system

Abstract

The system according to this embodiment aims to automatically monitor whether operations are in accordance with the procedure based on the procedure manual, and to prevent deviations from the procedure. [Solution] The system according to the embodiment comprises an input unit, an analysis unit, a determination unit, a warning unit, and an alert unit. The input unit inputs the procedure manual. The analysis unit analyzes the procedure manual input by the input unit. The determination unit determines whether the operation is in accordance with the procedure based on the procedure manual analyzed by the analysis unit. The warning unit issues a warning if the determination unit determines that the operation is likely to deviate from the procedure. The alert unit sends an alert to the administrator if the determination unit determines that the operation has deviated from the procedure.

Description

Technical Field

[0006] , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

[0007] The system according to this embodiment can automatically monitor whether the operation is in accordance with the procedure based on the procedure manual, and can prevent deviations from the procedure. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] 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.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The double-check AI agent system according to an embodiment of the present invention is a system that ensures adherence to procedures in business processes and prevents errors during operations. This double-check AI agent system utilizes the screen sharing function of a web conferencing application to monitor on-site work in real time. Procedure manuals are taken in via a generating AI, and the AI ​​uses generating AI analysis to determine whether the operation is in accordance with the procedure. If the operation is about to deviate from the procedure, a warning is issued, and if the operation is deviated from the procedure, an alert is immediately sent to the administrator. This ensures adherence to procedures and prevents errors during operations. For example, the double-check AI agent system shares a screen showing the worker performing an operation according to the procedure manual, and the AI ​​monitors the operation. In this case, the procedure manual is taken in via a generating AI. For example, the generating AI takes in the procedure manual in text format and analyzes its contents. Next, the AI ​​uses generating AI analysis to determine whether the operation is in accordance with the procedure. For example, the generating AI determines whether the operations included in the procedure manual are being performed correctly, and issues a warning if the operation does not follow the procedure. In this case, a warning is issued if the operation is about to deviate from the procedure, and if the operation is deviated from the procedure, an alert is immediately sent to the administrator. This ensures adherence to procedures and prevents errors during operations. For example, if an operator following a procedure manual is about to deviate from it, the AI ​​will issue a warning to alert the operator. If a deviation occurs, an alert is immediately sent to the manager to facilitate early problem resolution. In this way, the AI-powered automated monitoring and warning system improves the precision and reliability of operations. By instantly detecting deviations and quickly sending alerts to relevant parties, it facilitates early problem resolution. The burden of manual monitoring is reduced, allowing staff to focus on more advanced tasks. As a result, operational efficiency is improved and the quality of the entire process is guaranteed. Thus, the double-check AI agent system ensures adherence to procedures in business processes and prevents errors during operations.

[0029] The double-check AI agent system according to this embodiment comprises an input unit, an analysis unit, a determination unit, a warning unit, and an alert unit. The input unit inputs procedure documents. Procedure documents include, but are not limited to, operating procedures, manuals, and guidelines. The input unit digitizes and inputs procedure documents using scanning technology, for example. The input unit can also directly input procedure documents submitted in digital format. Furthermore, the input unit can read printed procedure documents using OCR technology. For example, the input unit scans the procedure document with a high-resolution scanner and converts it into text information using OCR technology. Digital procedure documents can be directly input if they are submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The analysis unit analyzes the procedure documents input by the input unit using a generation AI. The analysis is performed by, but is not limited to, methods such as text analysis, syntactic analysis, and semantic analysis. For example, the generation AI analyzes the procedure documents using a text generation AI (e.g., LLM). Furthermore, the analysis unit can analyze the contents of the procedure manual using a multimodal generation AI. The analysis unit can also extract and analyze important parts of the procedure manual using a generation AI. For example, the text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. The multimodal generation AI can handle multiple modals, including not only text but also images and audio. The generation AI uses keyword extraction technology to pick out particularly important information from the procedure manual and performs analysis based on that information. The judgment unit determines whether the operation conforms to the procedure based on the procedure manual analyzed by the analysis unit. The judgment is made based on criteria such as the degree of procedure conformance and error detection methods, but is not limited to these examples. For example, the judgment unit determines whether the operation conforms to the procedure based on the degree of procedure conformance. The judgment unit can also determine deviations from the procedure using error detection methods. Furthermore, the judgment unit can determine the degree of procedure conformance using AI. For example, the judgment unit can determine the degree of procedure conformance using an AI model that takes the contents of the procedure manual and the contents of the operation as input and outputs the degree of procedure conformance.The warning unit issues a warning if the judgment unit determines that a procedure is about to be deviated from. Warnings are issued based on criteria such as the format of the warning message and the notification method, but are not limited to such examples. The warning unit issues a warning message if a procedure is about to be deviated from. The warning unit can also issue warnings using notification methods. The warning unit can also issue warnings using AI. For example, the warning unit can issue a warning using an AI model that generates a warning message when a procedure is about to be deviated from. The alert unit sends an alert to the administrator if a procedure is deviated from by the judgment unit. Alerts are issued based on criteria such as the format of the alert message and the notification method, but are not limited to such examples. The alert unit sends an alert message if a procedure is deviated from. The alert unit can also send alerts using notification methods. The alert unit can also send alerts using AI. For example, the alert unit can send alerts using an AI model that generates an alert message when a procedure is deviated from. As a result, the double-check AI agent system according to this embodiment automates a series of processes from importing procedure manuals to analysis, judgment, warning, and alert transmission, ensuring compliance with procedures and preventing errors during operations.

[0030] The input unit inputs procedure documents. These procedures include, but are not limited to, operating procedures, manuals, and guidelines. The input unit can, for example, digitize and input procedure documents using scanning technology. It can also directly input procedure documents submitted in digital format. Furthermore, the input unit can read printed procedure documents using OCR technology. For example, the input unit scans the procedure document with a high-resolution scanner and converts it into text information using OCR technology. Digital procedure documents submitted in specific file formats can be directly input. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The input unit utilizes these technologies to accurately and quickly digitize the contents of procedure documents. Scanning technology scans the physical pages of the procedure document at high resolution and inputs them as image data. This allows for digitization while preserving the layout and format of the procedure document. OCR technology extracts text information from the scanned image data and converts it into text data. This allows the contents of the procedure document to be saved in a searchable text format. Procedure manuals submitted digitally are often provided in file formats such as PDF and Word, and the import unit can directly read these files. This allows the contents of the procedure manual to be imported as is, eliminating the need for manual data entry. By combining these technologies, the import unit can streamline the procedure manual import process and provide accurate data.

[0031] The analysis unit uses a generative AI to analyze the procedure manuals imported by the input unit. Analysis is performed using methods such as text analysis, syntactic analysis, and semantic analysis, but is not limited to these examples. For instance, the generative AI can analyze the procedure manual using a text generation AI (e.g., LLM). The analysis unit can also analyze the content of the procedure manual using a multimodal generative AI. Furthermore, the analysis unit can use the generative AI to extract and analyze important parts of the procedure manual. For example, a text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. A multimodal generative AI can handle multiple modals, including not only text but also images and audio. The generative AI uses keyword extraction techniques to pick out particularly important information from the procedure manual and performs analysis based on that information. The analysis unit leverages the generative AI's advanced natural language processing capabilities to analyze the content of the procedure manual in detail. Text analysis divides each paragraph and sentence of the procedure manual and understands the meaning of each. Syntactic analysis analyzes the sentence structure and clarifies the relationships between subjects, predicates, objects, etc. Semantic analysis involves understanding the meaning of sentences and grasping the intent and purpose of the procedure manual. Multimodal generation AI can also analyze visual information such as images and diagrams included in the procedure manual. This allows for a more comprehensive understanding of the manual's content and improves the accuracy of the analysis results. The generation AI extracts particularly important parts of the procedure manual and provides them as analysis results. For example, it picks out emphasized procedures and precautions within the manual and performs analysis based on them. This allows the analysis unit to analyze the manual's content in detail, extract important information, and provide it.

[0032] The judgment unit determines whether the operation follows the procedure based on the procedure manual analyzed by the analysis unit. The judgment is made based on criteria such as the degree of procedure conformance and the error detection method, but is not limited to these examples. For example, the judgment unit determines whether the operation follows the procedure based on the degree of procedure conformance. The judgment unit can also determine deviations from the procedure using the error detection method. The judgment unit can also determine the degree of procedure conformance using AI. For example, the judgment unit can determine the degree of procedure conformance using an AI model that takes the contents of the procedure manual and the contents of the operation as input and outputs the degree of procedure conformance. Based on the analysis results provided by the analysis unit, the judgment unit determines whether the operation follows the procedure described in the procedure manual. The degree of procedure conformance is evaluated by comparing each step of the procedure manual with the actual operation and determining whether they are consistent. The error detection method detects deviations from the procedure manual and issues a warning if the operation does not follow the procedure. The AI ​​model takes the contents of the procedure manual and the contents of the operation as input and outputs the degree of procedure conformance. As a result, the judgment unit can determine whether the operation is performed accurately based on the procedure manual and detect deviations from the procedure. The judgment unit compares each step of the procedure manual with the actual operation in detail to evaluate the degree of procedure conformity. For example, it compares the operation procedure described in the manual with the actual operation log and evaluates whether they match. The error detection method detects deviations from the procedure manual and issues a warning if the operation does not follow the procedure. The AI ​​model takes the contents of the procedure manual and the contents of the operation as input and outputs the degree of procedure conformity. This allows the judgment unit to determine whether the operation is being performed accurately according to the procedure manual and to detect deviations from the procedure.

[0033] The warning unit issues a warning if the judgment unit detects that the user is about to deviate from the procedure. Warnings are issued based on criteria such as the format of the warning message and the notification method, but are not limited to these examples. The warning unit issues a warning message if the user is about to deviate from the procedure. The warning unit can also issue warnings using notification methods. The warning unit can also issue warnings using AI. For example, the warning unit can issue a warning using an AI model that generates a warning message when the user is about to deviate from the procedure. The warning unit issues a warning if the user is about to deviate from the procedure based on information from the judgment unit. The warning message is intended to draw the user's attention to the operation that is about to deviate from the procedure. Notification methods include, for example, pop-up messages, voice notifications, and email notifications. The AI ​​model generates a warning message when the user is about to deviate from the procedure and issues a warning to the user. This allows the warning unit to quickly issue a warning when the user is about to deviate from the procedure, preventing operational errors. The warning unit issues a warning if the user is about to deviate from the procedure based on information from the judgment unit. Warning messages alert users who are about to deviate from the prescribed procedure. Notification methods include, for example, pop-up messages, voice notifications, and email notifications. The AI ​​model generates a warning message when the user is about to deviate from the procedure and issues a warning to the user. This allows the warning unit to quickly issue a warning when the user is about to deviate from the procedure, thus preventing operational errors.

[0034] The alert unit sends an alert to the administrator if the procedure is deviated from as determined by the judgment unit. Alerts are issued based on criteria such as the format of the alert message and the notification method, but are not limited to these examples. For example, the alert unit sends an alert message when the procedure is deviated. The alert unit can also send alerts using various notification methods. The alert unit can also send alerts using AI. For example, the alert unit can send alerts using an AI model that generates an alert message when the procedure is deviated. Based on information from the judgment unit, the alert unit sends an alert to the administrator when the procedure is deviated. The alert message is intended to draw the attention of the user performing an operation that deviates from the procedure. Notification methods include, for example, pop-up messages, voice notifications, and email notifications. The AI ​​model generates an alert message when the procedure is deviated and sends the alert to the administrator. This allows the alert unit to quickly issue an alert when the procedure is deviated and draw the attention of the administrator. Based on information from the judgment unit, the alert unit sends an alert to the administrator when the procedure is deviated. The alert message is intended to draw the attention of the user performing an operation that deviates from the procedure. Notification methods include, for example, pop-up messages, voice notifications, and email notifications. The AI ​​model generates an alert message and sends an alert to the administrator if the procedure is deviated from. This allows the alerting unit to quickly issue an alert when the procedure is deviated from, drawing the administrator's attention.

[0035] The import unit can import procedure manuals in text format using a generation AI. For example, the import unit can import procedure manuals in text format using a generation AI. For example, the import unit can import procedure manuals in text format using the generation AI's API. The import unit can also import procedure manuals by specifying the model version of the generation AI. For example, the import unit imports procedure manuals using the latest version of the generation AI. This makes the import of procedure manuals more efficient by using the generation AI. Some or all of the above processing in the import unit may be performed using the generation AI, or not. For example, the import unit can input the procedure manuals into the generation AI and have the generation AI import the procedure manuals.

[0036] The analysis unit can use a generating AI to determine whether the operations included in the procedure manual have been performed correctly. For example, the analysis unit can use a generating AI to determine whether the operations included in the procedure manual have been performed correctly. For example, the analysis unit can use the API of the generating AI to determine the operations in the procedure manual. The analysis unit can also specify the model version of the generating AI to determine the operations in the procedure manual. For example, the analysis unit can use the latest version of the generating AI to determine the operations in the procedure manual. This improves the accuracy of the procedure manual analysis by using a generating AI. Some or all of the above-described processes in the analysis unit may be performed using a generating AI, or they may not be performed using a generating AI. For example, the analysis unit can input the operations in the procedure manual into a generating AI and have the generating AI perform the determination of the operations in the procedure manual.

[0037] The warning unit can issue a warning if the procedure is about to be deviated from. For example, the warning unit can issue a warning message if the procedure is about to be deviated from. The warning unit can also issue a warning using a notification method if the procedure is about to be deviated from. For example, the warning unit can issue a warning by email if the procedure is about to be deviated from. The warning unit can also issue a warning using a chat tool if the procedure is about to be deviated from. For example, the warning unit can send a warning message using a chat tool if the procedure is about to be deviated from. This allows the worker to be alerted by issuing a warning if the procedure is about to be deviated from. Some or all of the above processing in the warning unit may be performed using AI, for example, or not using AI. For example, the warning unit can issue a warning using an AI model that generates a warning message if the procedure is about to be deviated from.

[0038] The alerting unit can send an alert to the administrator if the procedure is deviated from. For example, the alerting unit sends an alert when the procedure is deviated from. For example, the alerting unit sends an alert message when the procedure is deviated from. The alerting unit can also send an alert using a notification method when the procedure is deviated from. For example, the alerting unit sends an alert via email when the procedure is deviated from. The alerting unit can also send an alert via a chat tool when the procedure is deviated from. For example, the alerting unit sends an alert message via a chat tool when the procedure is deviated from. This facilitates the early resolution of problems by sending an alert to the administrator when the procedure is deviated from. Some or all of the above processing in the alerting unit may be performed using AI, for example, or not using AI. For example, the alerting unit can send an alert using an AI model that generates an alert message when the procedure is deviated from.

[0039] The alert unit can send alerts to administrators via email or chat tools. For example, the alert unit can send alert messages using email. The alert unit can also send alert messages using chat tools. For example, the alert unit can send alert messages using chat tools. This allows administrators to respond quickly by sending alerts via email or chat tools. Some or all of the above processing in the alert unit may be performed using AI, for example, or not using AI. For example, the alert unit can send alerts via email or chat tools using an AI model that generates alert messages.

[0040] The import unit can perform version control of procedure manuals and prioritize importing the latest version. For example, the import unit can perform version control of procedure manuals and prioritize importing the latest version. For example, the import unit can automatically check the version of a procedure manual and prioritize importing the latest version. The import unit can also maintain a version history of the procedure manuals and allow referencing of past versions as needed. For example, the import unit can perform version control of procedure manuals and record the change history. This ensures that the latest version of the procedure manual is always available through version control. Some or all of the above processing in the import unit may be performed using, for example, a generation AI, or not. For example, the import unit can have a generation AI perform version control of the procedure manuals.

[0041] The import unit can automatically classify the contents of procedure manuals and import them into different categories. For example, the import unit can automatically classify the contents of procedure manuals and import them into different categories. For example, the import unit can analyze the contents of procedure manuals and classify them into different categories (e.g., safety procedures, operating procedures). The import unit can also automatically tag the contents of procedure manuals and import them into categories. For example, the import unit can analyze the contents of procedure manuals and automatically assign them to the relevant categories. This makes it easier to manage procedure manuals by automatically classifying their contents. Some or all of the above processing in the import unit may be performed using, for example, a generative AI, or without a generative AI. For example, the import unit can have a generative AI perform the classification of the contents of procedure manuals.

[0042] The input unit can automatically translate the language of the procedure manual and input it in multiple languages. For example, the input unit can automatically translate the language of the procedure manual and input it in multiple languages. For example, the input unit can automatically translate the content of the procedure manual and input it in multiple languages. The input unit can also automatically detect the language of the procedure manual and translate it as needed. For example, the input unit can analyze the content of the procedure manual and input it in multiple languages. This makes it possible to input in multiple languages ​​by automatically translating the language of the procedure manual. Some or all of the above processing in the input unit may be performed using, for example, a generative AI, or without a generative AI. For example, the input unit can have a generative AI perform the translation of the procedure manual.

[0043] The data acquisition unit can improve the accuracy of data acquisition by referring to related literature in the procedure manual. For example, the data acquisition unit can improve the accuracy of data acquisition by referring to related literature in the procedure manual. For example, the data acquisition unit can analyze the contents of the procedure manual and improve the accuracy of data acquisition by referring to related literature. The data acquisition unit can also automatically classify the contents of the procedure manual and improve the accuracy of data acquisition by referring to related literature. For example, the data acquisition unit can analyze the contents of the procedure manual and improve the accuracy of data acquisition by referring to related literature. As a result, the accuracy of data acquisition is improved by referring to related literature in the procedure manual. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the data acquisition unit can have a generation AI perform the referencing of related literature in the procedure manual.

[0044] The analysis unit can automatically summarize the contents of the procedure manual and highlight important parts. For example, the analysis unit can automatically summarize the contents of the procedure manual and highlight important parts. For example, the analysis unit can analyze the contents of the procedure manual and automatically highlight important parts. The analysis unit can also summarize the contents of the procedure manual and highlight important parts. For example, the analysis unit can automatically summarize the contents of the procedure manual and highlight important parts. This ensures that workers do not miss important information by summarizing the contents of the procedure manual and highlighting important parts. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can have a generative AI perform the summarization and highlighting of the procedure manual.

[0045] The analysis unit can automatically compare the contents of the procedure manuals and identify the differences between different versions. For example, the analysis unit can automatically compare the contents of the procedure manuals and identify the differences between different versions. For example, the analysis unit can analyze the contents of the procedure manuals and automatically identify the differences between different versions. The analysis unit can also compare the contents of the procedure manuals and identify the differences between different versions. For example, the analysis unit can automatically compare the contents of the procedure manuals and identify the differences between different versions. In this way, by comparing the contents of the procedure manuals, the differences between different versions can be identified. Some or all of the above processing in the analysis unit may be performed using, for example, a generation AI, or without a generation AI. For example, the analysis unit can have a generation AI perform the task of identifying the differences between versions of the procedure manuals.

[0046] The analysis unit can automatically convert the contents of the procedure manual into speech and provide the analysis results in speech. For example, the analysis unit can automatically convert the contents of the procedure manual into speech and provide the analysis results in speech. For example, the analysis unit can analyze the contents of the procedure manual and provide the analysis results in speech. The analysis unit can also convert the contents of the procedure manual into speech and provide the analysis results. For example, the analysis unit can automatically convert the contents of the procedure manual into speech and provide the analysis results in speech. In this way, by converting the contents of the procedure manual into speech, the analysis results can be provided in speech. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can have a generating AI perform the speech conversion of the procedure manual.

[0047] The analysis unit can improve the accuracy of its analysis by referring to related videos of the procedure manual. For example, the analysis unit can improve the accuracy of its analysis by referring to related videos of the procedure manual. For example, the analysis unit can analyze the contents of the procedure manual and improve the accuracy of its analysis by referring to related videos. The analysis unit can also automatically classify the contents of the procedure manual and improve the accuracy of its analysis by referring to related videos. For example, the analysis unit can analyze the contents of the procedure manual and improve the accuracy of its analysis by referring to related videos. As a result, the accuracy of the analysis is improved by referring to related videos of the procedure manual. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can have the generating AI perform the task of referring to related videos of the procedure manual.

[0048] The judgment unit can monitor the contents of the procedure manual in real time and make an immediate judgment. For example, the judgment unit can monitor the contents of the procedure manual in real time and make an immediate judgment. For example, the judgment unit can analyze the contents of the procedure manual and make a real-time judgment. The judgment unit can also monitor the contents of the procedure manual and make an immediate judgment. For example, the judgment unit can monitor the contents of the procedure manual in real time and make an immediate judgment. This allows for immediate judgment by monitoring the contents of the procedure manual in real time. Some or all of the above-described processes in the judgment unit may be performed using, for example, a generative AI, or without a generative AI. For example, the judgment unit can have a generative AI perform real-time monitoring of the procedure manual.

[0049] The judgment unit can automatically learn the contents of the procedure manual and improve the accuracy of its judgment. For example, the judgment unit can automatically learn the contents of the procedure manual and improve the accuracy of its judgment. For example, the judgment unit can analyze and learn the contents of the procedure manual to improve the accuracy of its judgment. The judgment unit can also learn the contents of the procedure manual and improve the accuracy of its judgment. For example, the judgment unit can automatically learn the contents of the procedure manual and improve the accuracy of its judgment. As a result, the accuracy of the judgment is improved by automatically learning the contents of the procedure manual. Some or all of the above processing in the judgment unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the judgment unit can have a generative AI perform the learning of the procedure manual.

[0050] The judgment unit can automatically visualize the contents of the procedure manual and provide the judgment result visually. For example, the judgment unit can automatically visualize the contents of the procedure manual and provide the judgment result visually. For example, the judgment unit can analyze the contents of the procedure manual, visualize them, and provide the judgment result. The judgment unit can also visualize the contents of the procedure manual and provide the judgment result. For example, the judgment unit can automatically visualize the contents of the procedure manual and provide the judgment result visually. In this way, by visualizing the contents of the procedure manual, the judgment result can be provided visually. Some or all of the above processing in the judgment unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the judgment unit can have a generative AI perform the visualization of the procedure manual.

[0051] The judgment unit can improve the accuracy of its judgment by referring to relevant data in the procedure manual. For example, the judgment unit can improve the accuracy of its judgment by referring to relevant data in the procedure manual. For example, the judgment unit can analyze the contents of the procedure manual and improve the accuracy of its judgment by referring to relevant data. The judgment unit can also automatically classify the contents of the procedure manual and improve the accuracy of its judgment by referring to relevant data. For example, the judgment unit can analyze the contents of the procedure manual and improve the accuracy of its judgment by referring to relevant data. As a result, the accuracy of the judgment is improved by referring to relevant data in the procedure manual. Some or all of the above processing in the judgment unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the judgment unit can have the generating AI perform the referencing of relevant data in the procedure manual.

[0052] The warning unit can adjust the timing of warnings and issue warnings early if it is about to deviate from the procedure. For example, the warning unit can adjust the timing of warnings and issue warnings early if it is about to deviate from the procedure. For example, the warning unit can issue warnings early if it is about to deviate from the procedure to draw the worker's attention. The warning unit can also adjust the timing of warnings and issue warnings at the appropriate time if it is about to deviate from the procedure. For example, the warning unit can adjust the timing of warnings and issue warnings early if it is about to deviate from the procedure. This allows the worker to be drawn to the warning by issuing warnings early if it is about to deviate from the procedure. Some or all of the above processing in the warning unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the warning unit can have a generating AI perform the adjustment of the warning timing.

[0053] The warning unit can automatically customize the content of warnings and take individual action when it is likely that the procedure will be deviated from. For example, the warning unit can automatically customize the content of warnings and take individual action when it is likely that the procedure will be deviated from. For example, the warning unit can automatically customize the content of warnings and prompt the worker to take appropriate action when it is likely that the procedure will be deviated from. The warning unit can also customize the content of warnings and take individual action when it is likely that the procedure will be deviated from. For example, the warning unit can automatically customize the content of warnings and take individual action when it is likely that the procedure will be deviated from. In this way, by customizing the content of warnings when it is likely that the procedure will be deviated from, the worker can be prompted to take appropriate action. Some or all of the above processing in the warning unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the warning unit can have a generation AI perform the customization of the content of warnings.

[0054] The warning unit can automatically convert the warning content into voice and provide an audio warning when the procedure is about to be deviated from. For example, the warning unit can automatically convert the warning content into voice and provide an audio warning when the procedure is about to be deviated from. For example, the warning unit can automatically convert the warning content into voice and draw the worker's attention when the procedure is about to be deviated from. The warning unit can also convert the warning content into voice and provide a warning at an appropriate time when the procedure is about to be deviated from. For example, the warning unit can automatically convert the warning content into voice and provide an audio warning when the procedure is about to be deviated from. This allows the worker to be drawn to the warning content by converting it into voice when the procedure is about to be deviated from. Some or all of the above processing in the warning unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the warning unit can have a generation AI perform the voice conversion of the warning.

[0055] The warning unit can automatically visualize the content of a warning and provide a visual warning when a user is about to deviate from the procedure. For example, the warning unit can automatically visualize the content of a warning and provide a visual warning when a user is about to deviate from the procedure. For example, the warning unit can automatically visualize the content of a warning and draw the user's attention when a user is about to deviate from the procedure. The warning unit can also visualize the content of a warning and provide a warning at an appropriate time when a user is about to deviate from the procedure. For example, the warning unit can automatically visualize the content of a warning and provide a visual warning when a user is about to deviate from the procedure. This allows the system to draw the user's attention by visualizing the content of a warning when a user is about to deviate from the procedure. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the warning unit can have a generative AI perform the visualization of the warning.

[0056] The alert unit can adjust the timing of alerts and issue alerts immediately if the procedure is deviated from. For example, the alert unit can adjust the timing of alerts and issue alerts immediately if the procedure is deviated from. For example, the alert unit can issue an alert immediately and notify the administrator if the procedure is deviated from. The alert unit can also adjust the timing of alerts and issue alerts at an appropriate time if the procedure is deviated from. For example, the alert unit can adjust the timing of alerts and issue alerts immediately if the procedure is deviated from. This allows for quick notification to the administrator by issuing an alert immediately if the procedure is deviated from. Some or all of the above processing in the alert unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the alert unit can have a generation AI perform the adjustment of the timing of alerts.

[0057] The alert unit can automatically customize the content of the alert and take individual action if the procedure is deviated from. For example, the alert unit can automatically customize the content of the alert and take individual action if the procedure is deviated from. For example, the alert unit can automatically customize the content of the alert and prompt the administrator to take appropriate action if the procedure is deviated from. The alert unit can also customize the content of the alert and take individual action if the procedure is deviated from. For example, the alert unit can automatically customize the content of the alert and take individual action if the procedure is deviated from. This allows the administrator to take appropriate action by customizing the content of the alert when the procedure is deviated from. Some or all of the above processing in the alert unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the alert unit can have a generation AI perform the customization of the alert content.

[0058] The alert unit can automatically convert the content of an alert into speech and provide an audio alert if the procedure is deviated from. For example, the alert unit can automatically convert the content of an alert into speech and provide an audio alert if the procedure is deviated from. For example, if the procedure is deviated from, the alert unit can automatically convert the content of the alert into speech and notify the administrator. The alert unit can also convert the content of an alert into speech and provide an alert at an appropriate time if the procedure is deviated from. For example, if the procedure is deviated from, the alert unit can automatically convert the content of the alert into speech and provide an audio alert. This allows for quick notification to the administrator by converting the content of the alert into speech when the procedure is deviated from. Some or all of the above processing in the alert unit may be performed using, for example, a generation AI, or without a generation AI. For example, the alert unit can have a generation AI perform the voice conversion of the alert.

[0059] The alert unit can automatically visualize the content of an alert and provide a visual alert when a procedure is deviated from. For example, the alert unit can automatically visualize the content of an alert and provide a visual alert when a procedure is deviated from. For example, the alert unit can automatically visualize the content of an alert and notify the administrator when a procedure is deviated from. The alert unit can also visualize the content of an alert and provide an alert at an appropriate time when a procedure is deviated from. For example, the alert unit can automatically visualize the content of an alert and provide a visual alert when a procedure is deviated from. This allows for quick notification to the administrator by visualizing the content of the alert when a procedure is deviated from. Some or all of the above processing in the alert unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the alert unit can have a generation AI perform the visualization of the alert.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The import unit can automatically tag procedure manuals based on their content when they are imported. For example, the import unit can analyze the content of the procedure manuals, extract relevant keywords, and tag them. The import unit can also categorize and tag the procedure manuals based on their content. For example, the import unit can analyze the content of the procedure manuals and categorize them into categories such as safety procedures, operating procedures, and maintenance procedures, and then tag them. This allows for efficient management of the procedure manual content. Some or all of the above processing in the import unit may be performed using a generation AI, or it may be performed without using a generation AI.

[0062] The analysis unit can automatically summarize the contents of a procedure manual based on its analysis. For example, the analysis unit can analyze the contents of the procedure manual, extract important parts, and summarize them. Furthermore, when analyzing and summarizing the contents of the procedure manual, the analysis unit can also highlight important parts. For example, the analysis unit can analyze the contents of the procedure manual, highlight important parts, and then summarize them. This allows for an efficient understanding of the contents of the procedure manual. Some or all of the above-described processes in the analysis unit may be performed using a generative AI, or they may be performed without using a generative AI.

[0063] The judgment unit can automatically detect errors based on the content of the procedure manual when analyzing its contents. For example, the judgment unit analyzes the contents of the procedure manual and determines whether the operations described in the manual are being performed correctly. The judgment unit can also analyze the contents of the procedure manual and, if an error occurs, display the details of the error. For example, the judgment unit analyzes the contents of the procedure manual and, if an error occurs, displays the details of the error. This allows for an efficient understanding of the contents of the procedure manual. Some or all of the above-described processes in the judgment unit may be performed using a generation AI, or they may be performed without using a generation AI.

[0064] The warning unit can automatically customize the content of warnings when a worker is about to deviate from the procedure. For example, the warning unit can customize the content of warnings according to the worker's skill level when a worker is about to deviate from the procedure. The warning unit can also customize the content of warnings based on the worker's past error history when a worker is about to deviate from the procedure. For example, the warning unit can customize the content of warnings based on the worker's past error history when a worker is about to deviate from the procedure. This allows the warning unit to provide the worker with an appropriate warning when a worker is about to deviate from the procedure. Some or all of the above processing in the warning unit may be performed using generative AI, or it may be performed without using generative AI.

[0065] The alerting unit can automatically customize the content of alerts when procedures are deviated from. For example, the alerting unit can customize the content of alerts according to the administrator's skill level when procedures are deviated from. The alerting unit can also customize the content of alerts based on the administrator's past error history when procedures are deviated from. For example, the alerting unit can customize the content of alerts based on the administrator's past error history when procedures are deviated from. This allows the administrator to receive appropriate alerts when procedures are deviated from. Some or all of the above processing in the alerting unit may be performed using a generative AI, or it may be performed without using a generative AI.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The input unit captures the procedure manual. This manual includes operating instructions, manuals, and guidelines. The input unit can digitize and capture the procedure manual using scanning technology. It can also directly capture procedure manuals submitted in digital format, and can read printed procedure manuals using OCR technology. For example, it can scan with a high-resolution scanner and convert the information into text using OCR technology. Step 2: The analysis unit analyzes the procedure manuals imported by the import unit. Analysis is performed using methods such as text analysis, syntactic analysis, and semantic analysis. It is also possible to analyze the procedure manuals using generative AI and extract and analyze important parts. For example, the content of the procedure manuals can be analyzed using text generation AI or multimodal generation AI. Step 3: The judgment unit determines whether the operation follows the procedure based on the procedure manual analyzed by the analysis unit. The judgment is made based on criteria such as the degree of procedure agreement and the error detection method. The degree of procedure agreement can also be determined using AI. For example, the judgment can be made using an AI model that takes the contents of the procedure manual and the contents of the operation as input and outputs the degree of procedure agreement. Step 4: The warning unit issues a warning if the judgment unit determines that the procedure is about to be deviated from. Warnings are issued based on criteria such as the format of the warning message and the notification method. AI can be used to generate warning messages and issue warnings when the procedure is about to be deviated from. Step 5: The alert unit sends an alert to the administrator if the procedure is deviated from by the judgment unit. Alerts are triggered based on criteria such as the format of the alert message and the notification method. AI can be used to generate alert messages and send alerts when the procedure is deviated from.

[0068] (Example of form 2) The double-check AI agent system according to an embodiment of the present invention is a system that ensures adherence to procedures in business processes and prevents errors during operations. This double-check AI agent system utilizes the screen sharing function of a web conferencing application to monitor on-site work in real time. Procedure manuals are taken in via a generating AI, and the AI ​​uses generating AI analysis to determine whether the operation is in accordance with the procedure. If the operation is about to deviate from the procedure, a warning is issued, and if the operation is deviated from the procedure, an alert is immediately sent to the administrator. This ensures adherence to procedures and prevents errors during operations. For example, the double-check AI agent system shares a screen showing the worker performing an operation according to the procedure manual, and the AI ​​monitors the operation. In this case, the procedure manual is taken in via a generating AI. For example, the generating AI takes in the procedure manual in text format and analyzes its contents. Next, the AI ​​uses generating AI analysis to determine whether the operation is in accordance with the procedure. For example, the generating AI determines whether the operations included in the procedure manual are being performed correctly, and issues a warning if the operation does not follow the procedure. In this case, a warning is issued if the operation is about to deviate from the procedure, and if the operation is deviated from the procedure, an alert is immediately sent to the administrator. This ensures adherence to procedures and prevents errors during operations. For example, if an operator following a procedure manual is about to deviate from it, the AI ​​will issue a warning to alert the operator. If a deviation occurs, an alert is immediately sent to the manager to facilitate early problem resolution. In this way, the AI-powered automated monitoring and warning system improves the precision and reliability of operations. By instantly detecting deviations and quickly sending alerts to relevant parties, it facilitates early problem resolution. The burden of manual monitoring is reduced, allowing staff to focus on more advanced tasks. As a result, operational efficiency is improved and the quality of the entire process is guaranteed. Thus, the double-check AI agent system ensures adherence to procedures in business processes and prevents errors during operations.

[0069] The double-check AI agent system according to this embodiment comprises an input unit, an analysis unit, a determination unit, a warning unit, and an alert unit. The input unit inputs procedure documents. Procedure documents include, but are not limited to, operating procedures, manuals, and guidelines. The input unit digitizes and inputs procedure documents using scanning technology, for example. The input unit can also directly input procedure documents submitted in digital format. Furthermore, the input unit can read printed procedure documents using OCR technology. For example, the input unit scans the procedure document with a high-resolution scanner and converts it into text information using OCR technology. Digital procedure documents can be directly input if they are submitted in a specific file format. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The analysis unit analyzes the procedure documents input by the input unit using a generation AI. The analysis is performed by, but is not limited to, methods such as text analysis, syntactic analysis, and semantic analysis. For example, the generation AI analyzes the procedure documents using a text generation AI (e.g., LLM). Furthermore, the analysis unit can analyze the contents of the procedure manual using a multimodal generation AI. The analysis unit can also extract and analyze important parts of the procedure manual using a generation AI. For example, the text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. The multimodal generation AI can handle multiple modals, including not only text but also images and audio. The generation AI uses keyword extraction technology to pick out particularly important information from the procedure manual and performs analysis based on that information. The judgment unit determines whether the operation conforms to the procedure based on the procedure manual analyzed by the analysis unit. The judgment is made based on criteria such as the degree of procedure conformance and error detection methods, but is not limited to these examples. For example, the judgment unit determines whether the operation conforms to the procedure based on the degree of procedure conformance. The judgment unit can also determine deviations from the procedure using error detection methods. Furthermore, the judgment unit can determine the degree of procedure conformance using AI. For example, the judgment unit can determine the degree of procedure conformance using an AI model that takes the contents of the procedure manual and the contents of the operation as input and outputs the degree of procedure conformance.The warning unit issues a warning if the judgment unit determines that a procedure is about to be deviated from. Warnings are issued based on criteria such as the format of the warning message and the notification method, but are not limited to such examples. The warning unit issues a warning message if a procedure is about to be deviated from. The warning unit can also issue warnings using notification methods. The warning unit can also issue warnings using AI. For example, the warning unit can issue a warning using an AI model that generates a warning message when a procedure is about to be deviated from. The alert unit sends an alert to the administrator if a procedure is deviated from by the judgment unit. Alerts are issued based on criteria such as the format of the alert message and the notification method, but are not limited to such examples. The alert unit sends an alert message if a procedure is deviated from. The alert unit can also send alerts using notification methods. The alert unit can also send alerts using AI. For example, the alert unit can send alerts using an AI model that generates an alert message when a procedure is deviated from. As a result, the double-check AI agent system according to this embodiment automates a series of processes from importing procedure manuals to analysis, judgment, warning, and alert transmission, ensuring compliance with procedures and preventing errors during operations.

[0070] The input unit inputs procedure documents. These procedures include, but are not limited to, operating procedures, manuals, and guidelines. The input unit can, for example, digitize and input procedure documents using scanning technology. It can also directly input procedure documents submitted in digital format. Furthermore, the input unit can read printed procedure documents using OCR technology. For example, the input unit scans the procedure document with a high-resolution scanner and converts it into text information using OCR technology. Digital procedure documents submitted in specific file formats can be directly input. OCR technology recognizes printed characters with high accuracy and converts them into digital text. The input unit utilizes these technologies to accurately and quickly digitize the contents of procedure documents. Scanning technology scans the physical pages of the procedure document at high resolution and inputs them as image data. This allows for digitization while preserving the layout and format of the procedure document. OCR technology extracts text information from the scanned image data and converts it into text data. This allows the contents of the procedure document to be saved in a searchable text format. Procedure manuals submitted digitally are often provided in file formats such as PDF and Word, and the import unit can directly read these files. This allows the contents of the procedure manual to be imported as is, eliminating the need for manual data entry. By combining these technologies, the import unit can streamline the procedure manual import process and provide accurate data.

[0071] The analysis unit uses a generative AI to analyze the procedure manuals imported by the input unit. Analysis is performed using methods such as text analysis, syntactic analysis, and semantic analysis, but is not limited to these examples. For instance, the generative AI can analyze the procedure manual using a text generation AI (e.g., LLM). The analysis unit can also analyze the content of the procedure manual using a multimodal generative AI. Furthermore, the analysis unit can use the generative AI to extract and analyze important parts of the procedure manual. For example, a text generation AI has learned from a large amount of text data and possesses advanced natural language processing capabilities. A multimodal generative AI can handle multiple modals, including not only text but also images and audio. The generative AI uses keyword extraction techniques to pick out particularly important information from the procedure manual and performs analysis based on that information. The analysis unit leverages the generative AI's advanced natural language processing capabilities to analyze the content of the procedure manual in detail. Text analysis divides each paragraph and sentence of the procedure manual and understands the meaning of each. Syntactic analysis analyzes the sentence structure and clarifies the relationships between subjects, predicates, objects, etc. Semantic analysis involves understanding the meaning of sentences and grasping the intent and purpose of the procedure manual. Multimodal generation AI can also analyze visual information such as images and diagrams included in the procedure manual. This allows for a more comprehensive understanding of the manual's content and improves the accuracy of the analysis results. The generation AI extracts particularly important parts of the procedure manual and provides them as analysis results. For example, it picks out emphasized procedures and precautions within the manual and performs analysis based on them. This allows the analysis unit to analyze the manual's content in detail, extract important information, and provide it.

[0072] The judgment unit determines whether the operation follows the procedure based on the procedure manual analyzed by the analysis unit. The judgment is made based on criteria such as the degree of procedure conformance and the error detection method, but is not limited to these examples. For example, the judgment unit determines whether the operation follows the procedure based on the degree of procedure conformance. The judgment unit can also determine deviations from the procedure using the error detection method. The judgment unit can also determine the degree of procedure conformance using AI. For example, the judgment unit can determine the degree of procedure conformance using an AI model that takes the contents of the procedure manual and the contents of the operation as input and outputs the degree of procedure conformance. Based on the analysis results provided by the analysis unit, the judgment unit determines whether the operation follows the procedure described in the procedure manual. The degree of procedure conformance is evaluated by comparing each step of the procedure manual with the actual operation and determining whether they are consistent. The error detection method detects deviations from the procedure manual and issues a warning if the operation does not follow the procedure. The AI ​​model takes the contents of the procedure manual and the contents of the operation as input and outputs the degree of procedure conformance. As a result, the judgment unit can determine whether the operation is performed accurately based on the procedure manual and detect deviations from the procedure. The judgment unit compares each step of the procedure manual with the actual operation in detail to evaluate the degree of procedure conformity. For example, it compares the operation procedure described in the manual with the actual operation log and evaluates whether they match. The error detection method detects deviations from the procedure manual and issues a warning if the operation does not follow the procedure. The AI ​​model takes the contents of the procedure manual and the contents of the operation as input and outputs the degree of procedure conformity. This allows the judgment unit to determine whether the operation is being performed accurately according to the procedure manual and to detect deviations from the procedure.

[0073] The warning unit issues a warning if the judgment unit detects that the user is about to deviate from the procedure. Warnings are issued based on criteria such as the format of the warning message and the notification method, but are not limited to these examples. The warning unit issues a warning message if the user is about to deviate from the procedure. The warning unit can also issue warnings using notification methods. The warning unit can also issue warnings using AI. For example, the warning unit can issue a warning using an AI model that generates a warning message when the user is about to deviate from the procedure. The warning unit issues a warning if the user is about to deviate from the procedure based on information from the judgment unit. The warning message is intended to draw the user's attention to the operation that is about to deviate from the procedure. Notification methods include, for example, pop-up messages, voice notifications, and email notifications. The AI ​​model generates a warning message when the user is about to deviate from the procedure and issues a warning to the user. This allows the warning unit to quickly issue a warning when the user is about to deviate from the procedure, preventing operational errors. The warning unit issues a warning if the user is about to deviate from the procedure based on information from the judgment unit. Warning messages alert users who are about to deviate from the prescribed procedure. Notification methods include, for example, pop-up messages, voice notifications, and email notifications. The AI ​​model generates a warning message when the user is about to deviate from the procedure and issues a warning to the user. This allows the warning unit to quickly issue a warning when the user is about to deviate from the procedure, thus preventing operational errors.

[0074] The alert unit sends an alert to the administrator if the procedure is deviated from as determined by the judgment unit. Alerts are issued based on criteria such as the format of the alert message and the notification method, but are not limited to these examples. For example, the alert unit sends an alert message when the procedure is deviated. The alert unit can also send alerts using various notification methods. The alert unit can also send alerts using AI. For example, the alert unit can send alerts using an AI model that generates an alert message when the procedure is deviated. Based on information from the judgment unit, the alert unit sends an alert to the administrator when the procedure is deviated. The alert message is intended to draw the attention of the user performing an operation that deviates from the procedure. Notification methods include, for example, pop-up messages, voice notifications, and email notifications. The AI ​​model generates an alert message when the procedure is deviated and sends the alert to the administrator. This allows the alert unit to quickly issue an alert when the procedure is deviated and draw the attention of the administrator. Based on information from the judgment unit, the alert unit sends an alert to the administrator when the procedure is deviated. The alert message is intended to draw the attention of the user performing an operation that deviates from the procedure. Notification methods include, for example, pop-up messages, voice notifications, and email notifications. The AI ​​model generates an alert message and sends an alert to the administrator if the procedure is deviated from. This allows the alerting unit to quickly issue an alert when the procedure is deviated from, drawing the administrator's attention.

[0075] The import unit can import procedure manuals in text format using a generation AI. For example, the import unit can import procedure manuals in text format using a generation AI. For example, the import unit can import procedure manuals in text format using the generation AI's API. The import unit can also import procedure manuals by specifying the model version of the generation AI. For example, the import unit imports procedure manuals using the latest version of the generation AI. This makes the import of procedure manuals more efficient by using the generation AI. Some or all of the above processing in the import unit may be performed using the generation AI, or not. For example, the import unit can input the procedure manuals into the generation AI and have the generation AI import the procedure manuals.

[0076] The analysis unit can use a generating AI to determine whether the operations included in the procedure manual have been performed correctly. For example, the analysis unit can use a generating AI to determine whether the operations included in the procedure manual have been performed correctly. For example, the analysis unit can use the API of the generating AI to determine the operations in the procedure manual. The analysis unit can also specify the model version of the generating AI to determine the operations in the procedure manual. For example, the analysis unit can use the latest version of the generating AI to determine the operations in the procedure manual. This improves the accuracy of the procedure manual analysis by using a generating AI. Some or all of the above-described processes in the analysis unit may be performed using a generating AI, or they may not be performed using a generating AI. For example, the analysis unit can input the operations in the procedure manual into a generating AI and have the generating AI perform the determination of the operations in the procedure manual.

[0077] The warning unit can issue a warning if the procedure is about to be deviated from. For example, the warning unit can issue a warning message if the procedure is about to be deviated from. The warning unit can also issue a warning using a notification method if the procedure is about to be deviated from. For example, the warning unit can issue a warning by email if the procedure is about to be deviated from. The warning unit can also issue a warning using a chat tool if the procedure is about to be deviated from. For example, the warning unit can send a warning message using a chat tool if the procedure is about to be deviated from. This allows the worker to be alerted by issuing a warning if the procedure is about to be deviated from. Some or all of the above processing in the warning unit may be performed using AI, for example, or not using AI. For example, the warning unit can issue a warning using an AI model that generates a warning message if the procedure is about to be deviated from.

[0078] The alerting unit can send an alert to the administrator if the procedure is deviated from. For example, the alerting unit sends an alert when the procedure is deviated from. For example, the alerting unit sends an alert message when the procedure is deviated from. The alerting unit can also send an alert using a notification method when the procedure is deviated from. For example, the alerting unit sends an alert via email when the procedure is deviated from. The alerting unit can also send an alert via a chat tool when the procedure is deviated from. For example, the alerting unit sends an alert message via a chat tool when the procedure is deviated from. This facilitates the early resolution of problems by sending an alert to the administrator when the procedure is deviated from. Some or all of the above processing in the alerting unit may be performed using AI, for example, or not using AI. For example, the alerting unit can send an alert using an AI model that generates an alert message when the procedure is deviated from.

[0079] The alert unit can send alerts to administrators via email or chat tools. For example, the alert unit can send alert messages using email. The alert unit can also send alert messages using chat tools. For example, the alert unit can send alert messages using chat tools. This allows administrators to respond quickly by sending alerts via email or chat tools. Some or all of the above processing in the alert unit may be performed using AI, for example, or not using AI. For example, the alert unit can send alerts via email or chat tools using an AI model that generates alert messages.

[0080] The input unit can estimate the user's emotions and adjust the timing of instruction manual input based on the estimated user emotions. For example, if the user is stressed, the input unit can quickly input the instruction manual to prevent delays in work. If the user is relaxed, the input unit can also slowly input the instruction manual to encourage detailed review. For example, if the user is focused, the input unit can immediately input the instruction manual to avoid interrupting the workflow. This improves work efficiency by adjusting the timing of instruction manual input according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the input unit may be performed using, for example, generative AI or not using generative AI. For example, the data acquisition unit can input user emotion data into a generating AI, and have the generating AI adjust the timing of the instruction manual acquisition.

[0081] The import unit can perform version control of procedure manuals and prioritize importing the latest version. For example, the import unit can perform version control of procedure manuals and prioritize importing the latest version. For example, the import unit can automatically check the version of a procedure manual and prioritize importing the latest version. The import unit can also maintain a version history of the procedure manuals and allow referencing of past versions as needed. For example, the import unit can perform version control of procedure manuals and record the change history. This ensures that the latest version of the procedure manual is always available through version control. Some or all of the above processing in the import unit may be performed using, for example, a generation AI, or not. For example, the import unit can have a generation AI perform version control of the procedure manuals.

[0082] The import unit can automatically classify the contents of procedure manuals and import them into different categories. For example, the import unit can automatically classify the contents of procedure manuals and import them into different categories. For example, the import unit can analyze the contents of procedure manuals and classify them into different categories (e.g., safety procedures, operating procedures). The import unit can also automatically tag the contents of procedure manuals and import them into categories. For example, the import unit can analyze the contents of procedure manuals and automatically assign them to the relevant categories. This makes it easier to manage procedure manuals by automatically classifying their contents. Some or all of the above processing in the import unit may be performed using, for example, a generative AI, or without a generative AI. For example, the import unit can have a generative AI perform the classification of the contents of procedure manuals.

[0083] The input unit can estimate the user's emotions and determine the priority of the instruction manuals to input based on the estimated user emotions. For example, the input unit may prioritize important instruction manuals if the user is stressed. It may also prioritize detailed instruction manuals if the user is relaxed. For example, if the input unit is focused, it may prioritize instruction manuals related to the task. This improves work efficiency by prioritizing instruction manuals according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the input unit may be performed using a generative AI, or not. For example, the input unit can input user emotion data into a generative AI and have the generative AI determine the priority of the instruction manuals.

[0084] The input unit can automatically translate the language of the procedure manual and input it in multiple languages. For example, the input unit can automatically translate the language of the procedure manual and input it in multiple languages. For example, the input unit can automatically translate the content of the procedure manual and input it in multiple languages. The input unit can also automatically detect the language of the procedure manual and translate it as needed. For example, the input unit can analyze the content of the procedure manual and input it in multiple languages. This makes it possible to input in multiple languages ​​by automatically translating the language of the procedure manual. Some or all of the above processing in the input unit may be performed using, for example, a generative AI, or without a generative AI. For example, the input unit can have a generative AI perform the translation of the procedure manual.

[0085] The data acquisition unit can improve the accuracy of data acquisition by referring to related literature in the procedure manual. For example, the data acquisition unit can improve the accuracy of data acquisition by referring to related literature in the procedure manual. For example, the data acquisition unit can analyze the contents of the procedure manual and improve the accuracy of data acquisition by referring to related literature. The data acquisition unit can also automatically classify the contents of the procedure manual and improve the accuracy of data acquisition by referring to related literature. For example, the data acquisition unit can analyze the contents of the procedure manual and improve the accuracy of data acquisition by referring to related literature. As a result, the accuracy of data acquisition is improved by referring to related literature in the procedure manual. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the data acquisition unit can have a generation AI perform the referencing of related literature in the procedure manual.

[0086] The analysis unit can estimate the user's emotions and adjust the level of detail of the analysis based on the estimated emotions. For example, the analysis unit can estimate the user's emotions and adjust the level of detail of the analysis. For example, if the user is stressed, the analysis unit can lower the level of detail of the analysis and provide a concise result. Conversely, if the user is relaxed, the analysis unit can increase the level of detail of the analysis and provide a detailed result. For example, if the user is focused, the analysis unit can adjust the level of detail of the analysis to provide the optimal result. In this way, by adjusting the level of detail of the analysis according to the user's emotions, the optimal analysis result can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using a generative AI, for example, or without a generative AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the level of detail of the analysis.

[0087] The analysis unit can automatically summarize the contents of the procedure manual and highlight important parts. For example, the analysis unit can automatically summarize the contents of the procedure manual and highlight important parts. For example, the analysis unit can analyze the contents of the procedure manual and automatically highlight important parts. The analysis unit can also summarize the contents of the procedure manual and highlight important parts. For example, the analysis unit can automatically summarize the contents of the procedure manual and highlight important parts. This ensures that workers do not miss important information by summarizing the contents of the procedure manual and highlighting important parts. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can have a generative AI perform the summarization and highlighting of the procedure manual.

[0088] The analysis unit can automatically compare the contents of the procedure manuals and identify the differences between different versions. For example, the analysis unit can automatically compare the contents of the procedure manuals and identify the differences between different versions. For example, the analysis unit can analyze the contents of the procedure manuals and automatically identify the differences between different versions. The analysis unit can also compare the contents of the procedure manuals and identify the differences between different versions. For example, the analysis unit can automatically compare the contents of the procedure manuals and identify the differences between different versions. In this way, by comparing the contents of the procedure manuals, the differences between different versions can be identified. Some or all of the above processing in the analysis unit may be performed using, for example, a generation AI, or without a generation AI. For example, the analysis unit can have a generation AI perform the task of identifying the differences between versions of the procedure manuals.

[0089] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, the analysis unit can estimate the user's emotions and adjust the display method of the analysis results. For example, if the user is stressed, the analysis unit can provide a concise display method. The analysis unit can also provide a detailed display method if the user is relaxed. For example, if the user is focused, the analysis unit can provide an optimal display method. In this way, by adjusting the display method of the analysis results according to the user's emotions, the optimal display method can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using a generative AI, or not using a generative AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI adjust the display method of the analysis results.

[0090] The analysis unit can automatically convert the contents of the procedure manual into speech and provide the analysis results in speech. For example, the analysis unit can automatically convert the contents of the procedure manual into speech and provide the analysis results in speech. For example, the analysis unit can analyze the contents of the procedure manual and provide the analysis results in speech. The analysis unit can also convert the contents of the procedure manual into speech and provide the analysis results. For example, the analysis unit can automatically convert the contents of the procedure manual into speech and provide the analysis results in speech. In this way, by converting the contents of the procedure manual into speech, the analysis results can be provided in speech. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can have a generating AI perform the speech conversion of the procedure manual.

[0091] The analysis unit can improve the accuracy of its analysis by referring to related videos of the procedure manual. For example, the analysis unit can improve the accuracy of its analysis by referring to related videos of the procedure manual. For example, the analysis unit can analyze the contents of the procedure manual and improve the accuracy of its analysis by referring to related videos. The analysis unit can also automatically classify the contents of the procedure manual and improve the accuracy of its analysis by referring to related videos. For example, the analysis unit can analyze the contents of the procedure manual and improve the accuracy of its analysis by referring to related videos. As a result, the accuracy of the analysis is improved by referring to related videos of the procedure manual. Some or all of the above processing in the analysis unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis unit can have the generating AI perform the task of referring to related videos of the procedure manual.

[0092] The judgment unit can estimate the user's emotions and adjust the judgment criteria based on the estimated user emotions. For example, the judgment unit can estimate the user's emotions and adjust the judgment criteria. For example, if the user is stressed, the judgment unit can relax the judgment criteria to reduce errors. Conversely, if the user is relaxed, the judgment unit can tighten the judgment criteria to improve accuracy. For example, if the user is focused, the judgment unit can adjust the judgment criteria to provide the optimal result. In this way, by adjusting the judgment criteria according to the user's emotions, the optimal judgment result can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the judgment unit may be performed using a generative AI, or not using a generative AI. For example, the judgment unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the judgment criteria.

[0093] The judgment unit can monitor the contents of the procedure manual in real time and make an immediate judgment. For example, the judgment unit can monitor the contents of the procedure manual in real time and make an immediate judgment. For example, the judgment unit can analyze the contents of the procedure manual and make a real-time judgment. The judgment unit can also monitor the contents of the procedure manual and make an immediate judgment. For example, the judgment unit can monitor the contents of the procedure manual in real time and make an immediate judgment. This allows for immediate judgment by monitoring the contents of the procedure manual in real time. Some or all of the above-described processes in the judgment unit may be performed using, for example, a generative AI, or without a generative AI. For example, the judgment unit can have a generative AI perform real-time monitoring of the procedure manual.

[0094] The judgment unit can automatically learn the contents of the procedure manual and improve the accuracy of its judgment. For example, the judgment unit can automatically learn the contents of the procedure manual and improve the accuracy of its judgment. For example, the judgment unit can analyze and learn the contents of the procedure manual to improve the accuracy of its judgment. The judgment unit can also learn the contents of the procedure manual and improve the accuracy of its judgment. For example, the judgment unit can automatically learn the contents of the procedure manual and improve the accuracy of its judgment. As a result, the accuracy of the judgment is improved by automatically learning the contents of the procedure manual. Some or all of the above processing in the judgment unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the judgment unit can have a generative AI perform the learning of the procedure manual.

[0095] The judgment unit can estimate the user's emotions and adjust the display method of the judgment result based on the estimated user emotions. For example, the judgment unit can estimate the user's emotions and adjust the display method of the judgment result. For example, if the user is feeling stressed, the judgment unit can provide a concise display method. The judgment unit can also provide a detailed display method if the user is relaxed. For example, if the judgment unit is focused, it can provide an optimal display method. In this way, by adjusting the display method of the judgment result according to the user's emotions, the optimal display method can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the judgment unit may be performed using a generative AI, or not using a generative AI. For example, the judgment unit can input user emotion data into a generative AI and have the generative AI adjust the display method of the judgment result.

[0096] The judgment unit can automatically visualize the contents of the procedure manual and provide the judgment result visually. For example, the judgment unit can automatically visualize the contents of the procedure manual and provide the judgment result visually. For example, the judgment unit can analyze the contents of the procedure manual, visualize them, and provide the judgment result. The judgment unit can also visualize the contents of the procedure manual and provide the judgment result. For example, the judgment unit can automatically visualize the contents of the procedure manual and provide the judgment result visually. In this way, by visualizing the contents of the procedure manual, the judgment result can be provided visually. Some or all of the above processing in the judgment unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the judgment unit can have a generative AI perform the visualization of the procedure manual.

[0097] The judgment unit can improve the accuracy of its judgment by referring to relevant data in the procedure manual. For example, the judgment unit can improve the accuracy of its judgment by referring to relevant data in the procedure manual. For example, the judgment unit can analyze the contents of the procedure manual and improve the accuracy of its judgment by referring to relevant data. The judgment unit can also automatically classify the contents of the procedure manual and improve the accuracy of its judgment by referring to relevant data. For example, the judgment unit can analyze the contents of the procedure manual and improve the accuracy of its judgment by referring to relevant data. As a result, the accuracy of the judgment is improved by referring to relevant data in the procedure manual. Some or all of the above processing in the judgment unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the judgment unit can have the generating AI perform the referencing of relevant data in the procedure manual.

[0098] The warning unit can estimate the user's emotions and adjust the content of the warning based on the estimated emotions. For example, if the user is stressed, the warning unit can make the warning concise to reduce stress. If the user is relaxed, the warning unit can also provide a more detailed warning. For example, if the user is focused, the warning unit can provide the most appropriate warning. This allows the system to provide the most appropriate warning by adjusting the content according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the warning unit may be performed using a generative AI, or not. For example, the warning unit can input user emotion data into a generative AI and have the generative AI adjust the content of the warning.

[0099] The warning unit can adjust the timing of warnings and issue warnings early if it is about to deviate from the procedure. For example, the warning unit can adjust the timing of warnings and issue warnings early if it is about to deviate from the procedure. For example, the warning unit can issue warnings early if it is about to deviate from the procedure to draw the worker's attention. The warning unit can also adjust the timing of warnings and issue warnings at the appropriate time if it is about to deviate from the procedure. For example, the warning unit can adjust the timing of warnings and issue warnings early if it is about to deviate from the procedure. This allows the worker to be drawn to the warning by issuing warnings early if it is about to deviate from the procedure. Some or all of the above processing in the warning unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the warning unit can have a generating AI perform the adjustment of the warning timing.

[0100] The warning unit can automatically customize the content of warnings and take individual action when it is likely that the procedure will be deviated from. For example, the warning unit can automatically customize the content of warnings and take individual action when it is likely that the procedure will be deviated from. For example, the warning unit can automatically customize the content of warnings and prompt the worker to take appropriate action when it is likely that the procedure will be deviated from. The warning unit can also customize the content of warnings and take individual action when it is likely that the procedure will be deviated from. For example, the warning unit can automatically customize the content of warnings and take individual action when it is likely that the procedure will be deviated from. In this way, by customizing the content of warnings when it is likely that the procedure will be deviated from, the worker can be prompted to take appropriate action. Some or all of the above processing in the warning unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the warning unit can have a generation AI perform the customization of the content of warnings.

[0101] The warning unit can estimate the user's emotions and adjust the way the warning is displayed based on the estimated emotions. For example, the warning unit can provide a concise warning if the user is stressed, or a more detailed warning if the user is relaxed. For example, it can provide an optimal warning if the user is focused. By adjusting the warning display method according to the user's emotions, the optimal display method can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the warning unit may be performed using a generative AI, or not. For example, the warning unit can input user emotion data into a generative AI and have the generative AI adjust the way the warning is displayed.

[0102] The warning unit can automatically convert the warning content into voice and provide an audio warning when the procedure is about to be deviated from. For example, the warning unit can automatically convert the warning content into voice and provide an audio warning when the procedure is about to be deviated from. For example, the warning unit can automatically convert the warning content into voice and draw the worker's attention when the procedure is about to be deviated from. The warning unit can also convert the warning content into voice and provide a warning at an appropriate time when the procedure is about to be deviated from. For example, the warning unit can automatically convert the warning content into voice and provide an audio warning when the procedure is about to be deviated from. This allows the worker to be drawn to the warning content by converting it into voice when the procedure is about to be deviated from. Some or all of the above processing in the warning unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the warning unit can have a generation AI perform the voice conversion of the warning.

[0103] The warning unit can automatically visualize the content of a warning and provide a visual warning when a user is about to deviate from the procedure. For example, the warning unit can automatically visualize the content of a warning and provide a visual warning when a user is about to deviate from the procedure. For example, the warning unit can automatically visualize the content of a warning and draw the user's attention when a user is about to deviate from the procedure. The warning unit can also visualize the content of a warning and provide a warning at an appropriate time when a user is about to deviate from the procedure. For example, the warning unit can automatically visualize the content of a warning and provide a visual warning when a user is about to deviate from the procedure. This allows the system to draw the user's attention by visualizing the content of a warning when a user is about to deviate from the procedure. Some or all of the above processing in the warning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the warning unit can have a generative AI perform the visualization of the warning.

[0104] The alert unit can estimate the user's emotions and adjust the content of the alert based on the estimated emotions. For example, if the user is stressed, the alert unit can simplify the alert content to reduce stress. If the user is relaxed, the alert unit can also provide detailed alert content. For example, if the user is focused, the alert unit can provide optimal alert content. In this way, the system can provide optimal alert content by adjusting the alert content according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the alert unit may be performed using a generative AI, or not. For example, the alert unit can input user emotion data into a generative AI and have the generative AI adjust the content of the alert.

[0105] The alert unit can adjust the timing of alerts and issue alerts immediately if the procedure is deviated from. For example, the alert unit can adjust the timing of alerts and issue alerts immediately if the procedure is deviated from. For example, the alert unit can issue an alert immediately and notify the administrator if the procedure is deviated from. The alert unit can also adjust the timing of alerts and issue alerts at an appropriate time if the procedure is deviated from. For example, the alert unit can adjust the timing of alerts and issue alerts immediately if the procedure is deviated from. This allows for quick notification to the administrator by issuing an alert immediately if the procedure is deviated from. Some or all of the above processing in the alert unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the alert unit can have a generation AI perform the adjustment of the timing of alerts.

[0106] The alert unit can automatically customize the content of the alert and take individual action if the procedure is deviated from. For example, the alert unit can automatically customize the content of the alert and take individual action if the procedure is deviated from. For example, the alert unit can automatically customize the content of the alert and prompt the administrator to take appropriate action if the procedure is deviated from. The alert unit can also customize the content of the alert and take individual action if the procedure is deviated from. For example, the alert unit can automatically customize the content of the alert and take individual action if the procedure is deviated from. This allows the administrator to take appropriate action by customizing the content of the alert when the procedure is deviated from. Some or all of the above processing in the alert unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the alert unit can have a generation AI perform the customization of the alert content.

[0107] The alert unit can estimate the user's emotions and adjust the way the alert is displayed based on the estimated emotions. For example, the alert unit can provide a concise display if the user is stressed, or a more detailed display if the user is relaxed. For example, it can provide an optimal display if the user is focused. By adjusting the alert display according to the user's emotions, the system can provide the most appropriate display. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the alert unit may be performed using a generative AI, or not. For example, the alert unit can input user emotion data into a generative AI and have the generative AI adjust the way the alert is displayed.

[0108] The alert unit can automatically convert the content of an alert into speech and provide an audio alert if the procedure is deviated from. For example, the alert unit can automatically convert the content of an alert into speech and provide an audio alert if the procedure is deviated from. For example, if the procedure is deviated from, the alert unit can automatically convert the content of the alert into speech and notify the administrator. The alert unit can also convert the content of an alert into speech and provide an alert at an appropriate time if the procedure is deviated from. For example, if the procedure is deviated from, the alert unit can automatically convert the content of the alert into speech and provide an audio alert. This allows for quick notification to the administrator by converting the content of the alert into speech when the procedure is deviated from. Some or all of the above processing in the alert unit may be performed using, for example, a generation AI, or without a generation AI. For example, the alert unit can have a generation AI perform the voice conversion of the alert.

[0109] The alert unit can automatically visualize the content of an alert and provide a visual alert when a procedure is deviated from. For example, the alert unit can automatically visualize the content of an alert and provide a visual alert when a procedure is deviated from. For example, the alert unit can automatically visualize the content of an alert and notify the administrator when a procedure is deviated from. The alert unit can also visualize the content of an alert and provide an alert at an appropriate time when a procedure is deviated from. For example, the alert unit can automatically visualize the content of an alert and provide a visual alert when a procedure is deviated from. This allows for quick notification to the administrator by visualizing the content of the alert when a procedure is deviated from. Some or all of the above processing in the alert unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the alert unit can have a generation AI perform the visualization of the alert.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The import unit can automatically tag procedure manuals based on their content when they are imported. For example, the import unit can analyze the content of the procedure manuals, extract relevant keywords, and tag them. The import unit can also categorize and tag the procedure manuals based on their content. For example, the import unit can analyze the content of the procedure manuals and categorize them into categories such as safety procedures, operating procedures, and maintenance procedures, and then tag them. This allows for efficient management of the procedure manual content. Some or all of the above processing in the import unit may be performed using a generation AI, or it may be performed without using a generation AI.

[0112] The analysis unit can automatically summarize the contents of a procedure manual based on its analysis. For example, the analysis unit can analyze the contents of the procedure manual, extract important parts, and summarize them. Furthermore, when analyzing and summarizing the contents of the procedure manual, the analysis unit can also highlight important parts. For example, the analysis unit can analyze the contents of the procedure manual, highlight important parts, and then summarize them. This allows for an efficient understanding of the contents of the procedure manual. Some or all of the above-described processes in the analysis unit may be performed using a generative AI, or they may be performed without using a generative AI.

[0113] The judgment unit can automatically detect errors based on the content of the procedure manual when analyzing its contents. For example, the judgment unit analyzes the contents of the procedure manual and determines whether the operations described in the manual are being performed correctly. The judgment unit can also analyze the contents of the procedure manual and, if an error occurs, display the details of the error. For example, the judgment unit analyzes the contents of the procedure manual and, if an error occurs, displays the details of the error. This allows for an efficient understanding of the contents of the procedure manual. Some or all of the above-described processes in the judgment unit may be performed using a generation AI, or they may be performed without using a generation AI.

[0114] The warning unit can automatically customize the content of warnings when a worker is about to deviate from the procedure. For example, the warning unit can customize the content of warnings according to the worker's skill level when a worker is about to deviate from the procedure. The warning unit can also customize the content of warnings based on the worker's past error history when a worker is about to deviate from the procedure. For example, the warning unit can customize the content of warnings based on the worker's past error history when a worker is about to deviate from the procedure. This allows the warning unit to provide the worker with an appropriate warning when a worker is about to deviate from the procedure. Some or all of the above processing in the warning unit may be performed using generative AI, or it may be performed without using generative AI.

[0115] The alerting unit can automatically customize the content of alerts when procedures are deviated from. For example, the alerting unit can customize the content of alerts according to the administrator's skill level when procedures are deviated from. The alerting unit can also customize the content of alerts based on the administrator's past error history when procedures are deviated from. For example, the alerting unit can customize the content of alerts based on the administrator's past error history when procedures are deviated from. This allows the administrator to receive appropriate alerts when procedures are deviated from. Some or all of the above processing in the alerting unit may be performed using a generative AI, or it may be performed without using a generative AI.

[0116] The input unit can estimate the user's emotions and adjust the method of inputting the procedure manual based on the estimated emotions. For example, if the user is stressed, the input unit can input the procedure manual quickly to prevent delays in work. Conversely, if the user is relaxed, the input unit can input the procedure manual slowly to encourage detailed review. For example, if the user is focused, the input unit can input the procedure manual immediately to avoid interrupting the workflow. In this way, work efficiency is improved by adjusting the method of inputting the procedure manual according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above processing in the input unit may be performed using generative AI or not.

[0117] The analysis unit can estimate the user's emotions and adjust the level of detail of the analysis based on the estimated emotions. For example, if the user is stressed, the analysis unit can lower the level of detail of the analysis and provide a concise result. Conversely, if the user is relaxed, the analysis unit can increase the level of detail of the analysis and provide a detailed result. For example, if the user is focused, the analysis unit can adjust the level of detail of the analysis to provide the optimal result. In this way, by adjusting the level of detail of the analysis according to the user's emotions, the optimal analysis result can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above processing in the analysis unit may be performed using generative AI, or it may be performed without using generative AI.

[0118] The judgment unit can estimate the user's emotions and adjust the judgment criteria based on the estimated emotions. For example, if the judgment unit is stressed, it can relax the judgment criteria to reduce errors. Conversely, if the user is relaxed, it can tighten the judgment criteria to improve accuracy. For example, if the user is focused, it can adjust the judgment criteria to provide the optimal result. In this way, by adjusting the judgment criteria according to the user's emotions, the optimal judgment result can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above processing in the judgment unit may be performed using generative AI or not.

[0119] The warning unit can estimate the user's emotions and adjust the content of the warning based on the estimated emotions. For example, if the user is stressed, the warning unit can make the warning concise to reduce stress. Conversely, if the user is relaxed, the warning unit can provide a more detailed warning. For example, if the user is focused, the warning unit can provide the most appropriate warning. This allows for the provision of optimal warnings by adjusting the content according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the above-described processing in the warning unit may be performed using generative AI, or it may be performed without using generative AI.

[0120] The alert unit can estimate the user's emotions and adjust the content of the alert based on the estimated emotions. For example, if the user is stressed, the alert unit can simplify the content of the alert to reduce stress. Conversely, if the user is relaxed, the alert unit can provide a more detailed alert. For example, if the user is focused, the alert unit can provide the most appropriate alert content. This allows for the provision of optimal alert content by adjusting it according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Some or all of the processing described above in the alert unit may be performed using generative AI, or it may be performed without using generative AI.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The input unit captures the procedure manual. This manual includes operating instructions, manuals, and guidelines. The input unit can digitize and capture the procedure manual using scanning technology. It can also directly capture procedure manuals submitted in digital format, and can read printed procedure manuals using OCR technology. For example, it can scan with a high-resolution scanner and convert the information into text using OCR technology. Step 2: The analysis unit analyzes the procedure manuals imported by the import unit. Analysis is performed using methods such as text analysis, syntactic analysis, and semantic analysis. It is also possible to analyze the procedure manuals using generative AI and extract and analyze important parts. For example, the content of the procedure manuals can be analyzed using text generation AI or multimodal generation AI. Step 3: The judgment unit determines whether the operation follows the procedure based on the procedure manual analyzed by the analysis unit. The judgment is made based on criteria such as the degree of procedure agreement and the error detection method. The degree of procedure agreement can also be determined using AI. For example, the judgment can be made using an AI model that takes the contents of the procedure manual and the contents of the operation as input and outputs the degree of procedure agreement. Step 4: The warning unit issues a warning if the judgment unit determines that the procedure is about to be deviated from. Warnings are issued based on criteria such as the format of the warning message and the notification method. AI can be used to generate warning messages and issue warnings when the procedure is about to be deviated from. Step 5: The alert unit sends an alert to the administrator if the procedure is deviated from by the judgment unit. Alerts are triggered based on criteria such as the format of the alert message and the notification method. AI can be used to generate alert messages and send alerts when the procedure is deviated from.

[0123] 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.

[0124] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the data acquisition unit, analysis unit, determination unit, warning unit, and alert unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data acquisition unit can digitize and acquire the procedure manual using scanning technology by the control unit 46A of the smart device 14. The analysis unit can analyze the procedure manual using generated AI by the identification processing unit 290 of the data processing unit 12. The determination unit can determine whether the operation is in accordance with the procedure based on the degree of procedure conformance by the identification processing unit 290 of the data processing unit 12. The warning unit can issue a warning message if the operation is about to deviate from the procedure by the control unit 46A of the smart device 14. The alert unit can send an alert to the administrator if the operation deviates from the procedure by the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] 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.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0130] 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.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0132] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] 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.

[0134] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] 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.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the data acquisition unit, analysis unit, determination unit, warning unit, and alert unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the data acquisition unit can digitize and acquire the procedure manual using scanning technology by the control unit 46A of the smart glasses 214. The analysis unit can analyze the procedure manual using generated AI by the identification processing unit 290 of the data processing unit 12. The determination unit can determine, for example, whether the operation follows the procedure based on the degree of procedure conformance by the identification processing unit 290 of the data processing unit 12. The warning unit can, for example, issue a warning message if the user is about to deviate from the procedure by the control unit 46A of the smart glasses 214. The alert unit can, for example, send an alert to the administrator if the user deviates from the procedure by the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] 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.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0146] 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.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0148] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] 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.

[0150] 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.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] 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.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the data acquisition unit, analysis unit, determination unit, warning unit, and alert unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data acquisition unit can digitize and acquire the procedure manual using scanning technology by the control unit 46A of the headset terminal 314. The analysis unit can analyze the procedure manual using generated AI by the identification processing unit 290 of the data processing unit 12. The determination unit can determine whether the operation follows the procedure based on the degree of procedure conformance by the identification processing unit 290 of the data processing unit 12. The warning unit can issue a warning message if the procedure is about to be deviated from by the control unit 46A of the headset terminal 314. The alert unit can send an alert to the administrator if the procedure is deviated from by the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0162] 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.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0164] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] 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.

[0166] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] 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.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] 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.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the acquisition unit, analysis unit, determination unit, warning unit, and alert unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit can digitize and acquire the procedure manual using scanning technology by the control unit 46A of the robot 414. The analysis unit can analyze the procedure manual using generated AI by the specific processing unit 290 of the data processing unit 12. The determination unit can determine whether the operation is in accordance with the procedure based on the degree of procedure conformance by the specific processing unit 290 of the data processing unit 12. The warning unit can issue a warning message if the robot 414 is about to deviate from the procedure, for example by the control unit 46A of the robot 414. The alert unit can send an alert to the administrator if the procedure is deviated by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0176] 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.

[0177] Figure 9 shows the 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.

[0178] 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.

[0179] 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.

[0180] 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, and motorcycles, 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 based, for example, 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.

[0181] 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."

[0182] 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.

[0183] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] 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 other things 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.

[0193] 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.

[0194] (Note 1) The import unit for importing the procedure manual, An analysis unit analyzes the procedure manual acquired by the aforementioned acquisition unit, A determination unit determines whether the operation is in accordance with the procedure based on the procedure manual analyzed by the analysis unit, A warning unit that issues a warning if the determination unit determines that the procedure is likely to be deviated from, The system includes an alert unit that sends an alert to the administrator if the procedure is deviated from by the determination unit. A system characterized by the following features. (Note 2) The aforementioned intake unit is Use a generative AI to import procedure manuals in text format. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Use a generated AI to determine whether the operations included in the procedure manual are being performed correctly. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned warning unit is It issues a warning if you are about to deviate from the procedure. The system described in Appendix 1, characterized by the features described herein. (Note 5) The alert unit is, Send an alert to the administrator if the procedure is deviated from. The system described in Appendix 1, characterized by the features described herein. (Note 6) The alert unit is, Send alerts to administrators via email or chat tools. The system described in Appendix 5, characterized by the features described herein. (Note 7) The aforementioned intake unit is The system estimates the user's emotions and adjusts the timing of manual import based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned intake unit is Implement version control for procedure manuals and prioritize importing the latest version. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned intake unit is The contents of the procedure manual are automatically categorized and imported into different categories. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned intake unit is Estimate the user's emotions and determine the priority of the procedures to implement based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned intake unit is The system automatically translates the language of the instruction manual and imports it in multiple languages. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned intake unit is Refer to the relevant documentation in the procedure manual to improve the accuracy of data acquisition. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates the user's emotions and adjusts the level of detail in the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, Automatically summarizes the contents of the procedure manual and highlights the important parts. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, Automatically compare the contents of the procedure manual and identify differences between different versions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, The manual's contents are automatically converted into speech, and the analysis results are provided in audio format. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, Refer to the related videos in the procedure manual to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 19) The determination unit, The system estimates the user's emotions and adjusts the criteria for judgment based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The determination unit, The contents of the procedure manual are monitored in real time, and decisions are made immediately. The system described in Appendix 1, characterized by the features described herein. (Note 21) The determination unit, The system automatically learns the contents of the procedure manual and improves the accuracy of its judgments. The system described in Appendix 1, characterized by the features described herein. (Note 22) The determination unit, The system estimates the user's emotions and adjusts how the judgment results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The determination unit, The contents of the procedure manual are automatically visualized, and the judgment results are provided visually. The system described in Appendix 1, characterized by the features described herein. (Note 24) The determination unit, Improve the accuracy of the judgment by referring to the relevant data in the procedure manual. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned warning unit is It estimates the user's emotions and adjusts the content of the warning based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned warning unit is If the procedure is about to be deviated from, the timing of the warning will be adjusted to issue a warning earlier. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned warning unit is If the procedure is about to be deviated from, the warning content will be automatically customized and individual actions will be taken. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned warning unit is It estimates the user's emotions and adjusts how warnings are displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned warning unit is If you are about to deviate from the procedure, the system will automatically convert the warning into audio and provide a voice alert. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned warning unit is If you are about to deviate from the procedure, the warning content will be automatically visualized and a visual warning will be provided. The system described in Appendix 1, characterized by the features described herein. (Note 31) The alert unit is, It estimates the user's emotions and adjusts the content of alerts based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The alert unit is, If the procedure is deviated from, adjust the timing of the alert and issue an alert immediately. The system described in Appendix 1, characterized by the features described herein. (Note 33) The alert unit is, If the procedure is deviated from, the alert content will be automatically customized and individual actions will be taken. The system described in Appendix 1, characterized by the features described herein. (Note 34) The alert unit is, It estimates the user's emotions and adjusts how alerts are displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The alert unit is, If the procedure is deviated from, the alert content will be automatically converted into voice and an audio alert will be provided. The system described in Appendix 1, characterized by the features described herein. (Note 36) The alert unit is, If the procedure is deviated from, the content of the alert is automatically visualized and the alert is provided visually. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The import unit for importing the procedure manual, An analysis unit analyzes the procedure manual acquired by the aforementioned acquisition unit, A determination unit determines whether the operation is in accordance with the procedure based on the procedure manual analyzed by the analysis unit, A warning unit that issues a warning if the determination unit determines that the procedure is likely to be deviated from, The system includes an alert unit that sends an alert to the administrator if the procedure is deviated from by the determination unit. A system characterized by the following features.

2. The aforementioned intake unit is Use a generation AI to import the procedure manual in text format. The system according to feature 1.

3. The aforementioned analysis unit, Use a generated AI to determine whether the operations included in the procedure manual are being performed correctly. The system according to feature 1.

4. The aforementioned warning unit is It issues a warning if you are about to deviate from the procedure. The system according to feature 1.

5. The alert unit is, Send an alert to the administrator if the procedure is deviated from. The system according to feature 1.

6. The alert unit is, Send alerts to administrators via email or chat tools. The system according to claim 5, characterized in that it is the same as described in claim 5.

7. The aforementioned intake unit is The system estimates the user's emotions and adjusts the timing of manual import based on those estimated emotions. The system according to feature 1.

8. The aforementioned intake unit is Implement version control for procedure manuals and prioritize importing the latest version. The system according to feature 1.

Images