system

Abstract

Provide a system. 【Solution means】 Means for acquiring log data, Means for analyzing the log data using natural language processing technology, Means for comparing the analysis result with the standard operating procedure and detecting inconsistencies, Means for providing feedback to the user based on the inconsistencies, Means for learning the feedback result and improving the analysis accuracy, Evaluate the accuracy of operations by physical devices in real time, Means for presenting the result through a visual display device, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In support desks and window departments, a large amount of time and personnel are required for the scrutiny of various operations, so human errors are likely to occur and it is difficult to maintain a certain quality. In addition, prompt responses to urgent responses and inquiries are required, but there is a lack of efficient methods for this.

Means for Solving the Problems

[0005] This invention is a system that includes means for acquiring log data, means for analyzing the acquired log data using natural language processing technology, means for comparing the analysis results with standard work procedures and detecting inconsistencies, means for providing feedback to the user based on the inconsistencies, and means for learning from the feedback results to improve the accuracy of the analysis. This makes it possible to reduce human errors through automated work scrutiny and improve work efficiency and quality.

[0006] "Log data" refers to data that records, in chronological order, the operations and input information performed by the user during equipment setup.

[0007] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and is a method of processing text and audio data.

[0008] "Analysis" refers to the act of examining collected log data and deriving meaning and patterns from it.

[0009] A "standard operating procedure" is a predetermined set of steps or operations required to perform a specific task.

[0010] "Inconsistency" refers to discrepancies or contradictions between log data and standard operating procedures.

[0011] "Feedback" refers to information that provides users with specific instructions and advice based on the analysis results.

[0012] "Learning" is the process of accumulating changes and results after user feedback to improve the accuracy of future analyses. [Brief explanation of the drawing]

[0013] [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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It 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 an 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 an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple 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.

[0017] 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.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] 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."

[0021] [First Embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is a system for automating work verification, aiming to improve the quality and efficiency of equipment setup work in support desks and customer service departments. The system consists primarily of acquiring log data, analyzing it using natural language processing, comparing it with standard operating procedures, detecting inconsistencies, providing feedback, and continuously improving the accuracy of the analysis.

[0035] Retrieving log data

[0036] The terminal records all user operations during device configuration as real-time log data. This includes timestamped execution commands and entered configuration values.

[0037] Analysis and Inconsistency Detection

[0038] The server receives log data sent from the terminal and analyzes it using natural language processing technology. This analysis helps understand the meaning and relationships of the operations and compares the collected data with standard operating procedures. This makes it possible to identify inconsistencies and potential errors.

[0039] Provide feedback

[0040] The server provides users with real-time feedback generated based on the analysis results. This feedback includes specific problem areas and areas requiring correction, providing useful information for users to take quick action.

[0041] Continuous learning

[0042] The server stores the correction results after user feedback and uses them to improve the analysis algorithm. This improves the accuracy of subsequent analyses and enhances the overall system performance.

[0043] Specific example

[0044] For example, suppose a user enters the wrong IP address when configuring a network device. In this case, the terminal records this operation as log data, and the server analyzes it. If the analysis reveals that the entered IP address does not match the standard operating procedure, the server provides feedback to the user saying, "The IP address format is invalid. Please re-enter it in the correct format." The user can then review this and quickly correct the error.

[0045] Thus, embodiments of the present invention provide specific and practical methods for improving the accuracy and efficiency of work.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The terminal begins recording log data simultaneously with the start of the device configuration process. The log data includes detailed information such as the timestamp of each operation, input values, and executed commands.

[0049] Step 2:

[0050] The terminal sends recorded log data to the server in real time. This transmission is carried out through security protocols to ensure safety.

[0051] Step 3:

[0052] The server feeds the received log data into a natural language processing engine and begins analysis. Specifically, it performs text analysis on the log content and extracts important keywords and the meaning of operations.

[0053] Step 4:

[0054] The server compares the analysis results with standard operating procedures to identify inconsistencies and potential errors. In this process, a rule-based algorithm is used for pattern matching to detect deviations from the standard.

[0055] Step 5:

[0056] The server generates a feedback message based on the detection of inconsistencies. This feedback includes the specific location of the problem, its cause, and recommended corrective actions.

[0057] Step 6:

[0058] The server sends the generated feedback message to the user. The user can then review this feedback and correct their work according to the instructions.

[0059] Step 7:

[0060] The server collects user-modified log data and stores it in storage as training data. This data is then sequentially analyzed by machine learning algorithms to aid in subsequent analyses.

[0061] (Example 1)

[0062] 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."

[0063] In system operations and configuration tasks performed by users, it is necessary to quickly and effectively detect problems when incorrect operations or incompatible settings occur and provide users with appropriate corrective instructions in real time. However, existing systems lack sufficient mechanisms to automatically verify the accuracy of work and provide feedback, making it difficult to improve work efficiency and accuracy.

[0064] 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.

[0065] In this invention, the server includes means for transmitting information about an operation to an analysis device, means for analyzing the information about the operation in the analysis device using natural language processing technology and identifying inconsistencies by comparing it with a standard operation plan, and means for providing instructions to the user based on the inconsistencies. This makes it possible to quickly detect non-conformist operations performed by the user and provide appropriate corrective instructions in real time.

[0066] "Information regarding operations" refers to data that records all operations and settings performed by the user.

[0067] An "analysis device" is a device that processes information about received operations and compares it with a standard operation plan.

[0068] "Natural language processing technology" is a technology that semantically analyzes information related to operations and understands its content.

[0069] A "standard operating plan" is reference information that outlines predetermined, precise operating procedures and setting criteria.

[0070] "Inconsistency" refers to elements or errors in the information regarding an operation that do not match the standard operation plan.

[0071] "Providing instructions to users" refers to the process of providing specific guidance so that users can quickly correct any inconsistencies that are detected.

[0072] "Learning" refers to the process of accumulating user responses and correction results to improve the accuracy of future analyses.

[0073] This invention is an automated system that improves the accuracy and efficiency of equipment configuration tasks performed by users. The system mainly consists of two components: a terminal and a server.

[0074] The terminal records information about the user's operations in real time as they configure the device. This information includes, for example, the configuration parameters entered by the user and the commands executed, and is recorded with precise timestamps. The terminal also has the ability to send this data to the server in batch processing or at appropriate times.

[0075] The server analyzes information about received operations using advanced natural language processing techniques. This analysis helps understand the meaning of the operations and identify inconsistencies by comparing them with standard operation plans. The software technologies used include advanced natural language processing frameworks and data analysis algorithms. If an inconsistency is found, the server immediately generates instructions based on the inconsistency and provides them to the user via the terminal. These instructions specifically provide the information necessary to effectively correct the operational error.

[0076] As a concrete example, consider a scenario where a user configures the IP address of a new network device. The terminal records the user's input and sends that data to the server. The server analyzes the data, and if it detects that the entered IP address is incorrect, it provides the user with a message such as, "The IP address format is invalid. Please re-enter it in the correct format."

[0077] The following are some possible examples of prompt statements.

[0078] "Please create a feedback message to be displayed when an incorrect IP address is entered during network device configuration."

[0079] This invention aims to significantly improve the accuracy and efficiency of user-performed equipment setup tasks by automatically monitoring the process and providing real-time problem identification and instructions.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The terminal monitors all configuration operations performed by the user in real time and records information about those operations. Specifically, it adds a timestamp to the commands and configuration values ​​entered by the user and saves them as logs. The input includes the user's operation data, and the output is a log file containing this data.

[0083] Step 2:

[0084] The terminal sends the operation information recorded in the log to the server in batches at regular intervals. This operation involves splitting the recorded log file into packets and transferring them to the server via a secure communication protocol. The input is the operation log file, and the output is the data packets transferred to the server.

[0085] Step 3:

[0086] The server analyzes the operation information received from the terminal using natural language processing technology. The specific analysis involves tokenization and syntax analysis to extract meaning from the log data. The input is the log data sent from the terminal, and the output is the analyzed semantic information.

[0087] Step 4:

[0088] The server compares the standard operation plan and operational information based on the analysis to identify inconsistencies. Specifically, it uses a rule-based comparison algorithm to identify items that do not conform to the specified procedure. The inputs are the analyzed information and the standard operation plan, and the output is a list of identified inconsistencies.

[0089] Step 5:

[0090] The server generates instructions based on inconsistencies and provides them to the user in real time via the terminal. Specifically, its actions include creating proposed corrections based on the inconsistencies and sending these proposals to the user in an easily understandable message format. The input is a list of inconsistencies, and the output is a feedback message to the user.

[0091] Step 6:

[0092] The user corrects the error according to the instructions received and reconfigures the settings. This correction is again logged as operation information and sent to the server for subsequent learning processes. The input is a feedback message from the server, and the output is the generated corrected log information.

[0093] (Application Example 1)

[0094] 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."

[0095] There is a need to improve work efficiency while maintaining accuracy in setting up and adjusting equipment in factories. In particular, there is a lack of effective methods for immediately detecting and correcting setting errors that occur during manual setup. Furthermore, there is a challenge in providing an environment where workers can receive immediate feedback.

[0096] 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.

[0097] In this invention, the server includes means for acquiring log data, means for analyzing it using natural language processing technology, means for comparing the analysis results with standard operating procedures and detecting inconsistencies, and means for evaluating the accuracy of operations by physical devices in real time and presenting the results through a visual display device. This makes it possible to immediately detect misconfigurations during equipment setup work in a factory and provide rapid feedback to the worker to encourage correction.

[0098] "Log data" refers to a collection of data that records user operations during equipment configuration. Specifically, it includes information such as executed commands and entered configuration values, each with a timestamp.

[0099] "Natural language processing technology" is a part of computer science that analyzes the meaning and relationships of collected text data and organizes the information in a way that humans can understand.

[0100] "Means for detecting inconsistencies" refers to methods or devices for identifying errors or deviations from regulations by comparing analyzed work logs with standard operating procedures.

[0101] "Means of providing feedback" refers to a method or apparatus for notifying the user of specific problems and areas for correction based on detected inconsistencies, thereby facilitating the correction of work.

[0102] A "visual display device" is a device that displays analysis results and feedback information in a way that humans can visually understand, and this includes head-mounted displays and smart glasses.

[0103] This embodiment of the invention is a robot operation support system for a factory environment where equipment setup work is performed. The system consists of a terminal, a server, and a visual display device equipped with a user interface. Specifically, the following processes are performed.

[0104] The terminal records all operations during the device setup process as log data in real time, including executed commands and input settings as timestamps.

[0105] The server receives this log data and analyzes it using natural language processing techniques. In this analysis, specific natural language processing tools, such as spaCy or Google Cloud's Natural Language API, are used to understand the meaning and relationships of the operations. In this step, the analysis results are compared with standard operating procedures to detect inconsistencies and potential errors.

[0106] Based on the inconsistencies detected by the server, the feedback provided to the user includes information about specific problem areas and areas requiring correction. This information is transmitted to the user in real time through visual display devices, such as smart glasses or head-mounted displays, enabling the user to take immediate action.

[0107] The analysis results and user modification history are stored on the server and used to improve the analysis algorithm, enabling continuous learning and improving the accuracy of subsequent analyses.

[0108] For example, if a welding robot starts work with an incorrect temperature setting, the server provides feedback to the operator via a visual display, such as "The temperature setting is lower than standard. Please correct it to the specified temperature," enabling a quick response. This process can also be performed using a prompt message to a generative AI model, such as "Please check and provide feedback whether the robot is using the correct temperature setting for the current welding process."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The terminal records all operations as real-time log data when a user begins configuring the device. Input consists of the user's operation commands and configuration values, which are stored with timestamps. Output is log data that continuously updates with records of the configuration operations. In practice, the terminal monitors the configuration process and collects data at predetermined intervals.

[0112] Step 2:

[0113] The server receives log data sent from the terminal. The input is sequential log data from the terminal, and the output is a formatted dataset. The server aggregates the data and performs operations to prepare it for analysis.

[0114] Step 3:

[0115] The server analyzes pre-processed log data using natural language processing techniques. The input is a formatted dataset, and the output generates information analyzing the meaning and relationships of each operation. In this step, spaCy and the Google Cloud Natural Language API are used to extract linguistic features from the data.

[0116] Step 4:

[0117] The server compares the analysis results with standard operating procedures to detect inconsistencies. The input consists of the information obtained through analysis and existing standard operating procedures; the output is a list of inconsistencies. The server performs calculations and comparisons to extract the parts that do not match.

[0118] Step 5:

[0119] The server provides feedback to the user based on inconsistencies. The input is a list of inconsistencies, and the output is feedback highlighting the points that need correction. Visual displays are used to notify the user of this information in real time.

[0120] Step 6:

[0121] The user quickly corrects the device settings based on the feedback. The input is feedback information from a visual display, and the output is the correctly corrected settings. The user then performs the correction action based on the presented information.

[0122] Step 7:

[0123] The server stores feedback and its results as training data and uses it to improve the analysis algorithm. The input is the corrected feedback information, and the output is an improved algorithm for better accuracy in the next analysis. The server saves the information in a database and performs actions to update the algorithm using machine learning techniques. This process is optimized using prompts to the generative AI model such as, "The robot should check and provide feedback on whether it is using the correct temperature settings in the current welding process."

[0124] 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.

[0125] This invention is a system designed to more efficiently scrutinize user equipment setup procedures and reduce human error. The system combines log data collection, natural language processing analysis, comparison with standard operating procedures, inconsistency detection, user feedback, and a learning function to improve analysis accuracy, in addition to an emotion engine that recognizes user emotions.

[0126] Log data acquisition and analysis

[0127] The terminal logs all device configuration operations performed by the user and sends them to the server. The server analyzes the received log data using a natural language processing engine to understand its meaning. The analysis is then compared to standard operating procedures, and any inconsistencies are detected.

[0128] Emotion recognition by an emotion engine

[0129] The device collects the user's voice and text data and sends it to the server's emotion engine. The emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, confusion, satisfaction, etc.).

[0130] Provide feedback

[0131] The server generates feedback based on the analysis results of inconsistencies and the recognition results of the emotion engine. The feedback content is adjusted according to the user's emotional state and delivered at the optimal time and in the appropriate manner. If the user is stressed, gentle, step-by-step guidance can be provided; if the user is calm, efficient methods can be recommended.

[0132] Learning and accuracy improvement

[0133] The server accumulates user feedback as training data and uses it to improve the accuracy of its analysis. By also learning from emotional data, the server's ability to provide feedback that is more tailored to the user's emotions improves.

[0134] Specific example

[0135] For example, suppose a user enters incorrect parameters when configuring network settings. However, if the user is feeling stressed or anxious, the server will not only correct the error but also provide reassuring feedback such as, "It's okay, stay calm and try again." This kind of emotionally sensitive support allows users to complete tasks more smoothly.

[0136] This system simultaneously automates technical scrutiny and improves the user experience, leading to significant improvements in operational efficiency.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The terminal records all operations as log data from the moment the user begins configuring the device. The log details the commands entered and the settings changed, along with timestamps.

[0140] Step 2:

[0141] The terminal sends log data to the server in real time. A secure communication protocol is used to ensure the data's safety.

[0142] Step 3:

[0143] The server passes the received log data to the natural language processing engine and begins analysis. The analysis involves extracting specific keywords from the text content and performing contextual analysis to understand the intent behind the operations.

[0144] Step 4:

[0145] The device collects emotional data from the user's voice and text and sends it to the server.

[0146] Step 5:

[0147] The server uses an emotion engine to analyze the user's emotions. Specifically, it recognizes emotions such as stress, confusion, and satisfaction from the tone of voice and the content of the text.

[0148] Step 6:

[0149] The server detects inconsistencies by comparing the analysis results of log data and sentiment data with standard operating procedures. These analysis results, including the inconsistencies, are then compiled as feedback data.

[0150] Step 7:

[0151] The server adjusts the generated feedback based on the user's emotions. For example, if the user is stressed, it provides gentle, step-by-step instructions; if the user is relaxed, it suggests efficient methods.

[0152] Step 8:

[0153] The server sends the adjusted feedback to the user. The user receives this feedback, reviews their work, and makes corrections as needed.

[0154] Step 9:

[0155] The server records the results after user modifications and stores them in the system as training data. This helps improve the accuracy of future analyses and feedback.

[0156] (Example 2)

[0157] 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 will be referred to as the "terminal."

[0158] When users configure systems and equipment, problems can occur due to operational errors or incorrect input, leading to decreased work efficiency. Furthermore, a lack of accurate understanding of the user's emotions during operation can result in inadequate feedback, adding to their stress. Therefore, it is necessary to refine the configuration process, reduce human error through feedback that takes user emotions into account, and improve both work efficiency and user experience.

[0159] 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.

[0160] In this invention, the server includes means for acquiring log data, means for analyzing the log data using natural language processing technology, means for comparing the analysis results with standard operating procedures and detecting inconsistencies, means for recognizing the user's emotional state from their voice or text, means for providing feedback to the user based on the inconsistencies and emotional recognition, and means for improving the accuracy of the analysis by learning the feedback results and emotional data. This makes it possible to immediately detect user errors and provide appropriate feedback, thereby reducing user stress and enabling efficient operation.

[0161] "Log data" refers to data that records the details of equipment settings and operations performed by a user, and includes timestamps and details of the operations performed.

[0162] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes methods for converting text content into structured data.

[0163] A "standard operating procedure" is a set of predetermined procedures and standards for performing a specific task, serving as a guideline to ensure consistency and accuracy in operations.

[0164] "Inconsistency" refers to parts of the analyzed data that deviate from standard operating procedures, indicating errors or mistakes that occur during setup or operation.

[0165] "Feedback" refers to information and advice provided based on the user's actions and emotional state, and is a response that helps the user improve or adjust their next actions.

[0166] "Emotional state" refers to the psychological and emotional state a user is in while using the system, and includes a variety of emotions such as stress, confusion, and satisfaction.

[0167] "Learning" is the process by which a system continuously improves the accuracy of its analysis and feedback based on feedback results and sentiment data.

[0168] This invention is a system designed to streamline the user's equipment setup process and reduce human error. Specifically, it combines log data collection, natural language processing analysis, comparison with standard operating procedures, inconsistency detection, user feedback provision, a learning function aimed at improving analysis accuracy, and an emotion engine that recognizes the user's emotions.

[0169] The device includes hardware and software to record all user actions in real time and generate log data. Specifically, it captures keyboard input and screen operations using sensors and tracking software. The collected log data is sent to a server at regular intervals.

[0170] The server is equipped with a natural language processing engine for processing received log data. This engine uses natural language processing technologies (e.g., SpaCy and NLTK) to analyze the log content and understand the meaning of the operations performed. The results are compared with standard operating procedures, and if inconsistencies are detected, preparations for the next step are made.

[0171] The device also acquires voice and text messages entered by the user and sends them to the server's emotion engine as emotion data. The emotion engine recognizes the user's emotional state from the collected data and identifies states such as stress and confusion.

[0172] Based on the analysis results and emotion recognition results, the server generates optimal feedback. This feedback is adjusted according to the user's psychological state, so, for example, a user who is feeling anxious will receive content that promotes calmness. This feedback is communicated to the user through screen display and audio output.

[0173] Furthermore, the server accumulates feedback results and user sentiment data as training data, which is used to continuously improve the accuracy of the analysis. This uses a generative AI model to improve the accuracy and adaptability of the feedback.

[0174] As a concrete example, consider a situation where a user is configuring network settings and has entered incorrect parameters. If the user is feeling stressed, the system might provide feedback such as, "It's okay, please stay calm and try again." This kind of empathetic response allows the user to continue working smoothly.

[0175] An example of a prompt message could be, "Please suggest ways for users to provide feedback if they experience stress during the setup process."

[0176] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0177] Step 1:

[0178] The terminal monitors the user's device configuration operations in real time and records the input as log data. Specifically, it captures user interactions such as mouse clicks, keyboard input, and screen touches using sensors and tracking software. This log data includes a timestamp corresponding to the operation and the details of the operation, which are used in subsequent analysis processes.

[0179] Step 2:

[0180] The terminal processes the recorded log data in batches at regular intervals and sends it to the server. The server receives this log data as input to a natural language processing engine and performs analysis. As part of the data processing, natural language processing techniques are used to semantically analyze the log data and extract the user's intentions and actions. The analyzed data is compared with pre-configured standard operating procedures, and any inconsistencies are output.

[0181] Step 3:

[0182] The terminal acquires the user's voice input and text messages and sends them to the server as emotion data. This data is processed using voice analysis software and text analysis tools. The server's emotion engine performs data calculations based on this data to identify the user's emotional state. Specifically, it analyzes the characteristics of the voice tone and extracts emotion-related keywords from the text. This results in the output of the user's emotional state (e.g., stress, confusion, satisfaction).

[0183] Step 4:

[0184] The server receives the analyzed inconsistent data and emotion recognition results as input and generates optimal feedback. Using a generative AI model, the feedback is adjusted to match the user's current emotional state. For example, if the user is feeling anxious, the feedback might be a gentle instruction such as, "It's okay, calm down and try again." This feedback is provided to the user as a text message or voice output.

[0185] Step 5:

[0186] The server accumulates feedback results and user sentiment data, using it as training data to improve analysis accuracy. During this training process, the dataset is continuously updated. Based on this data, the generative AI model improves the accuracy of feedback, enabling new character recognition and more accurate sentiment responses. In this way, the overall operational efficiency and user experience of the system are continuously improved.

[0187] (Application Example 2)

[0188] 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".

[0189] In on-site work, it is crucial for workers to follow precise procedures, but human errors are more likely to occur in complex tasks or when many people are involved. Furthermore, a worker's mental state significantly impacts the accuracy and efficiency of their work, but existing systems have lacked sufficient support that takes this emotional state into account. Therefore, there is a need for a system that can reduce work errors and provide appropriate feedback tailored to the worker's emotional state.

[0190] 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.

[0191] In this invention, the server includes means for acquiring log information, means for analyzing the log information using natural language processing technology, means for comparing the analysis results with standard process procedures and detecting inconsistencies, and means for recognizing the emotional state of the worker. This makes it possible to reduce work errors and improve work efficiency by providing feedback that corresponds to the worker's mental state.

[0192] "Log information" refers to data that records user operations and actions.

[0193] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0194] "Standard process procedures" refer to a set of procedures or methods that serve as the standard for carrying out work.

[0195] "Inconsistency" refers to a state that indicates a discrepancy or contradiction between the analysis results and the standard process procedure.

[0196] "Feedback" refers to a response or reaction to given information or instructions.

[0197] "Analysis accuracy" is an indicator that shows the accuracy and detail of the data analysis results.

[0198] "Emotional state" refers to the psychological or emotional state that a user exhibits at a specific point in time.

[0199] "Diverse data" refers to data obtained from multiple sources that have different formats and content.

[0200] The system implementing this invention is intended for work supervision at construction sites, monitoring the work processes of on-site workers in real time and providing feedback to reduce work errors. The system uses smartphones or smart glasses to acquire and analyze worker operation logs and voice data.

[0201] The server analyzes the acquired log information using a natural language processing engine and detects inconsistencies by comparing the results with standard process procedures. If an inconsistency is detected, the server generates appropriate feedback, taking into account the worker's emotional state, and displays it on the terminal. The feedback is adjusted to alleviate the worker's emotional state and recommend a retry.

[0202] The system's specific configuration uses Python and Tensorflow® for natural language processing and emotion recognition, and Flask for server-side processing. The user interface is built with React and optimized for smartphones and smart glasses. For emotion recognition, a model based on diverse data is used to analyze emotions in real time from the worker's voice data.

[0203] For example, if a worker makes an incorrect connection while following a complex blueprint, they will receive real-time feedback, such as "Calm down, take a deep breath, and check the correct procedure." In this way, the system allows for highly accurate work while taking into consideration the emotional state of the worker.

[0204] An example of a prompt for a generative AI model might be: "Please tell me specifically how to automatically detect errors in construction site work procedures and provide optimal real-time feedback based on the emotional state of the workers."

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The terminal collects field workers' operations and voice data in real time and records it as log information. This input log information includes a process of converting work procedures and voice data into a digital format. This enables accuracy of operations and recognition of emotions from voice.

[0208] Step 2:

[0209] The terminal sends recorded log information to the server. The input here consists of digitized operation logs and audio data, which the server receives and prepares to proceed to the next analysis step.

[0210] Step 3:

[0211] The server analyzes the acquired log information using natural language processing techniques. In this process, the log information is compared against standard procedure data. The input is operation log data, and the output is the presence or absence of inconsistencies for each log. Specifically, it checks how closely the operation procedure matches the standard.

[0212] Step 4:

[0213] The server processes the voice data into an emotion recognition engine to analyze the worker's emotional state. The input for this step is voice data, and the output is an emotional state (e.g., stress, anxiety, calmness, etc.). Voice pattern analysis is performed at this stage.

[0214] Step 5:

[0215] The server generates feedback based on the analysis results and emotional state. In this step, the input is inconsistent information and emotional state, and the output is a tailored feedback message. Specific actions include sending messages to promote relaxation and determining effective guidance content.

[0216] Step 6:

[0217] The terminal displays the generated feedback to the worker. The input is a feedback message, and the expected output is the worker's response. Specifically, the terminal displays the message on its screen.

[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 a system for automating work verification, aiming to improve the quality and efficiency of equipment setup work in support desks and customer service departments. The system consists primarily of acquiring log data, analyzing it using natural language processing, comparing it with standard operating procedures, detecting inconsistencies, providing feedback, and continuously improving the accuracy of the analysis.

[0235] Retrieving log data

[0236] The terminal records all user operations during device configuration as real-time log data. This includes timestamped execution commands and entered configuration values.

[0237] Analysis and Inconsistency Detection

[0238] The server receives log data sent from the terminal and analyzes it using natural language processing technology. This analysis helps understand the meaning and relationships of the operations and compares the collected data with standard operating procedures. This makes it possible to identify inconsistencies and potential errors.

[0239] Provide feedback

[0240] The server provides users with real-time feedback generated based on the analysis results. This feedback includes specific problem areas and areas requiring correction, providing useful information for users to take quick action.

[0241] Continuous learning

[0242] The server stores the correction results after user feedback and uses them to improve the analysis algorithm. This improves the accuracy of subsequent analyses and enhances the overall system performance.

[0243] Specific example

[0244] For example, suppose a user enters the wrong IP address when configuring a network device. In this case, the terminal records this operation as log data, and the server analyzes it. If the analysis reveals that the entered IP address does not match the standard operating procedure, the server provides feedback to the user saying, "The IP address format is invalid. Please re-enter it in the correct format." The user can then review this and quickly correct the error.

[0245] Thus, embodiments of the present invention provide specific and practical methods for improving the accuracy and efficiency of work.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The terminal begins recording log data simultaneously with the start of the device configuration process. The log data includes detailed information such as the timestamp of each operation, input values, and executed commands.

[0249] Step 2:

[0250] The terminal sends recorded log data to the server in real time. This transmission is carried out through security protocols to ensure safety.

[0251] Step 3:

[0252] The server feeds the received log data into a natural language processing engine and begins analysis. Specifically, it performs text analysis on the log content and extracts important keywords and the meaning of operations.

[0253] Step 4:

[0254] The server compares the analysis results with standard operating procedures to identify inconsistencies and potential errors. In this process, a rule-based algorithm is used for pattern matching to detect deviations from the standard.

[0255] Step 5:

[0256] The server generates a feedback message based on the detection of inconsistencies. This feedback includes the specific location of the problem, its cause, and recommended corrective actions.

[0257] Step 6:

[0258] The server sends the generated feedback message to the user. The user can then review this feedback and correct their work according to the instructions.

[0259] Step 7:

[0260] The server collects user-modified log data and stores it in storage as training data. This data is then sequentially analyzed by machine learning algorithms to aid in subsequent analyses.

[0261] (Example 1)

[0262] 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."

[0263] In system operations and configuration tasks performed by users, it is necessary to quickly and effectively detect problems when incorrect operations or incompatible settings occur and provide users with appropriate corrective instructions in real time. However, existing systems lack sufficient mechanisms to automatically verify the accuracy of work and provide feedback, making it difficult to improve work efficiency and accuracy.

[0264] 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.

[0265] In this invention, the server includes means for transmitting information about an operation to an analysis device, means for analyzing the information about the operation in the analysis device using natural language processing technology and identifying inconsistencies by comparing it with a standard operation plan, and means for providing instructions to the user based on the inconsistencies. This makes it possible to quickly detect non-conformist operations performed by the user and provide appropriate corrective instructions in real time.

[0266] "Information regarding operations" refers to data that records all operations and settings performed by the user.

[0267] An "analysis device" is a device that processes information about received operations and compares it with a standard operation plan.

[0268] "Natural language processing technology" is a technology that semantically analyzes information related to operations and understands its content.

[0269] A "standard operating plan" is reference information that outlines predetermined, precise operating procedures and setting criteria.

[0270] "Inconsistency" refers to elements or errors in the information regarding an operation that do not match the standard operation plan.

[0271] "Providing instructions to users" refers to the process of providing specific guidance so that users can quickly correct any inconsistencies that are detected.

[0272] "Learning" refers to the process of accumulating user responses and correction results to improve the accuracy of future analyses.

[0273] This invention is an automated system that improves the accuracy and efficiency of equipment configuration tasks performed by users. The system mainly consists of two components: a terminal and a server.

[0274] The terminal records information about the user's operations in real time as they configure the device. This information includes, for example, the configuration parameters entered by the user and the commands executed, and is recorded with precise timestamps. The terminal also has the ability to send this data to the server in batch processing or at appropriate times.

[0275] The server analyzes information about received operations using advanced natural language processing techniques. This analysis helps understand the meaning of the operations and identify inconsistencies by comparing them with standard operation plans. The software technologies used include advanced natural language processing frameworks and data analysis algorithms. If an inconsistency is found, the server immediately generates instructions based on the inconsistency and provides them to the user via the terminal. These instructions specifically provide the information necessary to effectively correct the operational error.

[0276] As a concrete example, consider a scenario where a user configures the IP address of a new network device. The terminal records the user's input and sends that data to the server. The server analyzes the data, and if it detects that the entered IP address is incorrect, it provides the user with a message such as, "The IP address format is invalid. Please re-enter it in the correct format."

[0277] The following are some possible examples of prompt statements.

[0278] "Please create a feedback message to be displayed when an incorrect IP address is entered during network device configuration."

[0279] This invention aims to significantly improve the accuracy and efficiency of user-performed equipment setup tasks by automatically monitoring the process and providing real-time problem identification and instructions.

[0280] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0281] Step 1:

[0282] The terminal monitors all configuration operations performed by the user in real time and records information about those operations. Specifically, it adds a timestamp to the commands and configuration values ​​entered by the user and saves them as logs. The input includes the user's operation data, and the output is a log file containing this data.

[0283] Step 2:

[0284] The terminal sends the operation information recorded in the log to the server in batches at regular intervals. The operations here include splitting the recorded log file into packets and transferring them to the server via a secure communication protocol. The input is the operation log file, and the output is the data packets transferred to the server.

[0285] Step 3:

[0286] The server analyzes the operation information received from the terminal using natural language processing technology. The specific operations of the analysis include performing tokenization and syntactic analysis to extract the meaning of the log data. The input is the log data sent from the terminal, and the output is the generated semantic information.

[0287] Step 4:

[0288] The server compares the standard operation plan with the operation information based on the analysis and identifies inconsistencies. As a specific operation, a rule-based comparison algorithm is used to identify items that do not conform to the specified procedures. The input is the analyzed information and the standard operation plan, and the output is a list of identified inconsistencies.

[0289] Step 5:

[0290] The server generates instructions based on the inconsistencies and provides them to the user in real time via the terminal. As specific operations, it includes creating amendments based on the content of the inconsistencies and sending the proposal in a message format that is easy for the user to understand. The input is the list of inconsistencies, and the output is a feedback message to the user.

[0291] Step 6:

[0292] The user corrects the error according to the instructions received and reconfigures the settings. This correction is again logged as operation information and sent to the server for subsequent learning processes. The input is a feedback message from the server, and the output is the generated corrected log information.

[0293] (Application Example 1)

[0294] 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 glasses 214 will be referred to as the "terminal."

[0295] There is a need to improve work efficiency while maintaining accuracy in setting up and adjusting equipment in factories. In particular, there is a lack of effective methods for immediately detecting and correcting setting errors that occur during manual setup. Furthermore, there is a challenge in providing an environment where workers can receive immediate feedback.

[0296] 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.

[0297] In this invention, the server includes means for acquiring log data, means for analyzing it using natural language processing technology, means for comparing the analysis results with standard operating procedures and detecting inconsistencies, and means for evaluating the accuracy of operations by physical devices in real time and presenting the results through a visual display device. This makes it possible to immediately detect misconfigurations during equipment setup work in a factory and provide rapid feedback to the worker to encourage correction.

[0298] "Log data" refers to a collection of data that records user operations during equipment configuration. Specifically, it includes information such as executed commands and entered configuration values, each with a timestamp.

[0299] "Natural language processing technology" is a part of computer science that analyzes the meaning and relationships of collected text data and organizes the information in a way that humans can understand.

[0300] "Means for detecting inconsistencies" refers to methods or devices for identifying errors or deviations from regulations by comparing analyzed work logs with standard operating procedures.

[0301] "Means of providing feedback" refers to a method or apparatus for notifying the user of specific problems and areas for correction based on detected inconsistencies, thereby facilitating the correction of work.

[0302] A "visual display device" is a device that displays analysis results and feedback information in a way that humans can visually understand, and this includes head-mounted displays and smart glasses.

[0303] This embodiment of the invention is a robot operation support system for a factory environment where equipment setup work is performed. The system consists of a terminal, a server, and a visual display device equipped with a user interface. Specifically, the following processes are performed.

[0304] The terminal records all operations during the device setup process as log data in real time, including executed commands and input settings as timestamps.

[0305] The server receives this log data and analyzes it using natural language processing techniques. In this analysis, specific natural language processing tools, such as spaCy or Google Cloud's natural language API, are used to understand the meaning and relationships of the operations. In this step, the analysis results are compared with standard operating procedures to detect inconsistencies and potential errors.

[0306] Based on the inconsistencies detected by the server, the feedback provided to the user includes information about specific problem areas and areas that require correction. This information is transmitted to the user in real time through a visual display device, such as smart glasses or a head-mounted display. This enables the user to take immediate action.

[0307] The analysis results and the history of corrections made by the user are stored on the server and used to improve the analysis algorithm, enabling continuous learning and improving the analysis accuracy for subsequent times.

[0308] As a specific example, when a welding robot starts working with an incorrect temperature setting, the server provides feedback such as "The temperature setting is lower than the standard. Please correct it to the specified temperature" to the operator through the visual display device, enabling a prompt response. This process can also be executed by using a prompt sentence to the generative AI model that says "Please check whether the robot is using the correct temperature setting in the current welding process and provide feedback."

[0309] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0310] Step 1:

[0311] When the terminal starts the device setting operation by the user, it records all operations as log data in real time. The inputs are the user's operation commands and setting values, which are stored with a timestamp. As output, log data in which the record of the setting operation is continuously updated is obtained. The actual operation is that the terminal monitors the setting operation and collects data at predetermined intervals.

[0312] Step 2:

[0313] The server receives log data sent from the terminal. The input is sequential log data from the terminal, and the output is a formatted dataset. The server aggregates the data and performs operations to prepare it for analysis.

[0314] Step 3:

[0315] The server analyzes pre-processed log data using natural language processing techniques. The input is a formatted dataset, and the output generates information analyzing the meaning and relationships of each operation. In this step, spaCy and the Google Cloud Natural Language API are used to extract linguistic features from the data.

[0316] Step 4:

[0317] The server compares the analysis results with standard operating procedures to detect inconsistencies. The input consists of the information obtained through analysis and existing standard operating procedures; the output is a list of inconsistencies. The server performs calculations and comparisons to extract the parts that do not match.

[0318] Step 5:

[0319] The server provides feedback to the user based on inconsistencies. The input is a list of inconsistencies, and the output is feedback highlighting the points that need correction. Visual displays are used to notify the user of this information in real time.

[0320] Step 6:

[0321] The user quickly corrects the device settings based on the feedback. The input is feedback information from a visual display, and the output is the correctly corrected settings. The user then performs the correction action based on the presented information.

[0322] Step 7:

[0323] The server stores feedback and its results as training data and uses it to improve the analysis algorithm. The input is the corrected feedback information, and the output is an improved algorithm for better accuracy in the next analysis. The server saves the information in a database and performs actions to update the algorithm using machine learning techniques. This process is optimized using prompts to the generative AI model such as, "The robot should check and provide feedback on whether it is using the correct temperature settings in the current welding process."

[0324] 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.

[0325] This invention is a system designed to more efficiently scrutinize user equipment setup procedures and reduce human error. The system combines log data collection, natural language processing analysis, comparison with standard operating procedures, inconsistency detection, user feedback, and a learning function to improve analysis accuracy, in addition to an emotion engine that recognizes user emotions.

[0326] Log data acquisition and analysis

[0327] The terminal logs all device configuration operations performed by the user and sends them to the server. The server analyzes the received log data using a natural language processing engine to understand its meaning. The analysis is then compared to standard operating procedures, and any inconsistencies are detected.

[0328] Emotion recognition by an emotion engine

[0329] The device collects the user's voice and text data and sends it to the server's emotion engine. The emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, confusion, satisfaction, etc.).

[0330] Provide feedback

[0331] The server generates feedback based on the analysis results of inconsistencies and the recognition results of the emotion engine. The feedback content is adjusted according to the user's emotional state and delivered at the optimal time and in the appropriate manner. If the user is stressed, gentle, step-by-step guidance can be provided; if the user is calm, efficient methods can be recommended.

[0332] Learning and accuracy improvement

[0333] The server accumulates user feedback as training data and uses it to improve the accuracy of its analysis. By also learning from emotional data, the server's ability to provide feedback that is more tailored to the user's emotions improves.

[0334] Specific example

[0335] For example, suppose a user enters incorrect parameters when configuring network settings. However, if the user is feeling stressed or anxious, the server will not only correct the error but also provide reassuring feedback such as, "It's okay, stay calm and try again." This kind of emotionally sensitive support allows users to complete tasks more smoothly.

[0336] This system simultaneously automates technical scrutiny and improves the user experience, leading to significant improvements in operational efficiency.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] The terminal records all operations as log data from the moment the user begins configuring the device. The log details the commands entered and the settings changed, along with timestamps.

[0340] Step 2:

[0341] The terminal sends log data to the server in real time. A secure communication protocol is used to ensure the data's safety.

[0342] Step 3:

[0343] The server passes the received log data to the natural language processing engine and begins analysis. The analysis involves extracting specific keywords from the text content and performing contextual analysis to understand the intent behind the operations.

[0344] Step 4:

[0345] The device collects emotional data from the user's voice and text and sends it to the server.

[0346] Step 5:

[0347] The server uses an emotion engine to analyze the user's emotions. Specifically, it recognizes emotions such as stress, confusion, and satisfaction from the tone of voice and the content of the text.

[0348] Step 6:

[0349] The server detects inconsistencies by comparing the analysis results of log data and sentiment data with standard operating procedures. These analysis results, including the inconsistencies, are then compiled as feedback data.

[0350] Step 7:

[0351] The server adjusts the generated feedback based on the user's emotions. For example, if the user is stressed, it provides gentle, step-by-step instructions; if the user is relaxed, it suggests efficient methods.

[0352] Step 8:

[0353] The server sends the adjusted feedback to the user. The user receives this feedback, reviews their work, and makes corrections as needed.

[0354] Step 9:

[0355] The server records the results after user modifications and stores them in the system as training data. This helps improve the accuracy of future analyses and feedback.

[0356] (Example 2)

[0357] 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".

[0358] When users configure systems and equipment, problems can occur due to operational errors or incorrect input, leading to decreased work efficiency. Furthermore, a lack of accurate understanding of the user's emotions during operation can result in inadequate feedback, adding to their stress. Therefore, it is necessary to refine the configuration process, reduce human error through feedback that takes user emotions into account, and improve both work efficiency and user experience.

[0359] 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.

[0360] In this invention, the server includes means for acquiring log data, means for analyzing the log data using natural language processing technology, means for comparing the analysis results with standard operating procedures and detecting inconsistencies, means for recognizing the user's emotional state from their voice or text, means for providing feedback to the user based on the inconsistencies and emotional recognition, and means for improving the accuracy of the analysis by learning the feedback results and emotional data. This makes it possible to immediately detect user errors and provide appropriate feedback, thereby reducing user stress and enabling efficient operation.

[0361] "Log data" refers to data that records the details of equipment settings and operations performed by a user, and includes timestamps and details of the operations performed.

[0362] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes methods for converting text content into structured data.

[0363] A "standard operating procedure" is a set of predetermined procedures and standards for performing a specific task, serving as a guideline to ensure consistency and accuracy in operations.

[0364] "Inconsistency" refers to parts of the analyzed data that deviate from standard operating procedures, indicating errors or mistakes that occur during setup or operation.

[0365] "Feedback" refers to information and advice provided based on the user's actions and emotional state, and is a response that helps the user improve or adjust their next actions.

[0366] "Emotional state" refers to the psychological and emotional state a user is in while using the system, and includes a variety of emotions such as stress, confusion, and satisfaction.

[0367] "Learning" is the process by which a system continuously improves the accuracy of its analysis and feedback based on feedback results and sentiment data.

[0368] This invention is a system designed to streamline the user's equipment setup process and reduce human error. Specifically, it combines log data collection, natural language processing analysis, comparison with standard operating procedures, inconsistency detection, user feedback provision, a learning function aimed at improving analysis accuracy, and an emotion engine that recognizes the user's emotions.

[0369] The device includes hardware and software to record all user actions in real time and generate log data. Specifically, it captures keyboard input and screen operations using sensors and tracking software. The collected log data is sent to a server at regular intervals.

[0370] The server is equipped with a natural language processing engine for processing received log data. This engine uses natural language processing technologies (e.g., SpaCy and NLTK) to analyze the log content and understand the meaning of the operations performed. The results are compared with standard operating procedures, and if inconsistencies are detected, preparations for the next step are made.

[0371] The device also acquires voice and text messages entered by the user and sends them to the server's emotion engine as emotion data. The emotion engine recognizes the user's emotional state from the collected data and identifies states such as stress and confusion.

[0372] Based on the analysis results and emotion recognition results, the server generates optimal feedback. This feedback is adjusted according to the user's psychological state, so, for example, a user who is feeling anxious will receive content that promotes calmness. This feedback is communicated to the user through screen display and audio output.

[0373] Furthermore, the server accumulates feedback results and user sentiment data as training data, which is used to continuously improve the accuracy of the analysis. This uses a generative AI model to improve the accuracy and adaptability of the feedback.

[0374] As a concrete example, consider a situation where a user is configuring network settings and has entered incorrect parameters. If the user is feeling stressed, the system might provide feedback such as, "It's okay, please stay calm and try again." This kind of empathetic response allows the user to continue working smoothly.

[0375] An example of a prompt message could be, "Please suggest ways for users to provide feedback if they experience stress during the setup process."

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The terminal monitors the user's device configuration operations in real time and records the input as log data. Specifically, it captures user interactions such as mouse clicks, keyboard input, and screen touches using sensors and tracking software. This log data includes a timestamp corresponding to the operation and the details of the operation, which are used in subsequent analysis processes.

[0379] Step 2:

[0380] The terminal processes the recorded log data in batches at regular intervals and sends it to the server. The server receives this log data as input to a natural language processing engine and performs analysis. As part of the data processing, natural language processing techniques are used to semantically analyze the log data and extract the user's intentions and actions. The analyzed data is compared with pre-configured standard operating procedures, and any inconsistencies are output.

[0381] Step 3:

[0382] The terminal acquires the user's voice input and text messages and sends them to the server as emotion data. This data is processed using voice analysis software and text analysis tools. The server's emotion engine performs data calculations based on this data to identify the user's emotional state. Specifically, it analyzes the characteristics of the voice tone and extracts emotion-related keywords from the text. This results in the output of the user's emotional state (e.g., stress, confusion, satisfaction).

[0383] Step 4:

[0384] The server receives the analyzed inconsistent data and emotion recognition results as input and generates optimal feedback. Using a generative AI model, the feedback is adjusted to match the user's current emotional state. For example, if the user is feeling anxious, the feedback might be a gentle instruction such as, "It's okay, calm down and try again." This feedback is provided to the user as a text message or voice output.

[0385] Step 5:

[0386] The server accumulates feedback results and user sentiment data, using it as training data to improve analysis accuracy. During this training process, the dataset is continuously updated. Based on this data, the generative AI model improves the accuracy of feedback, enabling new character recognition and more accurate sentiment responses. In this way, the overall operational efficiency and user experience of the system are continuously improved.

[0387] (Application Example 2)

[0388] 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".

[0389] In on-site work, it is crucial for workers to follow precise procedures, but human errors are more likely to occur in complex tasks or when many people are involved. Furthermore, a worker's mental state significantly impacts the accuracy and efficiency of their work, but existing systems have lacked sufficient support that takes this emotional state into account. Therefore, there is a need for a system that can reduce work errors and provide appropriate feedback tailored to the worker's emotional state.

[0390] 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.

[0391] In this invention, the server includes means for acquiring log information, means for analyzing the log information using natural language processing technology, means for comparing the analysis results with standard process procedures and detecting inconsistencies, and means for recognizing the emotional state of the worker. This makes it possible to reduce work errors and improve work efficiency by providing feedback that corresponds to the worker's mental state.

[0392] "Log information" refers to data that records user operations and actions.

[0393] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0394] "Standard process procedures" refer to a set of procedures or methods that serve as the standard for carrying out work.

[0395] "Inconsistency" refers to a state that indicates a discrepancy or contradiction between the analysis results and the standard process procedure.

[0396] "Feedback" refers to a response or reaction to given information or instructions.

[0397] "Analysis accuracy" is an indicator that shows the accuracy and detail of the data analysis results.

[0398] "Emotional state" refers to the psychological or emotional state that a user exhibits at a specific point in time.

[0399] "Diverse data" refers to data obtained from multiple sources that have different formats and content.

[0400] The system implementing this invention is intended for work supervision at construction sites, monitoring the work processes of on-site workers in real time and providing feedback to reduce work errors. The system uses smartphones or smart glasses to acquire and analyze worker operation logs and voice data.

[0401] The server analyzes the acquired log information using a natural language processing engine and detects inconsistencies by comparing the results with standard process procedures. If an inconsistency is detected, the server generates appropriate feedback, taking into account the worker's emotional state, and displays it on the terminal. The feedback is adjusted to alleviate the worker's emotional state and recommend a retry.

[0402] The system's specific configuration uses Python and TensorFlow for natural language processing and emotion recognition, and Flask for server-side processing. The user interface is built with React and optimized for smartphones and smart glasses. For emotion recognition, a model based on diverse data is used to analyze emotions in real time from the worker's voice data.

[0403] For example, if a worker makes an incorrect connection while following a complex blueprint, they will receive real-time feedback, such as "Calm down, take a deep breath, and check the correct procedure." In this way, the system allows for highly accurate work while taking into consideration the emotional state of the worker.

[0404] An example of a prompt for a generative AI model might be: "Please tell me specifically how to automatically detect errors in construction site work procedures and provide optimal real-time feedback based on the emotional state of the workers."

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The terminal collects field workers' operations and voice data in real time and records it as log information. This input log information includes a process of converting work procedures and voice data into a digital format. This enables accuracy of operations and recognition of emotions from voice.

[0408] Step 2:

[0409] The terminal sends recorded log information to the server. The input here consists of digitized operation logs and audio data, which the server receives and prepares to proceed to the next analysis step.

[0410] Step 3:

[0411] The server analyzes the acquired log information using natural language processing techniques. In this process, the log information is compared against standard procedure data. The input is operation log data, and the output is the presence or absence of inconsistencies for each log. Specifically, it checks how closely the operation procedure matches the standard.

[0412] Step 4:

[0413] The server processes the voice data into an emotion recognition engine to analyze the worker's emotional state. The input for this step is voice data, and the output is an emotional state (e.g., stress, anxiety, calmness, etc.). Voice pattern analysis is performed at this stage.

[0414] Step 5:

[0415] The server generates feedback based on the analysis results and emotional state. In this step, the input is inconsistent information and emotional state, and the output is a tailored feedback message. Specific actions include sending messages to promote relaxation and determining effective guidance content.

[0416] Step 6:

[0417] The terminal displays the generated feedback to the worker. The input is a feedback message, and the expected output is the worker's response. Specifically, the terminal displays the message on its screen.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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".

[0434] This invention is a system for automating work verification, aiming to improve the quality and efficiency of equipment setup work in support desks and customer service departments. The system consists primarily of acquiring log data, analyzing it using natural language processing, comparing it with standard operating procedures, detecting inconsistencies, providing feedback, and continuously improving the accuracy of the analysis.

[0435] Retrieving log data

[0436] The terminal records all user operations during device configuration as real-time log data. This includes timestamped execution commands and entered configuration values.

[0437] Analysis and Inconsistency Detection

[0438] The server receives log data sent from the terminal and analyzes it using natural language processing technology. This analysis helps understand the meaning and relationships of the operations and compares the collected data with standard operating procedures. This makes it possible to identify inconsistencies and potential errors.

[0439] Provide feedback

[0440] The server provides users with real-time feedback generated based on the analysis results. This feedback includes specific problem areas and areas requiring correction, providing useful information for users to take quick action.

[0441] Continuous learning

[0442] The server stores the correction results after user feedback and uses them to improve the analysis algorithm. This improves the accuracy of subsequent analyses and enhances the overall system performance.

[0443] Specific example

[0444] For example, suppose a user enters the wrong IP address when configuring a network device. In this case, the terminal records this operation as log data, and the server analyzes it. If the analysis reveals that the entered IP address does not match the standard operating procedure, the server provides feedback to the user saying, "The IP address format is invalid. Please re-enter it in the correct format." The user can then review this and quickly correct the error.

[0445] Thus, embodiments of the present invention provide specific and practical methods for improving the accuracy and efficiency of work.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] The terminal begins recording log data simultaneously with the start of the device configuration process. The log data includes detailed information such as the timestamp of each operation, input values, and executed commands.

[0449] Step 2:

[0450] The terminal sends recorded log data to the server in real time. This transmission is carried out through security protocols to ensure safety.

[0451] Step 3:

[0452] The server feeds the received log data into a natural language processing engine and begins analysis. Specifically, it performs text analysis on the log content and extracts important keywords and the meaning of operations.

[0453] Step 4:

[0454] The server compares the analysis results with standard operating procedures to identify inconsistencies and potential errors. In this process, a rule-based algorithm is used for pattern matching to detect deviations from the standard.

[0455] Step 5:

[0456] The server generates a feedback message based on the detection of inconsistencies. This feedback includes the specific location of the problem, its cause, and recommended corrective actions.

[0457] Step 6:

[0458] The server sends the generated feedback message to the user. The user can then review this feedback and correct their work according to the instructions.

[0459] Step 7:

[0460] The server collects user-modified log data and stores it in storage as training data. This data is then sequentially analyzed by machine learning algorithms to aid in subsequent analyses.

[0461] (Example 1)

[0462] 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."

[0463] In system operations and configuration tasks performed by users, it is necessary to quickly and effectively detect problems when incorrect operations or incompatible settings occur and provide users with appropriate corrective instructions in real time. However, existing systems lack sufficient mechanisms to automatically verify the accuracy of work and provide feedback, making it difficult to improve work efficiency and accuracy.

[0464] 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.

[0465] In this invention, the server includes means for transmitting information about an operation to an analysis device, means for analyzing the information about the operation in the analysis device using natural language processing technology and identifying inconsistencies by comparing it with a standard operation plan, and means for providing instructions to the user based on the inconsistencies. This makes it possible to quickly detect non-conformist operations performed by the user and provide appropriate corrective instructions in real time.

[0466] "Information regarding operations" refers to data that records all operations and settings performed by the user.

[0467] An "analysis device" is a device that processes information about received operations and compares it with a standard operation plan.

[0468] "Natural language processing technology" is a technology that semantically analyzes information related to operations and understands its content.

[0469] A "standard operating plan" is reference information that outlines predetermined, precise operating procedures and setting criteria.

[0470] "Inconsistency" refers to elements or errors in the information regarding an operation that do not match the standard operation plan.

[0471] "Providing instructions to users" refers to the process of providing specific guidance so that users can quickly correct any inconsistencies that are detected.

[0472] "Learning" refers to the process of accumulating user responses and correction results to improve the accuracy of future analyses.

[0473] This invention is an automated system that improves the accuracy and efficiency of equipment configuration tasks performed by users. The system mainly consists of two components: a terminal and a server.

[0474] The terminal records information about the user's operations in real time as they configure the device. This information includes, for example, the configuration parameters entered by the user and the commands executed, and is recorded with precise timestamps. The terminal also has the ability to send this data to the server in batch processing or at appropriate times.

[0475] The server analyzes information about received operations using advanced natural language processing techniques. This analysis helps understand the meaning of the operations and identify inconsistencies by comparing them with standard operation plans. The software technologies used include advanced natural language processing frameworks and data analysis algorithms. If an inconsistency is found, the server immediately generates instructions based on the inconsistency and provides them to the user via the terminal. These instructions specifically provide the information necessary to effectively correct the operational error.

[0476] As a concrete example, consider a scenario where a user configures the IP address of a new network device. The terminal records the user's input and sends that data to the server. The server analyzes the data, and if it detects that the entered IP address is incorrect, it provides the user with a message such as, "The IP address format is invalid. Please re-enter it in the correct format."

[0477] The following are some possible examples of prompt statements.

[0478] "Please create a feedback message to be displayed when an incorrect IP address is entered during network device configuration."

[0479] This invention aims to significantly improve the accuracy and efficiency of user-performed equipment setup tasks by automatically monitoring the process and providing real-time problem identification and instructions.

[0480] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0481] Step 1:

[0482] The terminal monitors all configuration operations performed by the user in real time and records information about those operations. Specifically, it adds a timestamp to the commands and configuration values ​​entered by the user and saves them as logs. The input includes the user's operation data, and the output is a log file containing this data.

[0483] Step 2:

[0484] The terminal sends the operation information recorded in the log to the server in batches at regular intervals. This operation involves splitting the recorded log file into packets and transferring them to the server via a secure communication protocol. The input is the operation log file, and the output is the data packets transferred to the server.

[0485] Step 3:

[0486] The server analyzes the operation information received from the terminal using natural language processing technology. The specific analysis involves tokenization and syntax analysis to extract meaning from the log data. The input is the log data sent from the terminal, and the output is the analyzed semantic information.

[0487] Step 4:

[0488] The server compares the standard operation plan and operational information based on the analysis to identify inconsistencies. Specifically, it uses a rule-based comparison algorithm to identify items that do not conform to the specified procedure. The inputs are the analyzed information and the standard operation plan, and the output is a list of identified inconsistencies.

[0489] Step 5:

[0490] The server generates instructions based on inconsistencies and provides them to the user in real time via the terminal. Specifically, its actions include creating proposed corrections based on the inconsistencies and sending these proposals to the user in an easily understandable message format. The input is a list of inconsistencies, and the output is a feedback message to the user.

[0491] Step 6:

[0492] The user corrects the error according to the instructions received and reconfigures the settings. This correction is again logged as operation information and sent to the server for subsequent learning processes. The input is a feedback message from the server, and the output is the generated corrected log information.

[0493] (Application Example 1)

[0494] 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."

[0495] There is a need to improve work efficiency while maintaining accuracy in setting up and adjusting equipment in factories. In particular, there is a lack of effective methods for immediately detecting and correcting setting errors that occur during manual setup. Furthermore, there is a challenge in providing an environment where workers can receive immediate feedback.

[0496] 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.

[0497] In this invention, the server includes means for acquiring log data, means for analyzing it using natural language processing technology, means for comparing the analysis results with standard operating procedures and detecting inconsistencies, and means for evaluating the accuracy of operations by physical devices in real time and presenting the results through a visual display device. This makes it possible to immediately detect misconfigurations during equipment setup work in a factory and provide rapid feedback to the worker to encourage correction.

[0498] "Log data" refers to a collection of data that records user operations during equipment configuration. Specifically, it includes information such as executed commands and entered configuration values, each with a timestamp.

[0499] "Natural language processing technology" is a part of computer science that analyzes the meaning and relationships of collected text data and organizes the information in a way that humans can understand.

[0500] "Means for detecting inconsistencies" refers to methods or devices for identifying errors or deviations from regulations by comparing analyzed work logs with standard operating procedures.

[0501] "Means of providing feedback" refers to a method or apparatus for notifying the user of specific problems and areas for correction based on detected inconsistencies, thereby facilitating the correction of work.

[0502] A "visual display device" is a device that displays analysis results and feedback information in a way that humans can visually understand, and this includes head-mounted displays and smart glasses.

[0503] This embodiment of the invention is a robot operation support system for a factory environment where equipment setup work is performed. The system consists of a terminal, a server, and a visual display device equipped with a user interface. Specifically, the following processes are performed.

[0504] The terminal records all operations during the device setup process as log data in real time, including executed commands and input settings as timestamps.

[0505] The server receives this log data and analyzes it using natural language processing techniques. In this analysis, specific natural language processing tools, such as spaCy or Google Cloud's natural language API, are used to understand the meaning and relationships of the operations. In this step, the analysis results are compared with standard operating procedures to detect inconsistencies and potential errors.

[0506] Based on the inconsistencies detected by the server, the feedback provided to the user includes information about specific problem areas and areas requiring correction. This information is transmitted to the user in real time through visual display devices, such as smart glasses or head-mounted displays, enabling the user to take immediate action.

[0507] The analysis results and user modification history are stored on the server and used to improve the analysis algorithm, enabling continuous learning and improving the accuracy of subsequent analyses.

[0508] For example, if a welding robot starts work with an incorrect temperature setting, the server provides feedback to the operator via a visual display, such as "The temperature setting is lower than standard. Please correct it to the specified temperature," enabling a quick response. This process can also be performed using a prompt message to a generative AI model, such as "Please check and provide feedback whether the robot is using the correct temperature setting for the current welding process."

[0509] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0510] Step 1:

[0511] The terminal records all operations as real-time log data when a user begins configuring the device. Input consists of the user's operation commands and configuration values, which are stored with timestamps. Output is log data that continuously updates with records of the configuration operations. In practice, the terminal monitors the configuration process and collects data at predetermined intervals.

[0512] Step 2:

[0513] The server receives log data sent from the terminal. The input is sequential log data from the terminal, and the output is a formatted dataset. The server aggregates the data and performs operations to prepare it for analysis.

[0514] Step 3:

[0515] The server analyzes pre-processed log data using natural language processing techniques. The input is a formatted dataset, and the output generates information analyzing the meaning and relationships of each operation. In this step, spaCy and the Google Cloud Natural Language API are used to extract linguistic features from the data.

[0516] Step 4:

[0517] The server compares the analysis results with standard operating procedures to detect inconsistencies. The input consists of the information obtained through analysis and existing standard operating procedures; the output is a list of inconsistencies. The server performs calculations and comparisons to extract the parts that do not match.

[0518] Step 5:

[0519] The server provides feedback to the user based on inconsistencies. The input is a list of inconsistencies, and the output is feedback highlighting the points that need correction. Visual displays are used to notify the user of this information in real time.

[0520] Step 6:

[0521] The user quickly corrects the device settings based on the feedback. The input is feedback information from a visual display, and the output is the correctly corrected settings. The user then performs the correction action based on the presented information.

[0522] Step 7:

[0523] The server stores feedback and its results as training data and uses it to improve the analysis algorithm. The input is the corrected feedback information, and the output is an improved algorithm for better accuracy in the next analysis. The server saves the information in a database and performs actions to update the algorithm using machine learning techniques. This process is optimized using prompts to the generative AI model such as, "The robot should check and provide feedback on whether it is using the correct temperature settings in the current welding process."

[0524] 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.

[0525] This invention is a system designed to more efficiently scrutinize user equipment setup procedures and reduce human error. The system combines log data collection, natural language processing analysis, comparison with standard operating procedures, inconsistency detection, user feedback, and a learning function to improve analysis accuracy, in addition to an emotion engine that recognizes user emotions.

[0526] Log data acquisition and analysis

[0527] The terminal logs all device configuration operations performed by the user and sends them to the server. The server analyzes the received log data using a natural language processing engine to understand its meaning. The analysis is then compared to standard operating procedures, and any inconsistencies are detected.

[0528] Emotion recognition by an emotion engine

[0529] The device collects the user's voice and text data and sends it to the server's emotion engine. The emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, confusion, satisfaction, etc.).

[0530] Provide feedback

[0531] The server generates feedback based on the analysis results of inconsistencies and the recognition results of the emotion engine. The feedback content is adjusted according to the user's emotional state and delivered at the optimal time and in the appropriate manner. If the user is stressed, gentle, step-by-step guidance can be provided; if the user is calm, efficient methods can be recommended.

[0532] Learning and accuracy improvement

[0533] The server accumulates user feedback as training data and uses it to improve the accuracy of its analysis. By also learning from emotional data, the server's ability to provide feedback that is more tailored to the user's emotions improves.

[0534] Specific example

[0535] For example, suppose a user enters incorrect parameters when configuring network settings. However, if the user is feeling stressed or anxious, the server will not only correct the error but also provide reassuring feedback such as, "It's okay, stay calm and try again." This kind of emotionally sensitive support allows users to complete tasks more smoothly.

[0536] This system simultaneously automates technical scrutiny and improves the user experience, leading to significant improvements in operational efficiency.

[0537] The following describes the processing flow.

[0538] Step 1:

[0539] The terminal records all operations as log data from the moment the user begins configuring the device. The log details the commands entered and the settings changed, along with timestamps.

[0540] Step 2:

[0541] The terminal sends log data to the server in real time. A secure communication protocol is used to ensure the data's safety.

[0542] Step 3:

[0543] The server passes the received log data to the natural language processing engine and begins analysis. The analysis involves extracting specific keywords from the text content and performing contextual analysis to understand the intent behind the operations.

[0544] Step 4:

[0545] The device collects emotional data from the user's voice and text and sends it to the server.

[0546] Step 5:

[0547] The server uses an emotion engine to analyze the user's emotions. Specifically, it recognizes emotions such as stress, confusion, and satisfaction from the tone of voice and the content of the text.

[0548] Step 6:

[0549] The server detects inconsistencies by comparing the analysis results of log data and sentiment data with standard operating procedures. These analysis results, including the inconsistencies, are then compiled as feedback data.

[0550] Step 7:

[0551] The server adjusts the generated feedback based on the user's emotions. For example, if the user is stressed, it provides gentle, step-by-step instructions; if the user is relaxed, it suggests efficient methods.

[0552] Step 8:

[0553] The server sends the adjusted feedback to the user. The user receives this feedback, reviews their work, and makes corrections as needed.

[0554] Step 9:

[0555] The server records the results after user modifications and stores them in the system as training data. This helps improve the accuracy of future analyses and feedback.

[0556] (Example 2)

[0557] 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."

[0558] When users configure systems and equipment, problems can occur due to operational errors or incorrect input, leading to decreased work efficiency. Furthermore, a lack of accurate understanding of the user's emotions during operation can result in inadequate feedback, adding to their stress. Therefore, it is necessary to refine the configuration process, reduce human error through feedback that takes user emotions into account, and improve both work efficiency and user experience.

[0559] 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.

[0560] In this invention, the server includes means for acquiring log data, means for analyzing the log data using natural language processing technology, means for comparing the analysis results with standard operating procedures and detecting inconsistencies, means for recognizing the user's emotional state from their voice or text, means for providing feedback to the user based on the inconsistencies and emotional recognition, and means for improving the accuracy of the analysis by learning the feedback results and emotional data. This makes it possible to immediately detect user errors and provide appropriate feedback, thereby reducing user stress and enabling efficient operation.

[0561] "Log data" refers to data that records the details of equipment settings and operations performed by a user, and includes timestamps and details of the operations performed.

[0562] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes methods for converting text content into structured data.

[0563] A "standard operating procedure" is a set of predetermined procedures and standards for performing a specific task, serving as a guideline to ensure consistency and accuracy in operations.

[0564] "Inconsistency" refers to parts of the analyzed data that deviate from standard operating procedures, indicating errors or mistakes that occur during setup or operation.

[0565] "Feedback" refers to information and advice provided based on the user's actions and emotional state, and is a response that helps the user improve or adjust their next actions.

[0566] "Emotional state" refers to the psychological and emotional state a user is in while using the system, and includes a variety of emotions such as stress, confusion, and satisfaction.

[0567] "Learning" is the process by which a system continuously improves the accuracy of its analysis and feedback based on feedback results and sentiment data.

[0568] This invention is a system designed to streamline the user's equipment setup process and reduce human error. Specifically, it combines log data collection, natural language processing analysis, comparison with standard operating procedures, inconsistency detection, user feedback provision, a learning function aimed at improving analysis accuracy, and an emotion engine that recognizes the user's emotions.

[0569] The device includes hardware and software to record all user actions in real time and generate log data. Specifically, it captures keyboard input and screen operations using sensors and tracking software. The collected log data is sent to a server at regular intervals.

[0570] The server is equipped with a natural language processing engine for processing received log data. This engine uses natural language processing technologies (e.g., SpaCy and NLTK) to analyze the log content and understand the meaning of the operations performed. The results are compared with standard operating procedures, and if inconsistencies are detected, preparations for the next step are made.

[0571] The device also acquires voice and text messages entered by the user and sends them to the server's emotion engine as emotion data. The emotion engine recognizes the user's emotional state from the collected data and identifies states such as stress and confusion.

[0572] Based on the analysis results and emotion recognition results, the server generates optimal feedback. This feedback is adjusted according to the user's psychological state, so, for example, a user who is feeling anxious will receive content that promotes calmness. This feedback is communicated to the user through screen display and audio output.

[0573] Furthermore, the server accumulates feedback results and user sentiment data as training data, which is used to continuously improve the accuracy of the analysis. This uses a generative AI model to improve the accuracy and adaptability of the feedback.

[0574] As a concrete example, consider a situation where a user is configuring network settings and has entered incorrect parameters. If the user is feeling stressed, the system might provide feedback such as, "It's okay, please stay calm and try again." This kind of empathetic response allows the user to continue working smoothly.

[0575] An example of a prompt message could be, "Please suggest ways for users to provide feedback if they experience stress during the setup process."

[0576] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0577] Step 1:

[0578] The terminal monitors the user's device configuration operations in real time and records the input as log data. Specifically, it captures user interactions such as mouse clicks, keyboard input, and screen touches using sensors and tracking software. This log data includes a timestamp corresponding to the operation and the details of the operation, which are used in subsequent analysis processes.

[0579] Step 2:

[0580] The terminal processes the recorded log data in batches at regular intervals and sends it to the server. The server receives this log data as input to a natural language processing engine and performs analysis. As part of the data processing, natural language processing techniques are used to semantically analyze the log data and extract the user's intentions and actions. The analyzed data is compared with pre-configured standard operating procedures, and any inconsistencies are output.

[0581] Step 3:

[0582] The terminal acquires the user's voice input and text messages and sends them to the server as emotion data. This data is processed using voice analysis software and text analysis tools. The server's emotion engine performs data calculations based on this data to identify the user's emotional state. Specifically, it analyzes the characteristics of the voice tone and extracts emotion-related keywords from the text. This results in the output of the user's emotional state (e.g., stress, confusion, satisfaction).

[0583] Step 4:

[0584] The server receives the analyzed inconsistent data and emotion recognition results as input and generates optimal feedback. Using a generative AI model, the feedback is adjusted to match the user's current emotional state. For example, if the user is feeling anxious, the feedback might be a gentle instruction such as, "It's okay, calm down and try again." This feedback is provided to the user as a text message or voice output.

[0585] Step 5:

[0586] The server accumulates feedback results and user sentiment data, using it as training data to improve analysis accuracy. During this training process, the dataset is continuously updated. Based on this data, the generative AI model improves the accuracy of feedback, enabling new character recognition and more accurate sentiment responses. In this way, the overall operational efficiency and user experience of the system are continuously improved.

[0587] (Application Example 2)

[0588] 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."

[0589] In on-site work, it is crucial for workers to follow precise procedures, but human errors are more likely to occur in complex tasks or when many people are involved. Furthermore, a worker's mental state significantly impacts the accuracy and efficiency of their work, but existing systems have lacked sufficient support that takes this emotional state into account. Therefore, there is a need for a system that can reduce work errors and provide appropriate feedback tailored to the worker's emotional state.

[0590] 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.

[0591] In this invention, the server includes means for acquiring log information, means for analyzing the log information using natural language processing technology, means for comparing the analysis results with standard process procedures and detecting inconsistencies, and means for recognizing the emotional state of the worker. This makes it possible to reduce work errors and improve work efficiency by providing feedback that corresponds to the worker's mental state.

[0592] "Log information" refers to data that records user operations and actions.

[0593] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0594] "Standard process procedures" refer to a set of procedures or methods that serve as the standard for carrying out work.

[0595] "Inconsistency" refers to a state that indicates a discrepancy or contradiction between the analysis results and the standard process procedure.

[0596] "Feedback" refers to a response or reaction to given information or instructions.

[0597] "Analysis accuracy" is an indicator that shows the accuracy and detail of the data analysis results.

[0598] "Emotional state" refers to the psychological or emotional state that a user exhibits at a specific point in time.

[0599] "Diverse data" refers to data obtained from multiple sources that have different formats and content.

[0600] The system implementing this invention is intended for work supervision at construction sites, monitoring the work processes of on-site workers in real time and providing feedback to reduce work errors. The system uses smartphones or smart glasses to acquire and analyze worker operation logs and voice data.

[0601] The server analyzes the acquired log information using a natural language processing engine and detects inconsistencies by comparing the results with standard process procedures. If an inconsistency is detected, the server generates appropriate feedback, taking into account the worker's emotional state, and displays it on the terminal. The feedback is adjusted to alleviate the worker's emotional state and recommend a retry.

[0602] The system's specific configuration uses Python and TensorFlow for natural language processing and emotion recognition, and Flask for server-side processing. The user interface is built with React and optimized for smartphones and smart glasses. For emotion recognition, a model based on diverse data is used to analyze emotions in real time from the worker's voice data.

[0603] For example, if a worker makes an incorrect connection while following a complex blueprint, they will receive real-time feedback, such as "Calm down, take a deep breath, and check the correct procedure." In this way, the system allows for highly accurate work while taking into consideration the emotional state of the worker.

[0604] An example of a prompt for a generative AI model might be: "Please tell me specifically how to automatically detect errors in construction site work procedures and provide optimal real-time feedback based on the emotional state of the workers."

[0605] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0606] Step 1:

[0607] The terminal collects field workers' operations and voice data in real time and records it as log information. This input log information includes a process of converting work procedures and voice data into a digital format. This enables accuracy of operations and recognition of emotions from voice.

[0608] Step 2:

[0609] The terminal sends recorded log information to the server. The input here consists of digitized operation logs and audio data, which the server receives and prepares to proceed to the next analysis step.

[0610] Step 3:

[0611] The server analyzes the acquired log information using natural language processing techniques. In this process, the log information is compared against standard procedure data. The input is operation log data, and the output is the presence or absence of inconsistencies for each log. Specifically, it checks how closely the operation procedure matches the standard.

[0612] Step 4:

[0613] The server processes the voice data into an emotion recognition engine to analyze the worker's emotional state. The input for this step is voice data, and the output is an emotional state (e.g., stress, anxiety, calmness, etc.). Voice pattern analysis is performed at this stage.

[0614] Step 5:

[0615] The server generates feedback based on the analysis results and emotional state. In this step, the input is inconsistent information and emotional state, and the output is a tailored feedback message. Specific actions include sending messages to promote relaxation and determining effective guidance content.

[0616] Step 6:

[0617] The terminal displays the generated feedback to the worker. The input is a feedback message, and the expected output is the worker's response. Specifically, the terminal displays the message on its screen.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] [Fourth Embodiment]

[0622] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0623] 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.

[0624] 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).

[0625] 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.

[0626] 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.

[0627] 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).

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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".

[0635] This invention is a system for automating work verification, aiming to improve the quality and efficiency of equipment setup work in support desks and customer service departments. The system consists primarily of acquiring log data, analyzing it using natural language processing, comparing it with standard operating procedures, detecting inconsistencies, providing feedback, and continuously improving the accuracy of the analysis.

[0636] Retrieving log data

[0637] The terminal records all user operations during device configuration as real-time log data. This includes timestamped execution commands and entered configuration values.

[0638] Analysis and Inconsistency Detection

[0639] The server receives log data sent from the terminal and analyzes it using natural language processing technology. This analysis helps understand the meaning and relationships of the operations and compares the collected data with standard operating procedures. This makes it possible to identify inconsistencies and potential errors.

[0640] Provide feedback

[0641] The server provides users with real-time feedback generated based on the analysis results. This feedback includes specific problem areas and areas requiring correction, providing useful information for users to take quick action.

[0642] Continuous learning

[0643] The server stores the correction results after user feedback and uses them to improve the analysis algorithm. This improves the accuracy of subsequent analyses and enhances the overall system performance.

[0644] Specific example

[0645] For example, suppose a user enters the wrong IP address when configuring a network device. In this case, the terminal records this operation as log data, and the server analyzes it. If the analysis reveals that the entered IP address does not match the standard operating procedure, the server provides feedback to the user saying, "The IP address format is invalid. Please re-enter it in the correct format." The user can then review this and quickly correct the error.

[0646] Thus, embodiments of the present invention provide specific and practical methods for improving the accuracy and efficiency of work.

[0647] The following describes the processing flow.

[0648] Step 1:

[0649] The terminal begins recording log data simultaneously with the start of the device configuration process. The log data includes detailed information such as the timestamp of each operation, input values, and executed commands.

[0650] Step 2:

[0651] The terminal sends recorded log data to the server in real time. This transmission is carried out through security protocols to ensure safety.

[0652] Step 3:

[0653] The server feeds the received log data into a natural language processing engine and begins analysis. Specifically, it performs text analysis on the log content and extracts important keywords and the meaning of operations.

[0654] Step 4:

[0655] The server compares the analysis results with standard operating procedures to identify inconsistencies and potential errors. In this process, a rule-based algorithm is used for pattern matching to detect deviations from the standard.

[0656] Step 5:

[0657] The server generates a feedback message based on the detection of inconsistencies. This feedback includes the specific location of the problem, its cause, and recommended corrective actions.

[0658] Step 6:

[0659] The server sends the generated feedback message to the user. The user can then review this feedback and correct their work according to the instructions.

[0660] Step 7:

[0661] The server collects user-modified log data and stores it in storage as training data. This data is then sequentially analyzed by machine learning algorithms to aid in subsequent analyses.

[0662] (Example 1)

[0663] 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".

[0664] In system operations and configuration tasks performed by users, it is necessary to quickly and effectively detect problems when incorrect operations or incompatible settings occur and provide users with appropriate corrective instructions in real time. However, existing systems lack sufficient mechanisms to automatically verify the accuracy of work and provide feedback, making it difficult to improve work efficiency and accuracy.

[0665] 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.

[0666] In this invention, the server includes means for transmitting information about an operation to an analysis device, means for analyzing the information about the operation in the analysis device using natural language processing technology and identifying inconsistencies by comparing it with a standard operation plan, and means for providing instructions to the user based on the inconsistencies. This makes it possible to quickly detect non-conformist operations performed by the user and provide appropriate corrective instructions in real time.

[0667] "Information regarding operations" refers to data that records all operations and settings performed by the user.

[0668] An "analysis device" is a device that processes information about received operations and compares it with a standard operation plan.

[0669] "Natural language processing technology" is a technology that semantically analyzes information related to operations and understands its content.

[0670] A "standard operating plan" is reference information that outlines predetermined, precise operating procedures and setting criteria.

[0671] "Inconsistency" refers to elements or errors in the information regarding an operation that do not match the standard operation plan.

[0672] "Providing instructions to users" refers to the process of providing specific guidance so that users can quickly correct any inconsistencies that are detected.

[0673] "Learning" refers to the process of accumulating user responses and correction results to improve the accuracy of future analyses.

[0674] This invention is an automated system that improves the accuracy and efficiency of equipment configuration tasks performed by users. The system mainly consists of two components: a terminal and a server.

[0675] The terminal records information about the user's operations in real time as they configure the device. This information includes, for example, the configuration parameters entered by the user and the commands executed, and is recorded with precise timestamps. The terminal also has the ability to send this data to the server in batch processing or at appropriate times.

[0676] The server analyzes information about received operations using advanced natural language processing techniques. This analysis helps understand the meaning of the operations and identify inconsistencies by comparing them with standard operation plans. The software technologies used include advanced natural language processing frameworks and data analysis algorithms. If an inconsistency is found, the server immediately generates instructions based on the inconsistency and provides them to the user via the terminal. These instructions specifically provide the information necessary to effectively correct the operational error.

[0677] As a concrete example, consider a scenario where a user configures the IP address of a new network device. The terminal records the user's input and sends that data to the server. The server analyzes the data, and if it detects that the entered IP address is incorrect, it provides the user with a message such as, "The IP address format is invalid. Please re-enter it in the correct format."

[0678] The following are some possible examples of prompt statements.

[0679] "Please create a feedback message to be displayed when an incorrect IP address is entered during network device configuration."

[0680] This invention aims to significantly improve the accuracy and efficiency of user-performed equipment setup tasks by automatically monitoring the process and providing real-time problem identification and instructions.

[0681] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0682] Step 1:

[0683] The terminal monitors all configuration operations performed by the user in real time and records information about those operations. Specifically, it adds a timestamp to the commands and configuration values ​​entered by the user and saves them as logs. The input includes the user's operation data, and the output is a log file containing this data.

[0684] Step 2:

[0685] The terminal sends the operation information recorded in the log to the server in batches at regular intervals. This operation involves splitting the recorded log file into packets and transferring them to the server via a secure communication protocol. The input is the operation log file, and the output is the data packets transferred to the server.

[0686] Step 3:

[0687] The server analyzes the operation information received from the terminal using natural language processing technology. The specific analysis involves tokenization and syntax analysis to extract meaning from the log data. The input is the log data sent from the terminal, and the output is the analyzed semantic information.

[0688] Step 4:

[0689] The server compares the standard operation plan and operational information based on the analysis to identify inconsistencies. Specifically, it uses a rule-based comparison algorithm to identify items that do not conform to the specified procedure. The inputs are the analyzed information and the standard operation plan, and the output is a list of identified inconsistencies.

[0690] Step 5:

[0691] The server generates instructions based on inconsistencies and provides them to the user in real time via the terminal. Specifically, its actions include creating proposed corrections based on the inconsistencies and sending these proposals to the user in an easily understandable message format. The input is a list of inconsistencies, and the output is a feedback message to the user.

[0692] Step 6:

[0693] The user corrects the error according to the instructions received and reconfigures the settings. This correction is again logged as operation information and sent to the server for subsequent learning processes. The input is a feedback message from the server, and the output is the generated corrected log information.

[0694] (Application Example 1)

[0695] 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".

[0696] There is a need to improve work efficiency while maintaining accuracy in setting up and adjusting equipment in factories. In particular, there is a lack of effective methods for immediately detecting and correcting setting errors that occur during manual setup. Furthermore, there is a challenge in providing an environment where workers can receive immediate feedback.

[0697] 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.

[0698] In this invention, the server includes means for acquiring log data, means for analyzing it using natural language processing technology, means for comparing the analysis results with standard operating procedures and detecting inconsistencies, and means for evaluating the accuracy of operations by physical devices in real time and presenting the results through a visual display device. This makes it possible to immediately detect misconfigurations during equipment setup work in a factory and provide rapid feedback to the worker to encourage correction.

[0699] "Log data" refers to a collection of data that records user operations during equipment configuration. Specifically, it includes information such as executed commands and entered configuration values, each with a timestamp.

[0700] "Natural language processing technology" is a part of computer science that analyzes the meaning and relationships of collected text data and organizes the information in a way that humans can understand.

[0701] "Means for detecting inconsistencies" refers to methods or devices for identifying errors or deviations from regulations by comparing analyzed work logs with standard operating procedures.

[0702] "Means of providing feedback" refers to a method or apparatus for notifying the user of specific problems and areas for correction based on detected inconsistencies, thereby facilitating the correction of work.

[0703] A "visual display device" is a device that displays analysis results and feedback information in a way that humans can visually understand, and this includes head-mounted displays and smart glasses.

[0704] This embodiment of the invention is a robot operation support system for a factory environment where equipment setup work is performed. The system consists of a terminal, a server, and a visual display device equipped with a user interface. Specifically, the following processes are performed.

[0705] The terminal records all operations during the device setup process as log data in real time, including executed commands and input settings as timestamps.

[0706] The server receives this log data and analyzes it using natural language processing techniques. In this analysis, specific natural language processing tools, such as spaCy or Google Cloud's natural language API, are used to understand the meaning and relationships of the operations. In this step, the analysis results are compared with standard operating procedures to detect inconsistencies and potential errors.

[0707] Based on the inconsistencies detected by the server, the feedback provided to the user includes information about specific problem areas and areas requiring correction. This information is transmitted to the user in real time through visual display devices, such as smart glasses or head-mounted displays, enabling the user to take immediate action.

[0708] The analysis results and user modification history are stored on the server and used to improve the analysis algorithm, enabling continuous learning and improving the accuracy of subsequent analyses.

[0709] For example, if a welding robot starts work with an incorrect temperature setting, the server provides feedback to the operator via a visual display, such as "The temperature setting is lower than standard. Please correct it to the specified temperature," enabling a quick response. This process can also be performed using a prompt message to a generative AI model, such as "Please check and provide feedback whether the robot is using the correct temperature setting for the current welding process."

[0710] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0711] Step 1:

[0712] The terminal records all operations as real-time log data when a user begins configuring the device. Input consists of the user's operation commands and configuration values, which are stored with timestamps. Output is log data that continuously updates with records of the configuration operations. In practice, the terminal monitors the configuration process and collects data at predetermined intervals.

[0713] Step 2:

[0714] The server receives log data sent from the terminal. The input is sequential log data from the terminal, and the output is a formatted dataset. The server aggregates the data and performs operations to prepare it for analysis.

[0715] Step 3:

[0716] The server analyzes pre-processed log data using natural language processing techniques. The input is a formatted dataset, and the output generates information analyzing the meaning and relationships of each operation. In this step, spaCy and the Google Cloud Natural Language API are used to extract linguistic features from the data.

[0717] Step 4:

[0718] The server compares the analysis results with standard operating procedures to detect inconsistencies. The input consists of the information obtained through analysis and existing standard operating procedures; the output is a list of inconsistencies. The server performs calculations and comparisons to extract the parts that do not match.

[0719] Step 5:

[0720] The server provides feedback to the user based on inconsistencies. The input is a list of inconsistencies, and the output is feedback highlighting the points that need correction. Visual displays are used to notify the user of this information in real time.

[0721] Step 6:

[0722] The user quickly corrects the device settings based on the feedback. The input is feedback information from a visual display, and the output is the correctly corrected settings. The user then performs the correction action based on the presented information.

[0723] Step 7:

[0724] The server stores feedback and its results as training data and uses it to improve the analysis algorithm. The input is the corrected feedback information, and the output is an improved algorithm for better accuracy in the next analysis. The server saves the information in a database and performs actions to update the algorithm using machine learning techniques. This process is optimized using prompts to the generative AI model such as, "The robot should check and provide feedback on whether it is using the correct temperature settings in the current welding process."

[0725] 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.

[0726] This invention is a system designed to more efficiently scrutinize user equipment setup procedures and reduce human error. The system combines log data collection, natural language processing analysis, comparison with standard operating procedures, inconsistency detection, user feedback, and a learning function to improve analysis accuracy, in addition to an emotion engine that recognizes user emotions.

[0727] Log data acquisition and analysis

[0728] The terminal logs all device configuration operations performed by the user and sends them to the server. The server analyzes the received log data using a natural language processing engine to understand its meaning. The analysis is then compared to standard operating procedures, and any inconsistencies are detected.

[0729] Emotion recognition by an emotion engine

[0730] The device collects the user's voice and text data and sends it to the server's emotion engine. The emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, confusion, satisfaction, etc.).

[0731] Provide feedback

[0732] The server generates feedback based on the analysis results of inconsistencies and the recognition results of the emotion engine. The feedback content is adjusted according to the user's emotional state and delivered at the optimal time and in the appropriate manner. If the user is stressed, gentle, step-by-step guidance can be provided; if the user is calm, efficient methods can be recommended.

[0733] Learning and accuracy improvement

[0734] The server accumulates user feedback as training data and uses it to improve the accuracy of its analysis. By also learning from emotional data, the server's ability to provide feedback that is more tailored to the user's emotions improves.

[0735] Specific example

[0736] For example, suppose a user enters incorrect parameters when configuring network settings. However, if the user is feeling stressed or anxious, the server will not only correct the error but also provide reassuring feedback such as, "It's okay, stay calm and try again." This kind of emotionally sensitive support allows users to complete tasks more smoothly.

[0737] This system simultaneously automates technical scrutiny and improves the user experience, leading to significant improvements in operational efficiency.

[0738] The following describes the processing flow.

[0739] Step 1:

[0740] The terminal records all operations as log data from the moment the user begins configuring the device. The log details the commands entered and the settings changed, along with timestamps.

[0741] Step 2:

[0742] The terminal sends log data to the server in real time. A secure communication protocol is used to ensure the data's safety.

[0743] Step 3:

[0744] The server passes the received log data to the natural language processing engine and begins analysis. The analysis involves extracting specific keywords from the text content and performing contextual analysis to understand the intent behind the operations.

[0745] Step 4:

[0746] The device collects emotional data from the user's voice and text and sends it to the server.

[0747] Step 5:

[0748] The server uses an emotion engine to analyze the user's emotions. Specifically, it recognizes emotions such as stress, confusion, and satisfaction from the tone of voice and the content of the text.

[0749] Step 6:

[0750] The server detects inconsistencies by comparing the analysis results of log data and sentiment data with standard operating procedures. These analysis results, including the inconsistencies, are then compiled as feedback data.

[0751] Step 7:

[0752] The server adjusts the generated feedback based on the user's emotions. For example, if the user is stressed, it provides gentle, step-by-step instructions; if the user is relaxed, it suggests efficient methods.

[0753] Step 8:

[0754] The server sends the adjusted feedback to the user. The user receives this feedback, reviews their work, and makes corrections as needed.

[0755] Step 9:

[0756] The server records the results after user modifications and stores them in the system as training data. This helps improve the accuracy of future analyses and feedback.

[0757] (Example 2)

[0758] 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".

[0759] When users configure systems and equipment, problems can occur due to operational errors or incorrect input, leading to decreased work efficiency. Furthermore, a lack of accurate understanding of the user's emotions during operation can result in inadequate feedback, adding to their stress. Therefore, it is necessary to refine the configuration process, reduce human error through feedback that takes user emotions into account, and improve both work efficiency and user experience.

[0760] 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.

[0761] In this invention, the server includes means for acquiring log data, means for analyzing the log data using natural language processing technology, means for comparing the analysis results with standard operating procedures and detecting inconsistencies, means for recognizing the user's emotional state from their voice or text, means for providing feedback to the user based on the inconsistencies and emotional recognition, and means for improving the accuracy of the analysis by learning the feedback results and emotional data. This makes it possible to immediately detect user errors and provide appropriate feedback, thereby reducing user stress and enabling efficient operation.

[0762] "Log data" refers to data that records the details of equipment settings and operations performed by a user, and includes timestamps and details of the operations performed.

[0763] "Natural language processing technology" refers to techniques that enable computers to understand and analyze human language, and includes methods for converting text content into structured data.

[0764] A "standard operating procedure" is a set of predetermined procedures and standards for performing a specific task, serving as a guideline to ensure consistency and accuracy in operations.

[0765] "Inconsistency" refers to parts of the analyzed data that deviate from standard operating procedures, indicating errors or mistakes that occur during setup or operation.

[0766] "Feedback" refers to information and advice provided based on the user's actions and emotional state, and is a response that helps the user improve or adjust their next actions.

[0767] "Emotional state" refers to the psychological and emotional state a user is in while using the system, and includes a variety of emotions such as stress, confusion, and satisfaction.

[0768] "Learning" is the process by which a system continuously improves the accuracy of its analysis and feedback based on feedback results and sentiment data.

[0769] This invention is a system designed to streamline the user's equipment setup process and reduce human error. Specifically, it combines log data collection, natural language processing analysis, comparison with standard operating procedures, inconsistency detection, user feedback provision, a learning function aimed at improving analysis accuracy, and an emotion engine that recognizes the user's emotions.

[0770] The device includes hardware and software to record all user actions in real time and generate log data. Specifically, it captures keyboard input and screen operations using sensors and tracking software. The collected log data is sent to a server at regular intervals.

[0771] The server is equipped with a natural language processing engine for processing received log data. This engine uses natural language processing technologies (e.g., SpaCy and NLTK) to analyze the log content and understand the meaning of the operations performed. The results are compared with standard operating procedures, and if inconsistencies are detected, preparations for the next step are made.

[0772] The device also acquires voice and text messages entered by the user and sends them to the server's emotion engine as emotion data. The emotion engine recognizes the user's emotional state from the collected data and identifies states such as stress and confusion.

[0773] Based on the analysis results and emotion recognition results, the server generates optimal feedback. This feedback is adjusted according to the user's psychological state, so, for example, a user who is feeling anxious will receive content that promotes calmness. This feedback is communicated to the user through screen display and audio output.

[0774] Furthermore, the server accumulates feedback results and user sentiment data as training data, which is used to continuously improve the accuracy of the analysis. This uses a generative AI model to improve the accuracy and adaptability of the feedback.

[0775] As a concrete example, consider a situation where a user is configuring network settings and has entered incorrect parameters. If the user is feeling stressed, the system might provide feedback such as, "It's okay, please stay calm and try again." This kind of empathetic response allows the user to continue working smoothly.

[0776] An example of a prompt message could be, "Please suggest ways for users to provide feedback if they experience stress during the setup process."

[0777] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0778] Step 1:

[0779] The terminal monitors the user's device configuration operations in real time and records the input as log data. Specifically, it captures user interactions such as mouse clicks, keyboard input, and screen touches using sensors and tracking software. This log data includes a timestamp corresponding to the operation and the details of the operation, which are used in subsequent analysis processes.

[0780] Step 2:

[0781] The terminal processes the recorded log data in batches at regular intervals and sends it to the server. The server receives this log data as input to a natural language processing engine and performs analysis. As part of the data processing, natural language processing techniques are used to semantically analyze the log data and extract the user's intentions and actions. The analyzed data is compared with pre-configured standard operating procedures, and any inconsistencies are output.

[0782] Step 3:

[0783] The terminal acquires the user's voice input and text messages and sends them to the server as emotion data. This data is processed using voice analysis software and text analysis tools. The server's emotion engine performs data calculations based on this data to identify the user's emotional state. Specifically, it analyzes the characteristics of the voice tone and extracts emotion-related keywords from the text. This results in the output of the user's emotional state (e.g., stress, confusion, satisfaction).

[0784] Step 4:

[0785] The server receives the analyzed inconsistent data and emotion recognition results as input and generates optimal feedback. Using a generative AI model, the feedback is adjusted to match the user's current emotional state. For example, if the user is feeling anxious, the feedback might be a gentle instruction such as, "It's okay, calm down and try again." This feedback is provided to the user as a text message or voice output.

[0786] Step 5:

[0787] The server accumulates feedback results and user sentiment data, using it as training data to improve analysis accuracy. During this training process, the dataset is continuously updated. Based on this data, the generative AI model improves the accuracy of feedback, enabling new character recognition and more accurate sentiment responses. In this way, the overall operational efficiency and user experience of the system are continuously improved.

[0788] (Application Example 2)

[0789] 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".

[0790] In on-site work, it is crucial for workers to follow precise procedures, but human errors are more likely to occur in complex tasks or when many people are involved. Furthermore, a worker's mental state significantly impacts the accuracy and efficiency of their work, but existing systems have lacked sufficient support that takes this emotional state into account. Therefore, there is a need for a system that can reduce work errors and provide appropriate feedback tailored to the worker's emotional state.

[0791] 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.

[0792] In this invention, the server includes means for acquiring log information, means for analyzing the log information using natural language processing technology, means for comparing the analysis results with standard process procedures and detecting inconsistencies, and means for recognizing the emotional state of the worker. This makes it possible to reduce work errors and improve work efficiency by providing feedback that corresponds to the worker's mental state.

[0793] "Log information" refers to data that records user operations and actions.

[0794] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0795] "Standard process procedures" refer to a set of procedures or methods that serve as the standard for carrying out work.

[0796] "Inconsistency" refers to a state that indicates a discrepancy or contradiction between the analysis results and the standard process procedure.

[0797] "Feedback" refers to a response or reaction to given information or instructions.

[0798] "Analysis accuracy" is an indicator that shows the accuracy and detail of the data analysis results.

[0799] "Emotional state" refers to the psychological or emotional state that a user exhibits at a specific point in time.

[0800] "Diverse data" refers to data obtained from multiple sources that have different formats and content.

[0801] The system implementing this invention is intended for work supervision at construction sites, monitoring the work processes of on-site workers in real time and providing feedback to reduce work errors. The system uses smartphones or smart glasses to acquire and analyze worker operation logs and voice data.

[0802] The server analyzes the acquired log information using a natural language processing engine and detects inconsistencies by comparing the results with standard process procedures. If an inconsistency is detected, the server generates appropriate feedback, taking into account the worker's emotional state, and displays it on the terminal. The feedback is adjusted to alleviate the worker's emotional state and recommend a retry.

[0803] The system's specific configuration uses Python and TensorFlow for natural language processing and emotion recognition, and Flask for server-side processing. The user interface is built with React and optimized for smartphones and smart glasses. For emotion recognition, a model based on diverse data is used to analyze emotions in real time from the worker's voice data.

[0804] For example, if a worker makes an incorrect connection while following a complex blueprint, they will receive real-time feedback, such as "Calm down, take a deep breath, and check the correct procedure." In this way, the system allows for highly accurate work while taking into consideration the emotional state of the worker.

[0805] An example of a prompt for a generative AI model might be: "Please tell me specifically how to automatically detect errors in construction site work procedures and provide optimal real-time feedback based on the emotional state of the workers."

[0806] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0807] Step 1:

[0808] The terminal collects field workers' operations and voice data in real time and records it as log information. This input log information includes a process of converting work procedures and voice data into a digital format. This enables accuracy of operations and recognition of emotions from voice.

[0809] Step 2:

[0810] The terminal sends recorded log information to the server. The input here consists of digitized operation logs and audio data, which the server receives and prepares to proceed to the next analysis step.

[0811] Step 3:

[0812] The server analyzes the acquired log information using natural language processing techniques. In this process, the log information is compared against standard procedure data. The input is operation log data, and the output is the presence or absence of inconsistencies for each log. Specifically, it checks how closely the operation procedure matches the standard.

[0813] Step 4:

[0814] The server processes the voice data into an emotion recognition engine to analyze the worker's emotional state. The input for this step is voice data, and the output is an emotional state (e.g., stress, anxiety, calmness, etc.). Voice pattern analysis is performed at this stage.

[0815] Step 5:

[0816] The server generates feedback based on the analysis results and emotional state. In this step, the input is inconsistent information and emotional state, and the output is a tailored feedback message. Specific actions include sending messages to promote relaxation and determining effective guidance content.

[0817] Step 6:

[0818] The terminal displays the generated feedback to the worker. The input is a feedback message, and the expected output is the worker's response. Specifically, the terminal displays the message on its screen.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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."

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0840] The following is further disclosed regarding the embodiments described above.

[0841] (Claim 1)

[0842] Means for obtaining log data,

[0843] The means for analyzing the log data using natural language processing technology,

[0844] A means for comparing the analysis results with standard operating procedures and detecting inconsistencies,

[0845] A means for providing feedback to the user based on the aforementioned inconsistency,

[0846] A means of improving analysis accuracy by learning from the results of feedback,

[0847] A system that includes this.

[0848] (Claim 2)

[0849] The system according to claim 1, which monitors user input in real time and records it as log data.

[0850] (Claim 3)

[0851] The system according to claim 1, which utilizes multimodal data to obtain information from different data sources.

[0852] "Example 1"

[0853] (Claim 1)

[0854] A device for recording information related to the operation,

[0855] A device that transmits information regarding the aforementioned operation to an analysis device,

[0856] The analysis device includes a device that analyzes information related to the operation using natural language processing technology and identifies inconsistencies by comparing it with a standard operation plan,

[0857] A device that provides instructions to the user based on the aforementioned inconsistency,

[0858] A device that accumulates user responses to instructions and performs learning to improve analysis accuracy,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, which monitors user operations in real time and records information related to those operations.

[0862] (Claim 3)

[0863] The system according to claim 1, which utilizes complex data and obtains data from different sources.

[0864] "Application Example 1"

[0865] (Claim 1)

[0866] Means for obtaining log data,

[0867] The means for analyzing the log data using natural language processing technology,

[0868] A means for comparing the analysis results with standard operating procedures and detecting inconsistencies,

[0869] A means for providing feedback to the user based on the aforementioned inconsistency,

[0870] A means of improving analysis accuracy by learning from the results of feedback,

[0871] The accuracy of operations performed by physical devices is evaluated in real time.

[0872] A means for presenting the results through a visual display device,

[0873] A system that includes this.

[0874] (Claim 2)

[0875] The system according to claim 1, which monitors user input in real time and records it as log data.

[0876] (Claim 3)

[0877] The system according to claim 1, which utilizes multimodal data to obtain information from different data sources.

[0878] "Example 2 of combining an emotion engine"

[0879] (Claim 1)

[0880] Means for obtaining log data,

[0881] The means for analyzing the log data using natural language processing technology,

[0882] A means for comparing the analysis results with standard operating procedures and detecting inconsistencies,

[0883] A means of recognizing the emotional state from the user's voice or text,

[0884] Means for providing feedback to users based on inconsistencies and sentiment recognition,

[0885] A means of improving analysis accuracy by learning from feedback results and sentiment data,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, which monitors user input in real time and records it as log data.

[0889] (Claim 3)

[0890] The system according to claim 1, which utilizes multimodal data to obtain information from different data sources.

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

[0892] (Claim 1)

[0893] Means for obtaining log information,

[0894] The means for analyzing the log information using natural language processing technology,

[0895] A means for detecting inconsistencies by comparing the analysis results with standard process procedures,

[0896] A means of providing feedback to users based on the aforementioned inconsistencies,

[0897] A means of improving analysis accuracy by learning from the results of feedback,

[0898] Means for recognizing the emotional state of workers,

[0899] A means of adjusting feedback based on the user's emotional state,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, which monitors user information in real time and records it as log information.

[0903] (Claim 3)

[0904] The system according to claim 1, which utilizes diverse data and obtains information from different sources. [Explanation of Symbols]

[0905] 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 for obtaining log data, The means for analyzing the log data using natural language processing technology, A means for comparing the analysis results with standard operating procedures and detecting inconsistencies, A means for providing feedback to the user based on the aforementioned inconsistency, A means of improving analysis accuracy by learning from the results of feedback, The accuracy of operations performed by physical devices is evaluated in real time. A means for presenting the results through a visual display device, A system that includes this.

2. The system according to claim 1, which monitors user input in real time and records it as log data.

3. The system according to claim 1, which utilizes multimodal data to acquire information from different data sources.

Images