process improves accuracy over time by continuously updating the analysis model. In this way, the system always maintains an up-to-date state, enabling more accurate and efficient control.

[0240] As a concrete example, suppose a company is using RPA to automate routine data processing tasks. This company's servers constantly monitor the log data generated daily, and if they detect any signs of errors in the database connection, they proactively change the connection method or take preventative measures to increase the necessary resources. This ensures that the company's data processing operations continue uninterrupted, leading to increased productivity.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The server collects log data from the RPA system in real time. This includes retrieving log information using an API. The collected logs are temporarily stored in storage for later analysis.

[0244] Step 2:

[0245] The server sends the collected log data to an analysis module. The analysis module uses natural language processing technology to extract keywords from error messages and machine learning algorithms to identify anomalous patterns.

[0246] Step 3:

[0247] The server predicts the probability of an error occurring based on the analysis results. The prediction module uses a statistical model to calculate the probability that a specific error will occur within a specified time.

[0248] Step 4:

[0249] The server automatically adjusts system settings based on the predicted likelihood of errors occurring. This includes changing process priorities and optimizing resource allocation.

[0250] Step 5:

[0251] The terminal receives warning alerts from the server. When an error occurs or the probability of an error increases, a notification is immediately sent to the relevant parties.

[0252] Step 6:

[0253] The server receives the execution results as feedback data and starts a self-learning process. In this process, the analysis model is updated, improving the accuracy of future predictions.

[0254] (Example 1)

[0255] Next, we will describe Example 1. 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."

[0256] Conventional systems suffer from a lack of real-time detection and prediction of abnormal behavior and errors, resulting in reduced system reliability and efficiency. Furthermore, they lack adequate warnings and automatic adjustments to system settings when errors occur, making rapid and appropriate responses difficult. Additionally, existing analysis methods suffer from insufficient self-learning of analysis algorithms through feedback, making long-term accuracy improvement challenging.

[0257] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0258] In this invention, the server includes means for collecting data signals, means for analyzing the data signals to identify abnormal patterns, means for predicting the probability of failure based on the abnormal patterns, means for automatically adjusting protocol settings, means for sending warnings when a failure occurs, and means for self-learning using evaluation data to update the analysis algorithm. As a result, the system can rapidly detect and predict anomalies, and its reliability and efficiency are further improved through appropriate responses and automatic adjustments. In addition, the accuracy of the analysis model can be improved through self-learning.

[0259] A "data signal" is a flow of electrical or electronic information that indicates the operating status or events of a system.

[0260] An "abnormal pattern" is a collection of phenomena that deviate from normal operation and exhibit reproducible behavior or states.

[0261] "Failure probability" is a statistically significant value indicating the likelihood that a system will enter an abnormal state within a specific period of time.

[0262] "Protocol configuration" refers to the arrangement of a set of procedures and rules concerning communication and operation within a system.

[0263] A "warning" is a notification method that informs users and administrators of abnormalities or conditions requiring attention within a system.

[0264] "Evaluation data" refers to information generated for comparison and measurement based on the system's operating results and feedback.

[0265] "Self-learning" is the process by which a system independently improves its data analysis algorithms based on its experience.

[0266] An "analysis algorithm" is a set of calculation procedures or formulas used in a system to detect patterns in data and interpret the results.

[0267] In this invention, a server centrally manages and controls the entire system. The server first uses sensors and log collection software to collect data signals in real time. This utilizes encryption technologies such as SSL / TLS to ensure efficient data communication. The collected data signals are stored in a database on the server. At this stage, the database software functions, for example, as an SQL-based database management system.

[0268] Next, the server utilizes machine learning and natural language processing technologies in its analysis module. Specifically, it analyzes data using Python's TensorFlow library and NLTK, among others, to identify anomalous patterns. Because the machine learning model is pre-trained, it is possible to extract data features with high accuracy. Once anomalous patterns are identified, the server calculates the probability of failure based on this. Statistical methods such as the ARIMA model are introduced for time series data analysis.

[0269] The server automatically adjusts protocol settings based on the obtained failure probability. This dynamic adjustment is performed by changing the system configuration via a REST API. Furthermore, if an error occurs, the server immediately issues a warning and notifies terminals and user devices. This is achieved by using SMTP for email sending and utilizing a push notification service to enable rapid warnings to users.

[0270] Furthermore, the server aggregates evaluation data and evolves the analysis algorithm through a self-learning process. This aims to improve the model's accuracy over the long term. For data analysis, Jupyter Notebook is used to evaluate the model's performance and incorporate feedback data.

[0271] As a concrete example, consider a case where a company manages data processing using a system. The server monitors log data and detects early signs of abnormal database connections. By changing the protocol settings at that time, it is possible to prevent interruptions to data processing operations. An example of a prompt message based on this invention would be, "Please tell me specific examples of error messages that frequently occur in RPA systems and how to deal with them."

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The server collects data signals in real time through sensors and log collection software. The input is the operation logs of the RPA system, which become the data signals. Specifically, the log data is securely transferred to the server using SSL / TLS encryption. The output is the securely stored log data.

[0275] Step 2:

[0276] The server stores the collected log data in a database. The input for this step is the log data collected in Step 1. Using database software, such as an SQL-based system, the data is structured and formatted into a state where fast retrieval is possible. The output is the formatted database entry.

[0277] Step 3:

[0278] The server analyzes the data using machine learning techniques. The input includes the stored log data. The analysis module uses the Python TensorFlow library and NLTK to identify abnormal patterns and error messages. The output is the identified abnormal patterns. As a specific operation, the model is automatically executed based on the identified features.

[0279] Step 4:

[0280] The server calculates the probability of a fault occurrence based on the analysis results. The abnormal patterns, which are the output of Step 3, serve as the input. An ARIMA model is used for time series data analysis to perform the probability calculation. As a specific operation, predicted values are generated and recorded. The output is the calculated probability of a fault occurrence.

[0281] Step 5:

[0282] The server dynamically adjusts the protocol settings based on the calculated probability of a fault occurrence. The input for this step is the probability of a fault occurrence. The system configuration is changed via the REST API to flexibly update the settings. The output is the updated settings of the protocol.

[0283] Step 6:

[0284] When a fault is detected, the server sends a warning to the user's terminal or device. The input includes the result of the anomaly detection. Email notifications using SMTP or a push notification service are used to quickly send alerts. The output is the sent warning message.

[0285] Step 7:

[0286] The server collects evaluation data during operation and updates the analysis algorithm through self-learning. The input includes the user's feedback data. As a specific operation, it analyzes using Jupyter Notebook and makes improvements based on the feedback. The output is the updated analysis algorithm.

[0287] (Application Example 1)

[0288] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0289] In modern production sites, the stable operation of a robotic process automation (RPA) system is important. However, there are still many manual parts in the system's anomaly detection and error message handling, making efficient monitoring difficult. Also, when an anomaly occurs, immediate action is required to minimize its impact. Therefore, a means to grasp the situation in real time and provide visual information to workers is needed.

[0290] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0291] In this invention, the server includes means for collecting log data, means for analyzing the log data to identify error patterns, means for predicting the error occurrence probability based on the error patterns, means for automatically adjusting the system settings, means for notifying a warning when an error occurs, means for performing self-learning using feedback data to update the analysis model, and a display device for visually displaying the analysis results and assisting in monitoring the operation. Thereby, it becomes possible to quickly and efficiently detect anomalies in the RPA system within the factory and provide information to workers in real time.

[0292] "Means for collecting log data" refers to a function that records and saves all actions, error messages, and other information that occur within the system in real time.

[0293] "Methods for identifying error patterns" refer to algorithms that analyze collected log data and identify signs of specific errors or abnormal patterns based on past data.

[0294] "Methods for predicting the probability of error occurrence" refer to technologies that calculate the probability of future errors occurring based on identified error patterns, thereby assisting in the stable operation of the system.

[0295] "Means for automatically adjusting system settings" refers to a function that changes system settings in advance according to the predicted probability of error occurrence, in order to avoid errors or mitigate their impact.

[0296] "Means of notifying warnings when errors occur" refers to an alert function that enables a quick response by immediately notifying relevant parties of detected errors.

[0297] "A means of updating the analysis model through self-learning using feedback data" refers to a process of continuously improving the model and enhancing the system's performance in order to improve the accuracy of the analysis by utilizing past data.

[0298] A "display device that visually displays analysis results and supports monitoring of operation" is a device that provides workers with visually analyzed information, enabling them to easily understand the system status and take necessary actions.

[0299] In this invention, a server-centered system plays a major role. The server first collects various log data in real time and stores it in a database. This log data includes the system's operating status and error messages, which are used for later analysis.

[0300] The server processes the collected log data using an analysis module. This analysis combines machine learning and natural language processing techniques, making it possible to detect specific error patterns. The results of the analysis are used to predict future error occurrences, and the server automatically adjusts system settings based on these predictions.

[0301] Furthermore, the analysis results are visually displayed on a display device. This display device is a terminal such as a smart device, and it notifies the user of the system status and warnings in real time. For example, a worker using smart glasses can check the error predictions and warnings displayed on the device and take appropriate action immediately.

[0302] For self-learning purposes, the server acquires feedback data and continuously updates its analysis model using that data. This allows the system to perform more precise and efficient control.

[0303] As a concrete example, if implemented in a factory, workers wearing smart glasses would visually monitor production line operation information, and if an anomaly is predicted, a warning would be displayed on the glasses. This would enable stable operation of the production line and rapid problem resolution. An example of input to the generated AI model could be a prompt message such as, "Create a step-by-step guide for developing a smart glasses application that analyzes log data from an RPA system, identifies error patterns, and issues warnings to factory workers."

[0304] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0305] Step 1:

[0306] The server collects log data from the RPA system in real time. This input data includes operation logs and error messages. The collected data is stored in a database and used as the basis for analysis.

[0307] Step 2:

[0308] The server sends the log data stored in the database to the analysis module. The analysis module applies machine learning models and natural language processing techniques to this input data to identify error patterns. Specifically, it performs data operations aimed at identifying specific abnormal patterns by analyzing the content and frequency of error messages. As output, a list of error patterns is generated.

[0309] Step 3:

[0310] The server calculates the probability of error occurrence using the prediction module based on the error patterns identified by the analysis module. As input, past error pattern data and current log data are used. The prediction algorithm processes these data and performs data operations based on error messages and operation characteristics on the system. As a result, the probability of error occurrence is output.

[0311] Step 4:

[0312] The server automatically adjusts the system settings according to the predicted probability of error occurrence. This input includes the probability information calculated by the prediction module. The server performs appropriate setting changes and executes a process to ensure the stability of the system. As a result, a system environment with fewer errors is output.

[0313] Step 5:

[0314] When an error occurs or is predicted to occur with a high probability, the server issues a warning to the terminal and notifies the user. As input, there is the probability of error occurrence and specific error patterns. The application on the terminal receives this notification in real time and visually displays a warning message to the user.

[0315] Step 6:

[0316] The user reviews the warning message displayed on the terminal and considers appropriate action. The specific input is the warning message from the system. Based on this information, the user decides on a course of action, supporting the efficient operation of the production line.

[0317] Step 7:

[0318] The server collects feedback data and initiates a self-learning process. This input includes user responses and feedback data on system operation. The server uses this data to update its machine learning algorithms and perform data calculations to build a more precise analytical model. The output of this process is the updated analytical model.

[0319] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0320] This invention is implemented as a system that uses AI to automatically monitor and control an RPA system, and further combines it with an emotion engine that recognizes user emotions. In this system, a server is central, and processing is carried out through multiple modules.

[0321] First, the server collects log data related to the operation of the RPA system in real time. The collected data is stored in a database and used for analysis later.

[0322] Next, the server uses an analysis module to identify error patterns from the collected log data. This process employs machine learning and natural language processing techniques to analyze error messages and pinpoint the root cause of the problem. The results of the analysis are then used to predict future error occurrences.

[0323] Subsequently, the server uses a prediction module to calculate the probability of an error occurring. Based on the prediction results, the server automatically adjusts the system settings to prevent errors from occurring.

[0324] The server analyzes the user's emotional state using an emotion engine. This analysis can then be used to adjust system settings and processes, thereby providing a user-optimized operating environment.

[0325] Furthermore, if an error occurs, the device will receive a warning alert and immediately notify the administrator or responsible person.

[0326] The server uses feedback data to self-learn and sequentially updates its analysis model. The emotion engine also incorporates user emotion data as feedback, integrating it into the analysis model to improve the system's accuracy and efficiency.

[0327] As a concrete example, let's consider a company that uses RPA. This company's servers analyze log data obtained from daily operations and constantly monitor the system's operating status. One day, a user experiences system lag and expresses negative emotions. This emotion data is analyzed by an emotion engine, and the server dynamically adjusts resource allocation and takes immediate action to improve the user experience. As a result, business disruption can be minimized.

[0328] The following describes the processing flow.

[0329] Step 1:

[0330] The server collects log data from the RPA system in real time. The logs stored in the database include process start times, end times, error messages, and more.

[0331] Step 2:

[0332] The server sends the collected log data to an analysis module. Here, error messages are analyzed using natural language processing, and error patterns are identified using machine learning models.

[0333] Step 3:

[0334] The server predicts the probability of errors occurring based on the analysis results. The prediction module calculates the likelihood of each error recurring, and uses this information to assess system risk.

[0335] Step 4:

[0336] The server automatically adjusts system settings based on predictions. These adjustments include schedule changes and resource allocation for load balancing.

[0337] Step 5:

[0338] The server uses an emotion engine to analyze the user's emotional state. It extracts emotional patterns from user input and feedback data and evaluates the user's current emotions.

[0339] Step 6:

[0340] The server optimizes the system based on the analysis results of the emotion engine. Based on the emotional state, it makes configuration changes to make the user's work environment more comfortable.

[0341] Step 7:

[0342] The terminal receives warning alerts from the server. If an error occurs or a high probability of error is detected, the relevant administrator or user is immediately notified.

[0343] Step 8:

[0344] The server updates the machine learning model using the execution results and feedback data. Sentiment data is also incorporated into the feedback to improve the model's accuracy and efficiency.

[0345] (Example 2)

[0346] Next, we will describe Example 2. 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".

[0347] The present invention aims to provide a method for detecting unexpected system failures in advance and effectively addressing them in a robotic process automation (RPA) system. Furthermore, it addresses the challenge of improving the user experience by providing an optimized operating environment that takes into account the user's emotional state.

[0348] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0349] In this invention, the server includes means for collecting operational data, means for analyzing the operational data to identify abnormal patterns, means for predicting the probability of a problem occurring based on the abnormal patterns, and means for analyzing emotional states to adjust the operating environment. This enables the system to prevent problems while simultaneously providing a comfortable operating environment for the user.

[0350] "Operational data" refers to all information about operations and activities generated during the execution of a system.

[0351] An "abnormal pattern" refers to an event in a system that exhibits characteristic behavior, such as actions or error messages, that deviate from normal operation.

[0352] "Probability of problem occurrence" refers to a numerical evaluation of the likelihood of problems or errors occurring in a system.

[0353] "Configuration" refers to the setting, placement, or resource allocation of a system or service.

[0354] "Feedback information" refers to evaluations and re-entry information based on results and data obtained during system operation.

[0355] An "analytical model" refers to a mathematical or algorithmic framework or method for detecting, predicting, and solving problems based on collected data.

[0356] "Emotional state" refers to the state that represents the user's psychological response and emotions.

[0357] "Operating environment" refers to the interface and settings provided when a user interacts with the system.

[0358] This invention is implemented as an automated system for highly monitoring and controlling robotic process automation (RPA) systems. The system aims to detect system anomalies through the collection and analysis of operational data, and further optimize the operating environment by utilizing the user's emotional state.

[0359] The server first collects operational data from the RPA system in real time. This data collection is performed using standard data collection software, and the data is stored in a database. The stored data includes operation logs, error information, and user operation history.

[0360] Next, the server uses machine learning algorithms to analyze the collected operational data and identify abnormal patterns. This analysis applies anomaly detection algorithms and natural language processing techniques, and calculates the probability of a problem occurring based on what it has learned from past data.

[0361] Based on the predicted probability of problems occurring, the server automatically adjusts the system configuration. Specifically, the server changes resource allocation and prioritizes processes to prevent problems from occurring.

[0362] Furthermore, the server uses an emotion analysis engine to analyze the user's emotional state. This analysis measures user dissatisfaction and stress, and improves the user experience by making changes to the operating environment.

[0363] When an error occurs, the device receives a warning and immediately notifies the administrator or responsible person. This enables a quick response.

[0364] The server uses feedback information to self-learn and sequentially updates its analysis model. This continuously improves the system's accuracy and efficiency.

[0365] As a concrete example, suppose a user experiences system delays during work in a company's RPA system. When the user's negative reaction is analyzed by an emotion analysis engine, the server adjusts resource allocation and takes immediate action to improve the user experience.

[0366] As an example of a prompt to be input into the generating AI model, you can use the format: "List the system errors that are expected in the next task and suggest solutions, including sentiment responses, for each error."

[0367] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0368] Step 1:

[0369] The server collects operational data from the RPA system in real time. Inputs include various log data (operation logs, error information, user operation history). Specifically, log collection software is used to organize the data and store it in a database. This process allows for a detailed record of what operations and events occurred.

[0370] Step 2:

[0371] The server feeds the collected operational data into the analysis module. The input is the log data collected in step 1. Using machine learning algorithms, the data is analyzed to identify anomalous patterns. Anomaly detection and clustering techniques are applied to extract patterns that deviate from normal operation. The output of this analysis lists anomalous patterns and potential problem areas.

[0372] Step 3:

[0373] The server operates a prediction module based on the analysis results to calculate the probability of a problem occurring. The anomaly patterns identified in step 2 are used as input. This module utilizes a statistical model to predict the probability of a problem occurring. The output of this process is the probability value of the error occurring.

[0374] Step 4:

[0375] The server automatically adjusts the system configuration based on the predicted probability of the problem occurring. The input is the probability of the problem occurring, obtained in step 3. This adjustment involves changing resource allocation and process priorities to take specific actions to prevent the problem from occurring. The output is the improved system configuration.

[0376] Step 5:

[0377] The server analyzes the user's emotional state using an emotion analysis engine. User input data (comments and feedback) is used as input. Natural language processing is used to identify emotions and analyze the user's psychological state. As output, optimization suggestions for the operating environment are made, leading to an improvement in the user experience.

[0378] Step 6:

[0379] The terminal receives a warning when an error occurs and notifies the administrator. The input for this step is the error message generated by the system. The terminal displays a visual alert and immediately notifies relevant parties via email or phone call notification. The output is the state in which the error notification was sent.

[0380] Step 7:

[0381] The server collects feedback information after the system goes live and updates the analysis model. The feedback data is used as input, and self-learning is performed based on it. The machine learning algorithm improves the model, and an analysis model with improved accuracy and effectiveness of the system is output.

[0382] (Application Example 2)

[0383] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0384] Many current automation systems focus on predicting and preventing errors, but they are not adequately equipped to optimize work instructions based on the emotional state of workers. As a result, this leads to increased worker stress and decreased overall work efficiency and satisfaction. Therefore, flexible system settings that take workers' emotional states into account are necessary.

[0385] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0386] In this invention, the server includes means for collecting log data, means for analyzing the log data to identify error patterns, and means for recognizing and analyzing the emotional state of the worker. This makes it possible to optimize work instructions according to the emotional state of the worker.

[0387] "Log data" refers to data that records information about the operation of a system and is used to monitor the normal operation of the system and the occurrence of errors.

[0388] An "error pattern" is a pattern that describes the characteristics of errors that occur during system operation, and is a collection of errors that share common characteristics identified from past data.

[0389] "Error probability" is a numerical representation of the likelihood of a system making an error, and it is predicted through analysis based on past error data.

[0390] "Automatic system setting adjustment" is an operation that automatically changes system settings to optimize system operation and performance based on the predicted probability of errors occurring.

[0391] "Feedback data" refers to information including performance data obtained during system operation, as well as user feedback and evaluations, and is used to improve system performance.

[0392] "Self-learning" is the process by which a system uses machine learning algorithms to improve its own analytical model and increase its accuracy.

[0393] "Worker's emotional state" refers to the mental and emotional conditions and reactions exhibited by those engaged in work, and is a factor that influences work efficiency and satisfaction.

[0394] An "analytical model" is a computational model designed to make predictions and classifications based on data, and it serves as a foundation for understanding and judging the operation of a system.

[0395] In the system implementing this invention, a server is central to the operation and functions in the following configuration. First, the server collects log data generated from each process within the system in real time. The log data contains information about the progress of the work and the occurrence of errors. Based on this data, the server uses an analysis module to identify error patterns and predicts the probability of error occurrence using a machine learning model (for example, a model using TensorFlow).

[0396] The server further collects the worker's emotional state via devices such as smart glasses using an emotion analysis module, and analyzes the emotional data. This analysis is performed using natural language processing technology (e.g., Google Cloud Natural Language API). The results of the emotion analysis are reflected in the automatic adjustment of system settings, providing work instructions that are appropriate for the worker.

[0397] If an error occurs, the terminal receives an alert, enabling a quick response. Furthermore, the server has a self-learning function, improving accuracy by updating the analysis model based on feedback data. This could potentially utilize edge AI processors (e.g., NVIDIA Jetson).

[0398] A concrete example is a virtual assistant in a logistics center. By using this system, workers can receive appropriate work instructions in real time, even when they are feeling stressed, which ultimately improves work efficiency. An example of a prompt sentence to be input to the generative AI model used in this case would be: "Explain how smart glasses used in a logistics center can analyze employees' emotions in real time and improve work efficiency."

[0399] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0400] Step 1:

[0401] The server collects log data generated from each process within the logistics center in real time. It uses log data acquired from each work station and sensor as input. This data is stored in a database and processed into a format usable for subsequent analysis. The output is statistical data accumulated in a management database.

[0402] Step 2:

[0403] The server uses the collected log data to identify error patterns in its analysis module. The stored log data is passed to the analysis module as input. During this process, machine learning techniques are used to scan the log data and identify sections that match past error patterns. A list of error patterns is generated as output.

[0404] Step 3:

[0405] The server predicts the probability of an error occurring based on identified error patterns. The input is a list of error patterns. The prediction module applies machine learning algorithms and uses natural language processing techniques to analyze the incoming error message data. The output is a predicted value for the probability of an error occurring.

[0406] Step 4:

[0407] The server automatically adjusts system settings based on the generated error probability. It uses predicted values ​​as input to optimize each system parameter. This adjustment reduces the risk of errors. The updated system settings are output.

[0408] Step 5:

[0409] The server notifies the terminal of an error when it occurs. The input consists of the error message and alarm information. Based on this, it generates a notification message and outputs an alert to the display device on the terminal.

[0410] Step 6:

[0411] The server uses feedback data to self-learn and update its analysis model. It applies feedback data and the current model as input. Machine learning algorithms are used to refine the model and improve its accuracy. The output is an improved analysis model.

[0412] Step 7:

[0413] The server analyzes the worker's emotional state data acquired from smart glasses. It uses emotional data from the smart glasses' camera and microphone as input. Natural language processing is used to analyze the emotions, and data representing the emotional state is generated as output.

[0414] Step 8:

[0415] The server optimizes work instructions based on the results of an emotional analysis of the worker. It uses emotional state data and information about the current work environment as input. It generates instructions to reduce worker stress and outputs them to the appropriate device.

[0416] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0417] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0418] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0422] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0423] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0424] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0425] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0426] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0427] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0428] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0429] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0430] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0431] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0432] This invention is implemented as a system that uses AI to automatically monitor and control an RPA system. This system is constructed as software that includes multiple modules executed by a server.

[0433] First, the server collects operation logs of the RPA system in real time. The collected log data is stored in a database on the server and used for later analysis.

[0434] The collected log data is processed by the server's analysis module. This analysis module combines machine learning and natural language processing techniques to identify error messages and anomalous patterns within the logs. The server analyzes these patterns to identify error patterns. The results of the analysis are used to predict the likelihood of future errors.

[0435] The prediction module calculates the probability of an error occurring based on past analysis results and real-time log data. Based on this prediction, the server automatically selects how to adjust the system settings. This helps the RPA system avoid expected errors.

[0436] Furthermore, if an error occurs, the server will immediately issue a warning alert. This alert will be sent to terminals and user devices, prompting administrators to take prompt action.

[0437] Furthermore, the server acquires feedback data and uses it to perform self-learning. This learning process improves accuracy over time by continuously updating the analysis model. In this way, the system always maintains an up-to-date state, enabling more accurate and efficient control.

[0438] As a concrete example, suppose a company is using RPA to automate routine data processing tasks. This company's servers constantly monitor the log data generated daily, and if they detect any signs of errors in the database connection, they proactively change the connection method or take preventative measures to increase the necessary resources. This ensures that the company's data processing operations continue uninterrupted, leading to increased productivity.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] The server collects log data from the RPA system in real time. This includes retrieving log information using an API. The collected logs are temporarily stored in storage for later analysis.

[0442] Step 2:

[0443] The server sends the collected log data to an analysis module. The analysis module uses natural language processing technology to extract keywords from error messages and machine learning algorithms to identify anomalous patterns.

[0444] Step 3:

[0445] The server predicts the probability of an error occurring based on the analysis results. The prediction module uses a statistical model to calculate the probability that a specific error will occur within a specified time.

[0446] Step 4:

[0447] The server automatically adjusts system settings based on the predicted likelihood of errors occurring. This includes changing process priorities and optimizing resource allocation.

[0448] Step 5:

[0449] The terminal receives warning alerts from the server. When an error occurs or the probability of an error increases, a notification is immediately sent to the relevant parties.

[0450] Step 6:

[0451] The server receives the execution results as feedback data and starts a self-learning process. In this process, the analysis model is updated, improving the accuracy of future predictions.

[0452] (Example 1)

[0453] Next, we will describe Example 1. 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."

[0454] Conventional systems suffer from a lack of real-time detection and prediction of abnormal behavior and errors, resulting in reduced system reliability and efficiency. Furthermore, they lack adequate warnings and automatic adjustments to system settings when errors occur, making rapid and appropriate responses difficult. Additionally, existing analysis methods suffer from insufficient self-learning of analysis algorithms through feedback, making long-term accuracy improvement challenging.

[0455] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0456] In this invention, the server includes means for collecting data signals, means for analyzing the data signals to identify abnormal patterns, means for predicting the probability of failure based on the abnormal patterns, means for automatically adjusting protocol settings, means for sending warnings when a failure occurs, and means for self-learning using evaluation data to update the analysis algorithm. As a result, the system can rapidly detect and predict anomalies, and its reliability and efficiency are further improved through appropriate responses and automatic adjustments. In addition, the accuracy of the analysis model can be improved through self-learning.

[0457] A "data signal" is a flow of electrical or electronic information that indicates the operating status or events of a system.

[0458] An "abnormal pattern" is a collection of phenomena that deviate from normal operation and exhibit reproducible behavior or states.

[0459] "Failure probability" is a statistically significant value indicating the likelihood that a system will enter an abnormal state within a specific period of time.

[0460] "Protocol configuration" refers to the arrangement of a set of procedures and rules concerning communication and operation within a system.

[0461] A "warning" is a notification method that informs users and administrators of abnormalities or conditions requiring attention within a system.

[0462] "Evaluation data" refers to information generated for comparison and measurement based on the system's operating results and feedback.

[0463] "Self-learning" is the process by which a system independently improves its data analysis algorithms based on its experience.

[0464] An "analysis algorithm" is a set of calculation procedures or formulas used in a system to detect patterns in data and interpret the results.

[0465] In this invention, a server centrally manages and controls the entire system. The server first uses sensors and log collection software to collect data signals in real time. This utilizes encryption technologies such as SSL / TLS to ensure efficient data communication. The collected data signals are stored in a database on the server. At this stage, the database software functions, for example, as an SQL-based database management system.

[0466] Next, the server utilizes machine learning and natural language processing technologies in its analysis module. Specifically, it analyzes data using Python's TensorFlow library and NLTK, among others, to identify anomalous patterns. Because the machine learning model is pre-trained, it is possible to extract data features with high accuracy. Once anomalous patterns are identified, the server calculates the probability of failure based on this. Statistical methods such as the ARIMA model are introduced for time series data analysis.

[0467] The server automatically adjusts protocol settings based on the obtained failure probability. This dynamic adjustment is performed by changing the system configuration via a REST API. Furthermore, if an error occurs, the server immediately issues a warning and notifies terminals and user devices. This is achieved by using SMTP for email sending and utilizing a push notification service to enable rapid warnings to users.

[0468] Furthermore, the server aggregates evaluation data and evolves the analysis algorithm through a self-learning process. This aims to improve the model's accuracy over the long term. For data analysis, Jupyter Notebook is used to evaluate the model's performance and incorporate feedback data.

[0469] As a concrete example, consider a case where a company manages data processing using a system. The server monitors log data and detects early signs of abnormal database connections. By changing the protocol settings at that time, it is possible to prevent interruptions to data processing operations. An example of a prompt message based on this invention would be, "Please tell me specific examples of error messages that frequently occur in RPA systems and how to deal with them."

[0470] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0471] Step 1:

[0472] The server collects data signals in real time through sensors and log collection software. The input is the operation logs of the RPA system, which become the data signals. Specifically, the log data is securely transferred to the server using SSL / TLS encryption. The output is the securely stored log data.

[0473] Step 2:

[0474] The server stores the collected log data in a database. The input for this step is the log data collected in step 1. Database software, such as an SQL-based system, is used to structure the data and format it for fast searching. The output is the formatted database entry.

[0475] Step 3:

[0476] The server analyzes data using machine learning techniques. The input is stored log data. The analysis module uses Python's TensorFlow library and NLTK to identify anomalous patterns and error messages. The output is the identified anomalous patterns. Specifically, it automatically runs a model based on the identified features.

[0477] Step 4:

[0478] The server calculates the probability of failure based on the analysis results. The anomaly pattern, which is the output of Step 3, becomes the input. The ARIMA model is used for time series data analysis and probability calculations. Specifically, it generates and records predicted values. The output is the calculated probability of failure.

[0479] Step 5:

[0480] The server dynamically adjusts the protocol settings based on the calculated failure probability. The input for this step is the failure probability. The system configuration is modified via a REST API, allowing for flexible configuration updates. The output is the updated protocol configuration.

[0481] Step 6:

[0482] The server sends a warning to the user's terminal or device if a malfunction is detected. The input is the result of the anomaly detection. Alerts are quickly sent via SMTP email notifications or push notification services. The output is the sent warning message.

[0483] Step 7:

[0484] The server collects evaluation data during operation and updates its analysis algorithm through self-learning. Input includes user feedback data. Specifically, it uses Jupyter Notebook for analysis and makes improvements based on the feedback. The output is the updated analysis algorithm.

[0485] (Application Example 1)

[0486] Next, we will explain Application Example 1. In the following explanation, 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."

[0487] In modern manufacturing environments, the stable operation of robotic process automation (RPA) systems is crucial. However, detecting system anomalies and responding to error messages still largely rely on manual processes, making efficient monitoring difficult. Furthermore, when an anomaly occurs, immediate action is required to minimize its impact. To address this, a means of understanding the situation in real time and providing workers with visual information is necessary.

[0488] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0489] In this invention, the server includes means for collecting log data, means for analyzing the log data to identify error patterns, means for predicting the probability of error occurrence based on the error patterns, means for automatically adjusting system settings, means for notifying warnings when errors occur, means for self-learning using feedback data to update the analysis model, and a display device that visually displays the analysis results and assists in monitoring the operation. This makes it possible to quickly and efficiently detect abnormalities in the RPA system within the factory and provide information to workers in real time.

[0490] "Means for collecting log data" refers to a function that records and saves all actions, error messages, and other information that occur within the system in real time.

[0491] "Methods for identifying error patterns" refer to algorithms that analyze collected log data and identify signs of specific errors or abnormal patterns based on past data.

[0492] "Methods for predicting the probability of error occurrence" refer to technologies that calculate the probability of future errors occurring based on identified error patterns, thereby assisting in the stable operation of the system.

[0493] "Means for automatically adjusting system settings" refers to a function that changes system settings in advance according to the predicted probability of error occurrence, in order to avoid errors or mitigate their impact.

[0494] "Means of notifying warnings when errors occur" refers to an alert function that enables a quick response by immediately notifying relevant parties of detected errors.

[0495] "A means of updating the analysis model through self-learning using feedback data" refers to a process of continuously improving the model and enhancing the system's performance in order to improve the accuracy of the analysis by utilizing past data.

[0496] A "display device that visually displays analysis results and supports monitoring of operation" is a device that provides workers with visually analyzed information, enabling them to easily understand the system status and take necessary actions.

[0497] In this invention, a server-centered system plays a major role. The server first collects various log data in real time and stores it in a database. This log data includes the system's operating status and error messages, which are used for later analysis.

[0498] The server processes the collected log data using an analysis module. This analysis combines machine learning and natural language processing techniques, making it possible to detect specific error patterns. The results of the analysis are used to predict future error occurrences, and the server automatically adjusts system settings based on these predictions.

[0499] Furthermore, the analysis results are visually displayed on a display device. This display device is a terminal such as a smart device, and it notifies the user of the system status and warnings in real time. For example, a worker using smart glasses can check the error predictions and warnings displayed on the device and take appropriate action immediately.

[0500] For self-learning purposes, the server acquires feedback data and continuously updates its analysis model using that data. This allows the system to perform more precise and efficient control.

[0501] As a concrete example, if implemented in a factory, workers wearing smart glasses would visually monitor production line operation information, and if an anomaly is predicted, a warning would be displayed on the glasses. This would enable stable operation of the production line and rapid problem resolution. An example of input to the generated AI model could be a prompt message such as, "Create a step-by-step guide for developing a smart glasses application that analyzes log data from an RPA system, identifies error patterns, and issues warnings to factory workers."

[0502] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0503] Step 1:

[0504] The server collects log data from the RPA system in real time. This input data includes operation logs and error messages. The collected data is stored in a database and used as the basis for analysis.

[0505] Step 2:

[0506] The server sends log data stored in the database to the analysis module. The analysis module applies machine learning models and natural language processing techniques to this input data to identify error patterns. Specifically, it performs data calculations aimed at identifying specific abnormal patterns by analyzing the content and frequency of error messages. A list of error patterns is generated as output.

[0507] Step 3:

[0508] The server uses a prediction module to calculate the probability of an error occurring based on the error patterns identified by the analysis module. Past error pattern data and current log data are used as input. The prediction algorithm processes this data and performs calculations based on system error messages and operational characteristics. As a result, the probability of an error occurring is output.

[0509] Step 4:

[0510] The server automatically adjusts the system settings based on the predicted error probability. This input includes probability information calculated by the prediction module. The server makes appropriate configuration changes and performs processes to ensure system stability. As a result, a system environment with fewer errors is output.

[0511] Step 5:

[0512] The server issues a warning to the terminal and notifies the user if an error occurs or is highly likely to occur. Inputs for this warning include the probability of the error occurring and a specific error pattern. The application on the terminal receives this notification in real time and displays a visual warning message to the user.

[0513] Step 6:

[0514] The user reviews the warning message displayed on the terminal and considers appropriate action. The specific input is the warning message from the system. Based on this information, the user decides on a course of action, supporting the efficient operation of the production line.

[0515] Step 7:

[0516] The server collects feedback data and initiates a self-learning process. This input includes user responses and feedback data on system operation. The server uses this data to update its machine learning algorithms and perform data calculations to build a more precise analytical model. The output of this process is the updated analytical model.

[0517] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0518] This invention is implemented as a system that uses AI to automatically monitor and control an RPA system, and further combines it with an emotion engine that recognizes user emotions. In this system, a server is central, and processing is carried out through multiple modules.

[0519] First, the server collects log data related to the operation of the RPA system in real time. The collected data is stored in a database and used for analysis later.

[0520] Next, the server uses an analysis module to identify error patterns from the collected log data. This process employs machine learning and natural language processing techniques to analyze error messages and pinpoint the root cause of the problem. The results of the analysis are then used to predict future error occurrences.

[0521] Subsequently, the server uses a prediction module to calculate the probability of an error occurring. Based on the prediction results, the server automatically adjusts the system settings to prevent errors from occurring.

[0522] The server analyzes the user's emotional state using an emotion engine. This analysis can then be used to adjust system settings and processes, thereby providing a user-optimized operating environment.

[0523] Furthermore, if an error occurs, the device will receive a warning alert and immediately notify the administrator or responsible person.

[0524] The server uses feedback data to self-learn and sequentially updates its analysis model. The emotion engine also incorporates user emotion data as feedback, integrating it into the analysis model to improve the system's accuracy and efficiency.

[0525] As a concrete example, let's consider a company that uses RPA. This company's servers analyze log data obtained from daily operations and constantly monitor the system's operating status. One day, a user experiences system lag and expresses negative emotions. This emotion data is analyzed by an emotion engine, and the server dynamically adjusts resource allocation and takes immediate action to improve the user experience. As a result, business disruption can be minimized.

[0526] The following describes the processing flow.

[0527] Step 1:

[0528] The server collects log data from the RPA system in real time. The logs stored in the database include process start times, end times, error messages, and more.

[0529] Step 2:

[0530] The server sends the collected log data to an analysis module. Here, error messages are analyzed using natural language processing, and error patterns are identified using machine learning models.

[0531] Step 3:

[0532] The server predicts the probability of errors occurring based on the analysis results. The prediction module calculates the likelihood of each error recurring, and uses this information to assess system risk.

[0533] Step 4:

[0534] The server automatically adjusts system settings based on predictions. These adjustments include schedule changes and resource allocation for load balancing.

[0535] Step 5:

[0536] The server uses an emotion engine to analyze the user's emotional state. It extracts emotional patterns from user input and feedback data and evaluates the user's current emotions.

[0537] Step 6:

[0538] The server optimizes the system based on the analysis results of the emotion engine. Based on the emotional state, it makes configuration changes to make the user's work environment more comfortable.

[0539] Step 7:

[0540] The terminal receives warning alerts from the server. If an error occurs or a high probability of error is detected, the relevant administrator or user is immediately notified.

[0541] Step 8:

[0542] The server updates the machine learning model using the execution results and feedback data. Sentiment data is also incorporated into the feedback to improve the model's accuracy and efficiency.

[0543] (Example 2)

[0544] Next, we will describe Example 2. 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."

[0545] The present invention aims to provide a method for detecting unexpected system failures in advance and effectively addressing them in a robotic process automation (RPA) system. Furthermore, it addresses the challenge of improving the user experience by providing an optimized operating environment that takes into account the user's emotional state.

[0546] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0547] In this invention, the server includes means for collecting operational data, means for analyzing the operational data to identify abnormal patterns, means for predicting the probability of a problem occurring based on the abnormal patterns, and means for analyzing emotional states to adjust the operating environment. This enables the system to prevent problems while simultaneously providing a comfortable operating environment for the user.

[0548] "Operational data" refers to all information about operations and activities generated during the execution of a system.

[0549] An "abnormal pattern" refers to an event in a system that exhibits characteristic behavior, such as actions or error messages, that deviate from normal operation.

[0550] "Probability of problem occurrence" refers to a numerical evaluation of the likelihood of problems or errors occurring in a system.

[0551] "Configuration" refers to the setting, placement, or resource allocation of a system or service.

[0552] "Feedback information" refers to evaluations and re-entry information based on results and data obtained during system operation.

[0553] An "analytical model" refers to a mathematical or algorithmic framework or method for detecting, predicting, and solving problems based on collected data.

[0554] "Emotional state" refers to the state that represents the user's psychological response and emotions.

[0555] "Operating environment" refers to the interface and settings provided when a user interacts with the system.

[0556] This invention is implemented as an automated system for highly monitoring and controlling robotic process automation (RPA) systems. The system aims to detect system anomalies through the collection and analysis of operational data, and further optimize the operating environment by utilizing the user's emotional state.

[0557] The server first collects operational data from the RPA system in real time. This data collection is performed using standard data collection software, and the data is stored in a database. The stored data includes operation logs, error information, and user operation history.

[0558] Next, the server uses machine learning algorithms to analyze the collected operational data and identify abnormal patterns. This analysis applies anomaly detection algorithms and natural language processing techniques, and calculates the probability of a problem occurring based on what it has learned from past data.

[0559] Based on the predicted probability of problems occurring, the server automatically adjusts the system configuration. Specifically, the server changes resource allocation and prioritizes processes to prevent problems from occurring.

[0560] Furthermore, the server uses an emotion analysis engine to analyze the user's emotional state. This analysis measures user dissatisfaction and stress, and improves the user experience by making changes to the operating environment.

[0561] When an error occurs, the device receives a warning and immediately notifies the administrator or responsible person. This enables a quick response.

[0562] The server uses feedback information to self-learn and sequentially updates its analysis model. This continuously improves the system's accuracy and efficiency.

[0563] As a concrete example, suppose a user experiences system delays during work in a company's RPA system. When the user's negative reaction is analyzed by an emotion analysis engine, the server adjusts resource allocation and takes immediate action to improve the user experience.

[0564] As an example of a prompt to be input into the generating AI model, you can use the format: "List the system errors that are expected in the next task and suggest solutions, including sentiment responses, for each error."

[0565] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0566] Step 1:

[0567] The server collects operational data from the RPA system in real time. Inputs include various log data (operation logs, error information, user operation history). Specifically, log collection software is used to organize the data and store it in a database. This process allows for a detailed record of what operations and events occurred.

[0568] Step 2:

[0569] The server feeds the collected operational data into the analysis module. The input is the log data collected in step 1. Using machine learning algorithms, the data is analyzed to identify anomalous patterns. Anomaly detection and clustering techniques are applied to extract patterns that deviate from normal operation. The output of this analysis lists anomalous patterns and potential problem areas.

[0570] Step 3:

[0571] The server operates a prediction module based on the analysis results to calculate the probability of a problem occurring. The anomaly patterns identified in step 2 are used as input. This module utilizes a statistical model to predict the probability of a problem occurring. The output of this process is the probability value of the error occurring.

[0572] Step 4:

[0573] The server automatically adjusts the system configuration based on the predicted probability of the problem occurring. The input is the probability of the problem occurring, obtained in step 3. This adjustment involves changing resource allocation and process priorities to take specific actions to prevent the problem from occurring. The output is the improved system configuration.

[0574] Step 5:

[0575] The server analyzes the user's emotional state using an emotion analysis engine. User input data (comments and feedback) is used as input. Natural language processing is used to identify emotions and analyze the user's psychological state. As output, optimization suggestions for the operating environment are made, leading to an improvement in the user experience.

[0576] Step 6:

[0577] The terminal receives a warning when an error occurs and notifies the administrator. The input for this step is the error message generated by the system. The terminal displays a visual alert and immediately notifies relevant parties via email or phone call notification. The output is the state in which the error notification was sent.

[0578] Step 7:

[0579] The server collects feedback information after the system goes live and updates the analysis model. The feedback data is used as input, and self-learning is performed based on it. The machine learning algorithm improves the model, and an analysis model with improved accuracy and effectiveness of the system is output.

[0580] (Application Example 2)

[0581] Next, we will explain application example 2. In the following explanation, 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."

[0582] Many current automation systems focus on predicting and preventing errors, but they are not adequately equipped to optimize work instructions based on the emotional state of workers. As a result, this leads to increased worker stress and decreased overall work efficiency and satisfaction. Therefore, flexible system settings that take workers' emotional states into account are necessary.

[0583] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0584] In this invention, the server includes means for collecting log data, means for analyzing the log data to identify error patterns, and means for recognizing and analyzing the emotional state of the worker. This makes it possible to optimize work instructions according to the emotional state of the worker.

[0585] "Log data" refers to data that records information about the operation of a system and is used to monitor the normal operation of the system and the occurrence of errors.

[0586] An "error pattern" is a pattern that describes the characteristics of errors that occur during system operation, and is a collection of errors that share common characteristics identified from past data.

[0587] "Error probability" is a numerical representation of the likelihood of a system making an error, and it is predicted through analysis based on past error data.

[0588] "Automatic system setting adjustment" is an operation that automatically changes system settings to optimize system operation and performance based on the predicted probability of errors occurring.

[0589] "Feedback data" refers to information including performance data obtained during system operation, as well as user feedback and evaluations, and is used to improve system performance.

[0590] "Self-learning" is the process by which a system uses machine learning algorithms to improve its own analytical model and increase its accuracy.

[0591] "Worker's emotional state" refers to the mental and emotional conditions and reactions exhibited by those engaged in work, and is a factor that influences work efficiency and satisfaction.

[0592] An "analytical model" is a computational model designed to make predictions and classifications based on data, and it serves as a foundation for understanding and judging the operation of a system.

[0593] In the system implementing this invention, a server is central to the operation and functions in the following configuration. First, the server collects log data generated from each process within the system in real time. The log data contains information about the progress of the work and the occurrence of errors. Based on this data, the server uses an analysis module to identify error patterns and predicts the probability of error occurrence using a machine learning model (for example, a model using TensorFlow).

[0594] The server further collects the worker's emotional state via devices such as smart glasses using an emotion analysis module, and analyzes the emotional data. This analysis is performed using natural language processing technology (e.g., Google Cloud Natural Language API). The results of the emotion analysis are reflected in the automatic adjustment of system settings, providing work instructions that are appropriate for the worker.

[0595] If an error occurs, the terminal receives an alert, enabling a quick response. Furthermore, the server has a self-learning function, improving accuracy by updating the analysis model based on feedback data. This could potentially utilize edge AI processors (e.g., NVIDIA Jetson).

[0596] A concrete example is a virtual assistant in a logistics center. By using this system, workers can receive appropriate work instructions in real time, even when they are feeling stressed, which ultimately improves work efficiency. An example of a prompt sentence to be input to the generative AI model used in this case would be: "Explain how smart glasses used in a logistics center can analyze employees' emotions in real time and improve work efficiency."

[0597] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0598] Step 1:

[0599] The server collects log data generated from each process within the logistics center in real time. It uses log data acquired from each work station and sensor as input. This data is stored in a database and processed into a format usable for subsequent analysis. The output is statistical data accumulated in a management database.

[0600] Step 2:

[0601] The server uses the collected log data to identify error patterns in its analysis module. The stored log data is passed to the analysis module as input. During this process, machine learning techniques are used to scan the log data and identify sections that match past error patterns. A list of error patterns is generated as output.

[0602] Step 3:

[0603] The server predicts the probability of an error occurring based on identified error patterns. The input is a list of error patterns. The prediction module applies machine learning algorithms and uses natural language processing techniques to analyze the incoming error message data. The output is a predicted value for the probability of an error occurring.

[0604] Step 4:

[0605] The server automatically adjusts system settings based on the generated error probability. It uses predicted values ​​as input to optimize each system parameter. This adjustment reduces the risk of errors. The updated system settings are output.

[0606] Step 5:

[0607] The server notifies the terminal of an error when it occurs. The input consists of the error message and alarm information. Based on this, it generates a notification message and outputs an alert to the display device on the terminal.

[0608] Step 6:

[0609] The server uses feedback data to self-learn and update its analysis model. It applies feedback data and the current model as input. Machine learning algorithms are used to refine the model and improve its accuracy. The output is an improved analysis model.

[0610] Step 7:

[0611] The server analyzes the worker's emotional state data acquired from smart glasses. It uses emotional data from the smart glasses' camera and microphone as input. Natural language processing is used to analyze the emotions, and data representing the emotional state is generated as output.

[0612] Step 8:

[0613] The server optimizes work instructions based on the results of an emotional analysis of the worker. It uses emotional state data and information about the current work environment as input. It generates instructions to reduce worker stress and outputs them to the appropriate device.

[0614] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0615] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0616] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0617] [Fourth Embodiment]

[0618] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0619] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0620] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0621] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0622] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0623] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0624] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0625] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0626] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0627] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0628] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0629] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0630] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0631] This invention is implemented as a system that uses AI to automatically monitor and control an RPA system. This system is constructed as software that includes multiple modules executed by a server.

[0632] First, the server collects operation logs of the RPA system in real time. The collected log data is stored in a database on the server and used for later analysis.

[0633] The collected log data is processed by the server's analysis module. This analysis module combines machine learning and natural language processing techniques to identify error messages and anomalous patterns within the logs. The server analyzes these patterns to identify error patterns. The results of the analysis are used to predict the likelihood of future errors.

[0634] The prediction module calculates the probability of an error occurring based on past analysis results and real-time log data. Based on this prediction, the server automatically selects how to adjust the system settings. This helps the RPA system avoid expected errors.

[0635] Furthermore, if an error occurs, the server will immediately issue a warning alert. This alert will be sent to terminals and user devices, prompting administrators to take prompt action.

[0636] Furthermore, the server acquires feedback data and uses it to perform self-learning. This learning process improves accuracy over time by continuously updating the analysis model. In this way, the system always maintains an up-to-date state, enabling more accurate and efficient control.

[0637] As a concrete example, suppose a company is using RPA to automate routine data processing tasks. This company's servers constantly monitor the log data generated daily, and if they detect any signs of errors in the database connection, they proactively change the connection method or take preventative measures to increase the necessary resources. This ensures that the company's data processing operations continue uninterrupted, leading to increased productivity.

[0638] The following describes the processing flow.

[0639] Step 1:

[0640] The server collects log data from the RPA system in real time. This includes retrieving log information using an API. The collected logs are temporarily stored in storage for later analysis.

[0641] Step 2:

[0642] The server sends the collected log data to an analysis module. The analysis module uses natural language processing technology to extract keywords from error messages and machine learning algorithms to identify anomalous patterns.

[0643] Step 3:

[0644] The server predicts the probability of an error occurring based on the analysis results. The prediction module uses a statistical model to calculate the probability that a specific error will occur within a specified time.

[0645] Step 4:

[0646] The server automatically adjusts system settings based on the predicted likelihood of errors occurring. This includes changing process priorities and optimizing resource allocation.

[0647] Step 5:

[0648] The terminal receives warning alerts from the server. When an error occurs or the probability of an error increases, a notification is immediately sent to the relevant parties.

[0649] Step 6:

[0650] The server receives the execution results as feedback data and starts a self-learning process. In this process, the analysis model is updated, improving the accuracy of future predictions.

[0651] (Example 1)

[0652] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0653] Conventional systems suffer from a lack of real-time detection and prediction of abnormal behavior and errors, resulting in reduced system reliability and efficiency. Furthermore, they lack adequate warnings and automatic adjustments to system settings when errors occur, making rapid and appropriate responses difficult. Additionally, existing analysis methods suffer from insufficient self-learning of analysis algorithms through feedback, making long-term accuracy improvement challenging.

[0654] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0655] In this invention, the server includes means for collecting data signals, means for analyzing the data signals to identify abnormal patterns, means for predicting the probability of failure based on the abnormal patterns, means for automatically adjusting protocol settings, means for sending warnings when a failure occurs, and means for self-learning using evaluation data to update the analysis algorithm. As a result, the system can rapidly detect and predict anomalies, and its reliability and efficiency are further improved through appropriate responses and automatic adjustments. In addition, the accuracy of the analysis model can be improved through self-learning.

[0656] A "data signal" is a flow of electrical or electronic information that indicates the operating status or events of a system.

[0657] An "abnormal pattern" is a collection of phenomena that deviate from normal operation and exhibit reproducible behavior or states.

[0658] "Failure probability" is a statistically significant value indicating the likelihood that a system will enter an abnormal state within a specific period of time.

[0659] "Protocol configuration" refers to the arrangement of a set of procedures and rules concerning communication and operation within a system.

[0660] A "warning" is a notification method that informs users and administrators of abnormalities or conditions requiring attention within a system.

[0661] "Evaluation data" refers to information generated for comparison and measurement based on the system's operating results and feedback.

[0662] "Self-learning" is the process by which a system independently improves its data analysis algorithms based on its experience.

[0663] An "analysis algorithm" is a set of calculation procedures or formulas used in a system to detect patterns in data and interpret the results.

[0664] In this invention, a server centrally manages and controls the entire system. The server first uses sensors and log collection software to collect data signals in real time. This utilizes encryption technologies such as SSL / TLS to ensure efficient data communication. The collected data signals are stored in a database on the server. At this stage, the database software functions, for example, as an SQL-based database management system.

[0665] Next, the server utilizes machine learning and natural language processing technologies in its analysis module. Specifically, it analyzes data using Python's TensorFlow library and NLTK, among others, to identify anomalous patterns. Because the machine learning model is pre-trained, it is possible to extract data features with high accuracy. Once anomalous patterns are identified, the server calculates the probability of failure based on this. Statistical methods such as the ARIMA model are introduced for time series data analysis.

[0666] The server automatically adjusts protocol settings based on the obtained failure probability. This dynamic adjustment is performed by changing the system configuration via a REST API. Furthermore, if an error occurs, the server immediately issues a warning and notifies terminals and user devices. This is achieved by using SMTP for email sending and utilizing a push notification service to enable rapid warnings to users.

[0667] Furthermore, the server aggregates evaluation data and evolves the analysis algorithm through a self-learning process. This aims to improve the model's accuracy over the long term. For data analysis, Jupyter Notebook is used to evaluate the model's performance and incorporate feedback data.

[0668] As a concrete example, consider a case where a company manages data processing using a system. The server monitors log data and detects early signs of abnormal database connections. By changing the protocol settings at that time, it is possible to prevent interruptions to data processing operations. An example of a prompt message based on this invention would be, "Please tell me specific examples of error messages that frequently occur in RPA systems and how to deal with them."

[0669] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0670] Step 1:

[0671] The server collects data signals in real time through sensors and log collection software. The input is the operation logs of the RPA system, which become the data signals. Specifically, the log data is securely transferred to the server using SSL / TLS encryption. The output is the securely stored log data.

[0672] Step 2:

[0673] The server stores the collected log data in a database. The input for this step is the log data collected in step 1. Database software, such as an SQL-based system, is used to structure the data and format it for fast searching. The output is the formatted database entry.

[0674] Step 3:

[0675] The server analyzes data using machine learning techniques. The input is stored log data. The analysis module uses Python's TensorFlow library and NLTK to identify anomalous patterns and error messages. The output is the identified anomalous patterns. Specifically, it automatically runs a model based on the identified features.

[0676] Step 4:

[0677] The server calculates the probability of failure based on the analysis results. The anomaly pattern, which is the output of Step 3, becomes the input. The ARIMA model is used for time series data analysis and probability calculations. Specifically, it generates and records predicted values. The output is the calculated probability of failure.

[0678] Step 5:

[0679] The server dynamically adjusts the protocol settings based on the calculated failure probability. The input for this step is the failure probability. The system configuration is modified via a REST API, allowing for flexible configuration updates. The output is the updated protocol configuration.

[0680] Step 6:

[0681] The server sends a warning to the user's terminal or device if a malfunction is detected. The input is the result of the anomaly detection. Alerts are quickly sent via SMTP email notifications or push notification services. The output is the sent warning message.

[0682] Step 7:

[0683] The server collects evaluation data during operation and updates its analysis algorithm through self-learning. Input includes user feedback data. Specifically, it uses Jupyter Notebook for analysis and makes improvements based on the feedback. The output is the updated analysis algorithm.

[0684] (Application Example 1)

[0685] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0686] In modern manufacturing environments, the stable operation of robotic process automation (RPA) systems is crucial. However, detecting system anomalies and responding to error messages still largely rely on manual processes, making efficient monitoring difficult. Furthermore, when an anomaly occurs, immediate action is required to minimize its impact. To address this, a means of understanding the situation in real time and providing workers with visual information is necessary.

[0687] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0688] In this invention, the server includes means for collecting log data, means for analyzing the log data to identify error patterns, means for predicting the probability of error occurrence based on the error patterns, means for automatically adjusting system settings, means for notifying warnings when errors occur, means for self-learning using feedback data to update the analysis model, and a display device that visually displays the analysis results and assists in monitoring the operation. This makes it possible to quickly and efficiently detect abnormalities in the RPA system within the factory and provide information to workers in real time.

[0689] "Means for collecting log data" refers to a function that records and saves all actions, error messages, and other information that occur within the system in real time.

[0690] "Methods for identifying error patterns" refer to algorithms that analyze collected log data and identify signs of specific errors or abnormal patterns based on past data.

[0691] "Methods for predicting the probability of error occurrence" refer to technologies that calculate the probability of future errors occurring based on identified error patterns, thereby assisting in the stable operation of the system.

[0692] "Means for automatically adjusting system settings" refers to a function that changes system settings in advance according to the predicted probability of error occurrence, in order to avoid errors or mitigate their impact.

[0693] "Means of notifying warnings when errors occur" refers to an alert function that enables a quick response by immediately notifying relevant parties of detected errors.

[0694] "A means of updating the analysis model through self-learning using feedback data" refers to a process of continuously improving the model and enhancing the system's performance in order to improve the accuracy of the analysis by utilizing past data.

[0695] A "display device that visually displays analysis results and supports monitoring of operation" is a device that provides workers with visually analyzed information, enabling them to easily understand the system status and take necessary actions.

[0696] In this invention, a server-centered system plays a major role. The server first collects various log data in real time and stores it in a database. This log data includes the system's operating status and error messages, which are used for later analysis.

[0697] The server processes the collected log data using an analysis module. This analysis combines machine learning and natural language processing techniques, making it possible to detect specific error patterns. The results of the analysis are used to predict future error occurrences, and the server automatically adjusts system settings based on these predictions.

[0698] Furthermore, the analysis results are visually displayed on a display device. This display device is a terminal such as a smart device, and it notifies the user of the system status and warnings in real time. For example, a worker using smart glasses can check the error predictions and warnings displayed on the device and take appropriate action immediately.

[0699] For self-learning purposes, the server acquires feedback data and continuously updates its analysis model using that data. This allows the system to perform more precise and efficient control.

[0700] As a concrete example, if implemented in a factory, workers wearing smart glasses would visually monitor production line operation information, and if an anomaly is predicted, a warning would be displayed on the glasses. This would enable stable operation of the production line and rapid problem resolution. An example of input to the generated AI model could be a prompt message such as, "Create a step-by-step guide for developing a smart glasses application that analyzes log data from an RPA system, identifies error patterns, and issues warnings to factory workers."

[0701] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0702] Step 1:

[0703] The server collects log data from the RPA system in real time. This input data includes operation logs and error messages. The collected data is stored in a database and used as the basis for analysis.

[0704] Step 2:

[0705] The server sends log data stored in the database to the analysis module. The analysis module applies machine learning models and natural language processing techniques to this input data to identify error patterns. Specifically, it performs data calculations aimed at identifying specific abnormal patterns by analyzing the content and frequency of error messages. A list of error patterns is generated as output.

[0706] Step 3:

[0707] The server uses a prediction module to calculate the probability of an error occurring based on the error patterns identified by the analysis module. Past error pattern data and current log data are used as input. The prediction algorithm processes this data and performs calculations based on system error messages and operational characteristics. As a result, the probability of an error occurring is output.

[0708] Step 4:

[0709] The server automatically adjusts the system settings based on the predicted error probability. This input includes probability information calculated by the prediction module. The server makes appropriate configuration changes and performs processes to ensure system stability. As a result, a system environment with fewer errors is output.

[0710] Step 5:

[0711] The server issues a warning to the terminal and notifies the user if an error occurs or is highly likely to occur. Inputs for this warning include the probability of the error occurring and a specific error pattern. The application on the terminal receives this notification in real time and displays a visual warning message to the user.

[0712] Step 6:

[0713] The user reviews the warning message displayed on the terminal and considers appropriate action. The specific input is the warning message from the system. Based on this information, the user decides on a course of action, supporting the efficient operation of the production line.

[0714] Step 7:

[0715] The server collects feedback data and initiates a self-learning process. This input includes user responses and feedback data on system operation. The server uses this data to update its machine learning algorithms and perform data calculations to build a more precise analytical model. The output of this process is the updated analytical model.

[0716] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0717] This invention is implemented as a system that uses AI to automatically monitor and control an RPA system, and further combines it with an emotion engine that recognizes user emotions. In this system, a server is central, and processing is carried out through multiple modules.

[0718] First, the server collects log data related to the operation of the RPA system in real time. The collected data is stored in a database and used for analysis later.

[0719] Next, the server uses an analysis module to identify error patterns from the collected log data. This process employs machine learning and natural language processing techniques to analyze error messages and pinpoint the root cause of the problem. The results of the analysis are then used to predict future error occurrences.

[0720] Subsequently, the server uses a prediction module to calculate the probability of an error occurring. Based on the prediction results, the server automatically adjusts the system settings to prevent errors from occurring.

[0721] The server analyzes the user's emotional state using an emotion engine. This analysis can then be used to adjust system settings and processes, thereby providing a user-optimized operating environment.

[0722] Furthermore, if an error occurs, the device will receive a warning alert and immediately notify the administrator or responsible person.

[0723] The server uses feedback data to self-learn and sequentially updates its analysis model. The emotion engine also incorporates user emotion data as feedback, integrating it into the analysis model to improve the system's accuracy and efficiency.

[0724] As a concrete example, let's consider a company that uses RPA. This company's servers analyze log data obtained from daily operations and constantly monitor the system's operating status. One day, a user experiences system lag and expresses negative emotions. This emotion data is analyzed by an emotion engine, and the server dynamically adjusts resource allocation and takes immediate action to improve the user experience. As a result, business disruption can be minimized.

[0725] The following describes the processing flow.

[0726] Step 1:

[0727] The server collects log data from the RPA system in real time. The logs stored in the database include process start times, end times, error messages, and more.

[0728] Step 2:

[0729] The server sends the collected log data to an analysis module. Here, error messages are analyzed using natural language processing, and error patterns are identified using machine learning models.

[0730] Step 3:

[0731] The server predicts the probability of errors occurring based on the analysis results. The prediction module calculates the likelihood of each error recurring, and uses this information to assess system risk.

[0732] Step 4:

[0733] The server automatically adjusts system settings based on predictions. These adjustments include schedule changes and resource allocation for load balancing.

[0734] Step 5:

[0735] The server uses an emotion engine to analyze the user's emotional state. It extracts emotional patterns from user input and feedback data and evaluates the user's current emotions.

[0736] Step 6:

[0737] The server optimizes the system based on the analysis results of the emotion engine. Based on the emotional state, it makes configuration changes to make the user's work environment more comfortable.

[0738] Step 7:

[0739] The terminal receives warning alerts from the server. If an error occurs or a high probability of error is detected, the relevant administrator or user is immediately notified.

[0740] Step 8:

[0741] The server updates the machine learning model using the execution results and feedback data. Sentiment data is also incorporated into the feedback to improve the model's accuracy and efficiency.

[0742] (Example 2)

[0743] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0744] The present invention aims to provide a method for detecting unexpected system failures in advance and effectively addressing them in a robotic process automation (RPA) system. Furthermore, it addresses the challenge of improving the user experience by providing an optimized operating environment that takes into account the user's emotional state.

[0745] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0746] In this invention, the server includes means for collecting operational data, means for analyzing the operational data to identify abnormal patterns, means for predicting the probability of a problem occurring based on the abnormal patterns, and means for analyzing emotional states to adjust the operating environment. This enables the system to prevent problems while simultaneously providing a comfortable operating environment for the user.

[0747] "Operational data" refers to all information about operations and activities generated during the execution of a system.

[0748] An "abnormal pattern" refers to an event in a system that exhibits characteristic behavior, such as actions or error messages, that deviate from normal operation.

[0749] "Probability of problem occurrence" refers to a numerical evaluation of the likelihood of problems or errors occurring in a system.

[0750] "Configuration" refers to the setting, placement, or resource allocation of a system or service.

[0751] "Feedback information" refers to evaluations and re-entry information based on results and data obtained during system operation.

[0752] An "analytical model" refers to a mathematical or algorithmic framework or method for detecting, predicting, and solving problems based on collected data.

[0753] "Emotional state" refers to the state that represents the user's psychological response and emotions.

[0754] "Operating environment" refers to the interface and settings provided when a user interacts with the system.

[0755] This invention is implemented as an automated system for highly monitoring and controlling robotic process automation (RPA) systems. The system aims to detect system anomalies through the collection and analysis of operational data, and further optimize the operating environment by utilizing the user's emotional state.

[0756] The server first collects operational data from the RPA system in real time. This data collection is performed using standard data collection software, and the data is stored in a database. The stored data includes operation logs, error information, and user operation history.

[0757] Next, the server uses machine learning algorithms to analyze the collected operational data and identify abnormal patterns. This analysis applies anomaly detection algorithms and natural language processing techniques, and calculates the probability of a problem occurring based on what it has learned from past data.

[0758] Based on the predicted probability of problems occurring, the server automatically adjusts the system configuration. Specifically, the server changes resource allocation and prioritizes processes to prevent problems from occurring.

[0759] Furthermore, the server uses an emotion analysis engine to analyze the user's emotional state. This analysis measures user dissatisfaction and stress, and improves the user experience by making changes to the operating environment.

[0760] When an error occurs, the device receives a warning and immediately notifies the administrator or responsible person. This enables a quick response.

[0761] The server uses feedback information to self-learn and sequentially updates its analysis model. This continuously improves the system's accuracy and efficiency.

[0762] As a concrete example, suppose a user experiences system delays during work in a company's RPA system. When the user's negative reaction is analyzed by an emotion analysis engine, the server adjusts resource allocation and takes immediate action to improve the user experience.

[0763] As an example of a prompt to be input into the generating AI model, you can use the format: "List the system errors that are expected in the next task and suggest solutions, including sentiment responses, for each error."

[0764] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0765] Step 1:

[0766] The server collects operational data from the RPA system in real time. Inputs include various log data (operation logs, error information, user operation history). Specifically, log collection software is used to organize the data and store it in a database. This process allows for a detailed record of what operations and events occurred.

[0767] Step 2:

[0768] The server feeds the collected operational data into the analysis module. The input is the log data collected in step 1. Using machine learning algorithms, the data is analyzed to identify anomalous patterns. Anomaly detection and clustering techniques are applied to extract patterns that deviate from normal operation. The output of this analysis lists anomalous patterns and potential problem areas.

[0769] Step 3:

[0770] The server operates a prediction module based on the analysis results to calculate the probability of a problem occurring. The anomaly patterns identified in step 2 are used as input. This module utilizes a statistical model to predict the probability of a problem occurring. The output of this process is the probability value of the error occurring.

[0771] Step 4:

[0772] The server automatically adjusts the system configuration based on the predicted probability of the problem occurring. The input is the probability of the problem occurring, obtained in step 3. This adjustment involves changing resource allocation and process priorities to take specific actions to prevent the problem from occurring. The output is the improved system configuration.

[0773] Step 5:

[0774] The server analyzes the user's emotional state using an emotion analysis engine. User input data (comments and feedback) is used as input. Natural language processing is used to identify emotions and analyze the user's psychological state. As output, optimization suggestions for the operating environment are made, leading to an improvement in the user experience.

[0775] Step 6:

[0776] The terminal receives a warning when an error occurs and notifies the administrator. The input for this step is the error message generated by the system. The terminal displays a visual alert and immediately notifies relevant parties via email or phone call notification. The output is the state in which the error notification was sent.

[0777] Step 7:

[0778] The server collects feedback information after the system goes live and updates the analysis model. The feedback data is used as input, and self-learning is performed based on it. The machine learning algorithm improves the model, and an analysis model with improved accuracy and effectiveness of the system is output.

[0779] (Application Example 2)

[0780] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0781] Many current automation systems focus on predicting and preventing errors, but they are not adequately equipped to optimize work instructions based on the emotional state of workers. As a result, this leads to increased worker stress and decreased overall work efficiency and satisfaction. Therefore, flexible system settings that take workers' emotional states into account are necessary.

[0782] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0783] In this invention, the server includes means for collecting log data, means for analyzing the log data to identify error patterns, and means for recognizing and analyzing the emotional state of the worker. This makes it possible to optimize work instructions according to the emotional state of the worker.

[0784] "Log data" refers to data that records information about the operation of a system and is used to monitor the normal operation of the system and the occurrence of errors.

[0785] An "error pattern" is a pattern that describes the characteristics of errors that occur during system operation, and is a collection of errors that share common characteristics identified from past data.

[0786] "Error probability" is a numerical representation of the likelihood of a system making an error, and it is predicted through analysis based on past error data.

[0787] "Automatic system setting adjustment" is an operation that automatically changes system settings to optimize system operation and performance based on the predicted probability of errors occurring.

[0788] "Feedback data" refers to information including performance data obtained during system operation, as well as user feedback and evaluations, and is used to improve system performance.

[0789] "Self-learning" is the process by which a system uses machine learning algorithms to improve its own analytical model and increase its accuracy.

[0790] "Worker's emotional state" refers to the mental and emotional conditions and reactions exhibited by those engaged in work, and is a factor that influences work efficiency and satisfaction.

[0791] An "analytical model" is a computational model designed to make predictions and classifications based on data, and it serves as a foundation for understanding and judging the operation of a system.

[0792] In the system implementing this invention, a server is central to the operation and functions in the following configuration. First, the server collects log data generated from each process within the system in real time. The log data contains information about the progress of the work and the occurrence of errors. Based on this data, the server uses an analysis module to identify error patterns and predicts the probability of error occurrence using a machine learning model (for example, a model using TensorFlow).

[0793] The server further collects the worker's emotional state via devices such as smart glasses using an emotion analysis module, and analyzes the emotional data. This analysis is performed using natural language processing technology (e.g., Google Cloud Natural Language API). The results of the emotion analysis are reflected in the automatic adjustment of system settings, providing work instructions that are appropriate for the worker.

[0794] If an error occurs, the terminal receives an alert, enabling a quick response. Furthermore, the server has a self-learning function, improving accuracy by updating the analysis model based on feedback data. This could potentially utilize edge AI processors (e.g., NVIDIA Jetson).

[0795] A concrete example is a virtual assistant in a logistics center. By using this system, workers can receive appropriate work instructions in real time, even when they are feeling stressed, which ultimately improves work efficiency. An example of a prompt sentence to be input to the generative AI model used in this case would be: "Explain how smart glasses used in a logistics center can analyze employees' emotions in real time and improve work efficiency."

[0796] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0797] Step 1:

[0798] The server collects log data generated from each process within the logistics center in real time. It uses log data acquired from each work station and sensor as input. This data is stored in a database and processed into a format usable for subsequent analysis. The output is statistical data accumulated in a management database.

[0799] Step 2:

[0800] The server uses the collected log data to identify error patterns in its analysis module. The stored log data is passed to the analysis module as input. During this process, machine learning techniques are used to scan the log data and identify sections that match past error patterns. A list of error patterns is generated as output.

[0801] Step 3:

[0802] The server predicts the probability of an error occurring based on identified error patterns. The input is a list of error patterns. The prediction module applies machine learning algorithms and uses natural language processing techniques to analyze the incoming error message data. The output is a predicted value for the probability of an error occurring.

[0803] Step 4:

[0804] The server automatically adjusts system settings based on the generated error probability. It uses predicted values ​​as input to optimize each system parameter. This adjustment reduces the risk of errors. The updated system settings are output.

[0805] Step 5:

[0806] The server notifies the terminal of an error when it occurs. The input consists of the error message and alarm information. Based on this, it generates a notification message and outputs an alert to the display device on the terminal.

[0807] Step 6:

[0808] The server uses feedback data to self-learn and update its analysis model. It applies feedback data and the current model as input. Machine learning algorithms are used to refine the model and improve its accuracy. The output is an improved analysis model.

[0809] Step 7:

[0810] The server analyzes the worker's emotional state data acquired from smart glasses. It uses emotional data from the smart glasses' camera and microphone as input. Natural language processing is used to analyze the emotions, and data representing the emotional state is generated as output.

[0811] Step 8:

[0812] The server optimizes work instructions based on the results of an emotional analysis of the worker. It uses emotional state data and information about the current work environment as input. It generates instructions to reduce worker stress and outputs them to the appropriate device.

[0813] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0814] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0815] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0816] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0817] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0818] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0819] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0820] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0821] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0822] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0823] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0824] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0825] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0826] 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.

[0827] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0828] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0829] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0830] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0831] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0832] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0833] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0834] The following is further disclosed regarding the embodiments described above.

[0835] (Claim 1)

[0836] Means of collecting log data,

[0837] A means for analyzing the aforementioned log data to identify error patterns,

[0838] A means for predicting the probability of an error occurring based on the aforementioned error pattern,

[0839] A means for automatically adjusting system settings based on the aforementioned prediction,

[0840] A means of notifying a warning when an error occurs,

[0841] A means of performing self-learning using feedback data and updating the analysis model,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, characterized in that the update of the analysis model based on feedback is performed using a machine learning algorithm.

[0845] (Claim 3)

[0846] The system according to claim 1, characterized in that the prediction of the probability of error occurrence is performed based on error message data analyzed using natural language processing technology.

[0847] "Example 1"

[0848] (Claim 1)

[0849] A means for collecting data signals,

[0850] A means for analyzing the aforementioned data signal to identify an abnormal pattern,

[0851] A means for predicting the probability of failure based on the aforementioned abnormal pattern,

[0852] A means for automatically adjusting protocol settings based on the aforementioned prediction,

[0853] A means of transmitting a warning when a malfunction occurs,

[0854] A means of performing self-learning using evaluation data and updating the analysis algorithm,

[0855] Methods of using encryption technology on log data,

[0856] A means of making predictions based on data analyzed using machine learning techniques,

[0857] A means for dynamically changing the system configuration based on the analysis results,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, characterized in that the analysis algorithm is updated using digital control technology.

[0861] (Claim 3)

[0862] The system according to claim 1, characterized in that the prediction of the failure probability is performed based on error message information analyzed using natural language processing technology.

[0863] "Application Example 1"

[0864] (Claim 1)

[0865] Means of collecting log data,

[0866] A means for analyzing the aforementioned log data to identify error patterns,

[0867] A means for predicting the probability of an error occurring based on the aforementioned error pattern,

[0868] A means for automatically adjusting system settings based on the aforementioned prediction,

[0869] A means of notifying a warning when an error occurs,

[0870] A means of performing self-learning using feedback data and updating the analysis model,

[0871] A display device that visually displays analysis results and assists in monitoring operation,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, characterized in that the update of the analysis model based on feedback is performed using a machine learning algorithm.

[0875] (Claim 3)

[0876] The system according to claim 1, characterized in that the prediction of the probability of error occurrence is performed based on error message data analyzed using natural language processing technology, and the analysis results are displayed visually on the device in real time.

[0877] "Example 2 of combining an emotion engine"

[0878] (Claim 1)

[0879] Means for collecting motion data,

[0880] A means for analyzing the aforementioned operational data to identify abnormal patterns,

[0881] A means for predicting the probability of a problem occurring based on the aforementioned abnormal pattern,

[0882] Means for automatically adjusting the configuration based on the aforementioned prediction,

[0883] A means of notifying a warning when an anomaly occurs,

[0884] A means of self-learning using feedback information and updating the analysis model,

[0885] A means of analyzing emotional states and adjusting the operating environment,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, characterized in that the update of the analysis model through feedback is performed using predictive technology.

[0889] (Claim 3)

[0890] The system according to claim 1, characterized in that the prediction of the probability of the aforementioned problem occurring is performed based on abnormal message information analyzed using a natural language processing method.

[0891] "Application example 2 when combining with an emotional engine"

[0892] (Claim 1)

[0893] Means of collecting log data,

[0894] A means for analyzing the aforementioned log data to identify error patterns,

[0895] A means for predicting the probability of an error occurring based on the aforementioned error pattern,

[0896] A means for automatically adjusting system settings based on the aforementioned prediction,

[0897] A means of notifying a warning when an error occurs,

[0898] A means of performing self-learning using feedback data and updating the analysis model,

[0899] A means of recognizing and analyzing the emotional state of workers,

[0900] A means of optimizing work instructions according to emotional state,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, characterized in that the update of the analysis model based on feedback is performed using a machine learning algorithm.

[0904] (Claim 3)

[0905] The system according to claim 1, characterized in that the prediction of the probability of error occurrence is performed based on error message data analyzed using natural language processing technology. [Explanation of symbols]

[0906] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting log data, A means for analyzing the aforementioned log data to identify error patterns, A means for predicting the probability of an error occurring based on the aforementioned error pattern, A means for automatically adjusting system settings based on the aforementioned prediction, A means of notifying a warning when an error occurs, A means of performing self-learning using feedback data and updating the analysis model, A system that includes this.

2. The system according to claim 1, characterized in that the update of the analysis model based on feedback is performed using a machine learning algorithm.

3. The system according to claim 1, characterized in that the prediction of the probability of error occurrence is performed based on error message data analyzed using natural language processing technology.

Images