System

Abstract

A system is provided.SOLUTION: A system including an information processing means for learning service contents and business procedures in advance, a data collection means for collecting exchanges in a communication tool after occurrence of an accident as text data, an analysis means for analyzing the collected text data and automatically generating report contents about details of a malfunction, an influence range, a cause, a resolution date and time, and a recurrence prevention measure, and an output means for outputting the automatically generated report contents.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In service operations, unexpected accidents are unavoidable, no matter how careful employees are. However, reporting accidents after they occur and formulating measures to prevent recurrence is costly and time-consuming, placing a burden on employees. In this situation, there is a need for a system that can quickly and accurately automatically generate accident reports and preventive measures, reducing the burden on employees and improving work efficiency. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system including an information processing means that has learned service content and business procedures in advance, a data collection means that collects exchanges via communication tools after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report on the details of the malfunction, the scope of impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an output means that outputs the automatically generated report. Specifically, by having AI learn service content and business procedures in advance, and analyzing the text data after an accident occurs to automatically generate appropriate report content, and outputting the report content in a specified format, the system reduces the workload of employees and enables quick and efficient accident response.

[0006] "Information processing means" refers to a device or program that allows the system to learn the service content and business procedures in advance.

[0007] "Data collection means" refers to a device or program that records and collects exchanges made via communication tools after an accident as text data.

[0008] The "analysis means" is a device or program that analyzes the details of the accident, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence based on the collected text data, and automatically generates report content.

[0009] The "output means" is a device or program for arranging the report content generated by the analysis means into a predetermined format and outputting it to the user as a report. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0011] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0012] First, the terms used in the following description will be explained.

[0013] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0014] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0015] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0016] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0017] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0018] [First embodiment]

[0019] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0020] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0021] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0022] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0023] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0024] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0025] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0026] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0027] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0028] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0029] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0030] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0031] The present invention provides a system for automatically generating report content and preventive measures quickly and efficiently when an unexpected accident occurs during service operation. The system includes an information processing unit, a data collection unit, an analysis unit, and an output unit.

[0032] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The server uses this as an information processing tool and has the AI ​​learn the contents of the document. Based on the learned service content and business procedures, the AI ​​builds a knowledge base to quickly derive appropriate countermeasures.

[0033] Next, when an accident occurs, the user reports the details of the accident through a communication tool (e.g., a chat system or email). The device uses this communication as a means of collecting data and records it as text data in real time. The recorded data is automatically sent to the server.

[0034] The server uses the transmitted text data as an analytical tool, and the AI ​​begins its analysis. The AI ​​extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence from the text data, and automatically generates a report. This report is then formatted appropriately based on the analysis results.

[0035] The server then uses the prepared report content as an output means and saves it in a specified format (e.g., PDF).Finally, the automatically generated report is sent to the user, who can check the report and make additional corrections or comments as necessary.

[0036] Specific examples

[0037] 1. Initial Setup:

[0038] The user prepares an operation manual and an abnormality response procedure manual for the "customer support system" and uploads them to the server.

[0039] The server uses AI to learn from the uploaded documents and understand how to respond if a system abnormality occurs.

[0040] 2. Information gathering after an accident:

[0041] Users can use the chat system to report:

[0042] "System went down at 13:00"

[0043] "All users are affected"

[0044] "The cause is server overload"

[0045] The device automatically records this exchange as text data and sends it to the server.

[0046] 3. Data Analysis:

[0047] The server uses AI to analyze the recorded text data.

[0048] On the server, AI extracts from the text data the following: "System down," "Affecting all users," "Cause is server overload," "Estimated time of resolution is 2:00 p.m.", and "Increasing server resources to prevent recurrence."

[0049] 4. Automatic report generation:

[0050] The server automatically generates a report based on the extracted information.

[0051] Example: "A system outage occurred on October 12, 2023 at 1:00 PM. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence."

[0052] 5. Report printing and distribution:

[0053] The server saves the generated report in PDF format and sends it to the user.

[0054] The user checks the report received by email and makes corrections or comments as necessary.

[0055] This will speed up the response after an accident occurs and significantly reduce the effort required by the user.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] Data preparation (user)

[0059] The user prepares a text file or document that specifically describes the service content and business procedures.

[0060] Example: "Service Contents_Business Procedures.docx" contains an overview of the service, daily business procedures, and common problems and their solutions.

[0061] Step 2:

[0062] Data upload (user)

[0063] The user uploads the prepared text files or documents to the server via the terminal.

[0064] Uploading is done using a dedicated upload function.

[0065] Step 3:

[0066] Data learning (server)

[0067] The server takes the uploaded documents and feeds them into an AI model, which learns important information.

[0068] The information to be learned includes business procedures, how to respond to errors, and examples of past accidents.

[0069] Step 4:

[0070] Information collection in the event of an accident (terminal)

[0071] When an accident occurs, users report the details of the accident using a chat system or email.

[0072] The device records these interactions as text data in real time.

[0073] Step 5:

[0074] Data transmission (terminal)

[0075] The terminal automatically transmits the recorded text data to the server.

[0076] The transmission can be by a periodically executed process or by a trigger event.

[0077] Step 6:

[0078] Data reception (server)

[0079] The server receives the text data sent from the terminal.

[0080] The received data includes detailed information such as the time of the accident, the extent of the impact, and the cause.

[0081] Step 7:

[0082] Text analysis (server)

[0083] The server inputs the received text data into the AI ​​and analyzes the details of the accident, the type of malfunction, the extent of the impact, the cause, etc.

[0084] The AI ​​uses natural language processing techniques to extract important keywords and phrases.

[0085] Step 8:

[0086] Organizing analysis results (server)

[0087] The server organizes the report content based on the information extracted by the AI.

[0088] Specifically, it summarizes details of the problem, the scope of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0089] Step 9:

[0090] Report template generation (server)

[0091] The server generates a report template based on the organized information.

[0092] The template applies pre-trained formats.

[0093] Step 10:

[0094] Final check (server)

[0095] The server performs a final check on the generated report template to check for errors.

[0096] Step 11:

[0097] Report storage (server)

[0098] The server stores the final verified report in a format such as PDF.

[0099] The saved files contain detailed information about the accident, its scope of impact, causes, and countermeasures.

[0100] Step 12:

[0101] Sending reports (server)

[0102] The server automatically sends the generated report to the user.

[0103] It is usually sent through communication tools such as email.

[0104] Step 13:

[0105] User Verification (User)

[0106] The user checks the report received by email and makes additional corrections or comments as necessary.

[0107] Once the final report is completed, it will be shared with internal stakeholders.

[0108] Example 1

[0109] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0110] In modern service operations, when unexpected accidents occur, a rapid and accurate response is required. Traditional manual methods of creating reports and documenting preventative measures require a lot of time and effort, and there is also a risk of information being overlooked or mistyped. This can delay the response to the accident and cause further problems. To address these issues, this invention aims to provide a system that automatically generates rapid and efficient report content and preventative measures when an accident occurs.

[0111] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0112] In this invention, the server includes an information processing means that has learned the service content and business procedures in advance, a data collection means that collects communication via the communication means after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report on the details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an output means that saves the automatically generated report in a predetermined format and provides the information. This enables a quick response after an accident occurs and efficient report creation.

[0113] "Information processing means" refers to devices and programs that allow AI to learn service content and business procedures.

[0114] "Data collection means" refers to a device and program that collects text data exchanged through communication means after an accident occurs.

[0115] "Analysis means" refers to a device and program that analyzes collected text data, extracts details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence, and automatically generates report content.

[0116] "Output means" refers to a device and program that saves the automatically generated report content in a predetermined format and provides the information.

[0117] "Service Content" refers to the full range of functionality and support provided by a particular Service.

[0118] "Business procedures" refers to documents that describe specific work procedures and response methods for service operation.

[0119] "Means of communication" refers to tools for exchanging text data, such as chat systems and email.

[0120] "Text data" refers to character data sent and received via communication means.

[0121] "Details of the malfunction" refers to the specific content and circumstances of the accident or problem.

[0122] "Scope of impact" refers to the range and scale of the impact caused by the malfunction.

[0123] "Cause" refers to the reason or background behind the occurrence of the defect.

[0124] "Resolution date and time" refers to the time when the defect is scheduled to be resolved or the time when it is actually resolved.

[0125] "Measures to prevent recurrence" refers to specific measures to prevent the recurrence of similar defects.

[0126] "Report" refers to a detailed written report of a defect generated by the analysis means.

[0127] "Prescribed format" refers to the standard file format (e.g., PDF) in which the generated report content is stored and provided.

[0128] The present invention provides a system that automatically generates report content and preventive measures quickly and efficiently when an unexpected accident occurs during service operation. This system includes an information processing unit, a data collection unit, an analysis unit, and an output unit. Specific embodiments of the system are described below.

[0129] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of an accident and how to respond. Specifically, the user uses a text editor or similar tool to create an operation manual for the "customer support system" or an abnormality response procedure manual, and then uploads it to the server.

[0130] The server uses the uploaded documents as a means of information processing and uses a generative AI model (e.g., BERT or GPT) to learn the contents of the documents, allowing the AI ​​to build a knowledge base that can quickly derive countermeasures based on service content and business procedures.

[0131] Next, when an accident occurs, the user reports the details of the accident using a communication method such as a chat system or email. For example, they might report something like, "The system went down at 1:00 PM," "All users are affected," or "The cause was a server overload." The device uses this exchange as a means of collecting data and records it as text data. This recorded data is automatically sent to the server.

[0132] The server uses the text data as an analytical tool, and the AI ​​begins analyzing it. In the analytical tool, the AI ​​extracts important information from the text data, such as "System down," "All users affected," "Cause is server overload," "Estimated resolution time is 2:00 PM," and "Server resources will be increased to prevent recurrence."

[0133] The server then automatically generates a report based on the extracted information. The generated report is formatted using a template engine. Specifically, the report generated looks like this:

[0134] "A system outage occurred at 1:00 PM on October 12, 2023. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence."

[0135] The server saves the report in a predetermined format, such as PDF, and sends it to the user. A PDF generator library (e.g., PDFKit or ReportLab) is used for saving the report. The user can then review the report received by email and make any necessary corrections or comments.

[0136] This will speed up the response after an accident occurs and significantly reduce the effort required by the user.

[0137] Example prompt sentence:

[0138] "The system went down at 13:00. All users are affected. The cause was server overload."

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1:

[0141] The user prepares and creates text files and documents that detail the service content and business procedures. These include system operation manuals and abnormality response procedures. Specifically, the user uses a text editor to create a detailed business procedure manual that describes how to operate the "customer support system" and the response procedures in the event of an abnormality. This document becomes the input data.

[0142] Step 2:

[0143] Users upload text files or documents they have created to a server via their terminal. Specifically, they use a web interface or dedicated upload tool to send the document to a specified location. At this stage, the input data is the text file or document, and the output is a notification that the upload has been completed.

[0144] Step 3:

[0145] The server uses the uploaded document as a means of information processing, learning the document's contents using a generative AI model (e.g., BERT or GPT). The input here is the document uploaded by the user, and the output is a knowledge base in which the AI ​​understands the service content and business procedures. Specifically, the server performs text analysis of the document's contents and stores them in a database using a learning algorithm.

[0146] Step 4:

[0147] When an accident occurs, the user reports the details of the accident using a communication method such as a chat system or email. The specific report content is "The system went down at 13:00," "All users are affected," and "The cause was a server overload." The input in this step is a text message containing the details of the accident, and the output is the generation of text data.

[0148] Step 5:

[0149] The device uses this exchange as a data collection tool and records it as text data in real time. The input is the text message sent and received via the communication tool, and the output is the recorded text data. Specific operations include recording the contents of chats and emails in a database using system logs and storage functions.

[0150] Step 6:

[0151] The recorded text data is automatically sent to the server, which receives it. The input here is the text data sent from the device, and the output is the text data saved on the server. Specifically, the server receives the data using an API or data transfer service and stores it in a database.

[0152] Step 7:

[0153] The server uses the transmitted text data as an analytical tool and begins analysis using a generative AI model. During this analysis, important information is extracted from the text data, such as "System down," "All users affected," "Cause is server overload," "Estimated resolution time is 2:00 PM," and "Server resources will be increased to prevent recurrence." The input is the received text data, and the output is the extracted important information. Specifically, the data is analyzed using a pixel processing engine and natural language processing algorithms.

[0154] Step 8:

[0155] The server automatically generates a report based on the extracted information. The input is the key information extracted through analysis, and the output is the report content arranged in a report template. Specifically, a template engine is used to embed the extracted information into a specified report format.

[0156] Step 9:

[0157] The server saves the generated report in PDF format. The tool used here is a PDF generator library (e.g. PDFKit or ReportLab). The input is the formatted report content, and the output is a PDF file. Specifically, the report content is formatted using a template engine, and the file is generated using a PDF generator.

[0158] Step 10:

[0159] Finally, the server sends the generated PDF to the user. The input is the PDF file, and the output is a notification of completion of sending. Specifically, it uses a mail library (e.g., SMTP) to send an email with the PDF file attached to the user's address. The user checks the received report and makes additional corrections or comments as necessary.

[0160] (Application example 1)

[0161] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0162] It is extremely important to quickly and efficiently respond to quality and production line problems that occur within a factory and to appropriately implement measures to prevent recurrence. However, with conventional systems, it took a long time to report accidents and formulate preventive measures, and there was a tendency for human error and omissions to occur. In particular, manually creating complex accident reports and preventive measures required a great deal of effort and time, which was a major obstacle in workplaces where a rapid response was required. Given this current situation, there was a need for a system that could automatically create detailed reports when an accident occurred and propose efficient preventive measures.

[0163] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0164] In this invention, the server includes an information processing means that has been trained on service content and business procedures in advance, a data collection means that collects exchanges via communication tools after an accident occurs as text data, an analysis means that uses a generative AI model to analyze the collected text data and automatically generate a report on the details of the defect, the scope of impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an output means that converts the automatically generated report into a PDF in a predetermined format and outputs it. This makes it possible to quickly and efficiently create a detailed report and propose measures to prevent recurrence when an accident occurs in a factory.

[0165] "Information processing means" refers to a means for learning the service content and business procedures in advance and then performing processing to derive countermeasures based on that information.

[0166] "Data collection means" refers to a means of collecting exchanges via communication tools after an accident occurs as text data.

[0167] A "generative AI model" is an artificial intelligence model that analyzes collected data and automatically generates report content.

[0168] The "analysis means" is a means for analyzing collected text data using a generative AI model and automatically generating a report containing details of the defect, the scope of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0169] The "output means" is a means for converting the automatically generated report into a PDF in a predetermined format and saving or transmitting it to the user.

[0170] "PDF" stands for Portable Document Format, a format for electronically storing and distributing documents while preserving their layout.

[0171] This invention is a "Smart Factory Incident Manager" system that responds quickly and efficiently to quality and production line problems that occur within a factory. Specific processing procedures for implementing this system will be described below.

[0172] System Overview

[0173] The system mainly consists of the following elements:

[0174] 1. Information processing method: Study documents such as factory operation manuals and abnormality response procedures in advance to build a knowledge base.

[0175] 2. Data collection method: Collect text data from interactions using communication tools after the accident.

[0176] 3. Analysis method: The collected text data is analyzed using a generative AI model to automatically generate a report containing details of the defect, the scope of impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0177] 4. Output method: The automatically generated report is converted into a PDF in a specified format and saved or sent to the user.

[0178] Hardware and Software

[0179] The hardware and software used to implement this system are as follows:

[0180] Hardware: Factory robots (e.g. KUKA, Fanuc)

[0181] software:

[0182] Python: a programming language

[0183] OpenAI GPT-3: Generative AI model

[0184] pdfkit: A library for converting HTML and strings to PDF

[0185] Detailed procedure

[0186] 1. Information gathering and learning

[0187] The user prepares documents such as operation manuals and abnormality response procedures and uploads them to the server.

[0188] The server reads these documents and builds a knowledge base by training the AI.

[0189] 2. Collecting accident information

[0190] When an accident occurs, users can report the details of the accident via chat system or email. For example, "Production line 2 stopped at 14:00 on October 12, 2023. The cause was a robot arm malfunction. The expected time of resolution is 15:30."

[0191] The terminal records this exchange as text data and transmits it to the server.

[0192] 3. Analysis and report generation

[0193] The server analyzes the transmitted text data using a generative AI model (OpenAI GPT-3) to extract details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0194] Report content is automatically generated based on the collected data.

[0195] 4. PDF Output

[0196] The server converts the generated report content into a PDF in a predetermined format and saves it using an output means.

[0197] If necessary, the server sends the PDF to the user.

[0198] Specific examples

[0199] For example, based on the accident information "Occurrence date and time: October 12, 2023, 14:00," "Affected area: Production line 2 stopped," "Cause: Robot arm failure," and "Estimated time of resolution: October 12, 2023, 15:30," the following prompt sentence can be used to have the AI ​​generate a report:

[0200] Prompt Sentence Examples

[0201] Date and time of occurrence: October 12, 2023, 14:00

[0202] Affected area: Production line 2 stopped

[0203] Cause: Robot arm malfunction

[0204] Estimated time of resolution: October 12, 2023, 15:30

[0205] Use this information to generate a report that includes details of the incident, the extent of the impact, the cause, how it was resolved, and how to prevent it from happening again.

[0206] This makes it possible to quickly and efficiently prepare detailed reports and propose measures to prevent recurrence when an accident occurs within a factory.

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] The user prepares documents such as operation manuals and abnormality response procedures and uploads them to the server.

[0210] Input: Documents (text files) such as operation manuals and abnormality response procedures

[0211] Processing: The server loads these documents and trains a generative AI model to build a knowledge base.

[0212] Output: Trained knowledge base

[0213] Step 2:

[0214] If an accident occurs, users can report the details of the accident via a chat system or email.

[0215] Input: Detailed information about the accident (e.g., "Production Line 2 stopped at 14:00 on October 12, 2023. The cause was a robot arm malfunction. The estimated time of resolution is 15:30.")

[0216] Processing: The device records this exchange as text data and sends it to the server.

[0217] Output: Collected accident report text data

[0218] Step 3:

[0219] The server analyzes the transmitted text data using a generative AI model to extract details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0220] Input: Collected accident report text data

[0221] Processing: The generative AI model analyzes the text data and extracts information such as defect details, scope of impact, cause, resolution date and time, and measures to prevent recurrence.

[0222] Output: Extracted information (details of the defect, scope of impact, cause, resolution date and time, measures to prevent recurrence)

[0223] Step 4:

[0224] The server automatically generates a report based on the extracted information.

[0225] Input: Extracted information

[0226] Processing: The generative AI model automatically generates report content in a specified format based on the extracted information.

[0227] Output: Auto-generated report text

[0228] Step 5:

[0229] The server converts the automatically generated report into a PDF in a predetermined format and saves or transmits it to the user.

[0230] Input: Auto-generated report text

[0231] Processing: The server converts the report to PDF using the pdfkit library, saves it in the required format, and sends the PDF to the user if necessary.

[0232] Output: Report in PDF format

[0233] In this way, the system automates all processes, making it possible to quickly and efficiently create accident reports and implement measures to prevent recurrence.

[0234] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0235] The present invention is a system that automatically generates report content and preventive measures quickly and efficiently when an accident occurs during service operation. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the tone and expression of the report content, enabling a more appropriate response. The system of the present invention has information processing means, data collection means, analysis means, output means, and an emotion engine.

[0236] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The server uses this as an information processing tool and has the AI ​​learn the contents of the document. Based on the learned service content and business procedures, the AI ​​builds a knowledge base to quickly derive appropriate countermeasures.

[0237] Next, when an accident occurs, the user reports the details of the accident through a communication tool (e.g., a chat system or email). The device uses this communication as a means of collecting data and records it as text data in real time. The recorded data is automatically sent to the server.

[0238] The server uses the transmitted text data as an analytical tool, and the AI ​​begins its analysis. The AI ​​extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence from the text data, and automatically generates a report. This report is then formatted appropriately based on the analysis results and passed to the emotion engine.

[0239] The emotion engine analyzes the user's emotional state from their interactions. For example, it reads emotions such as stress or impatience from the user's writing and reflects them in the analysis results. If necessary, it adjusts the tone and expression of the report and converts it into a more appropriate format.

[0240] The server then uses the prepared report content as an output means and saves it in a specified format (e.g., PDF).Finally, the automatically generated report is sent to the user, who can check the report and make additional corrections or comments as necessary.

[0241] Specific examples

[0242] 1. Initial Setup:

[0243] The user prepares an operation manual and an abnormality response procedure manual for the "customer support system" and uploads them to the server.

[0244] The server uses AI to learn from the uploaded documents and understand how to respond if a system abnormality occurs.

[0245] 2. Information gathering after an accident:

[0246] Users can use the chat system to report:

[0247] "System went down at 13:00"

[0248] "All users are affected"

[0249] "The cause is server overload"

[0250] The device automatically records this exchange as text data and sends it to the server.

[0251] 3. Data Analysis:

[0252] The server uses AI to analyze the recorded text data.

[0253] On the server, AI extracts from the text data the following: "System down," "Affecting all users," "Cause is server overload," "Estimated time of resolution is 2:00 p.m.", and "Increasing server resources to prevent recurrence."

[0254] 4. Sentiment analysis and adjustment:

[0255] The server uses an emotion engine to analyze emotions such as "stress" and "anxiety" from user interactions.

[0256] The server adjusts the tone of the report based on the emotional information. For example, if an urgent part expresses strong emotions, it will describe that part in more detail and add expressions to soften the emotions.

[0257] 5. Automatic report generation:

[0258] The server automatically generates a final report based on the extracted information and the tone adjusted by the emotion engine.

[0259] Example: "A system outage occurred on October 12, 2023 at 1:00 PM. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence. Users have reported that the issue is urgent and causing increased stress, so special attention is required."

[0260] 6. Report printing and distribution:

[0261] The server saves the generated report in PDF format and sends it to the user.

[0262] The user checks the report received by email and makes corrections or comments as necessary.

[0263] This not only speeds up response after an accident occurs, but also enables more appropriate responses that take into account the user's emotions.

[0264] The processing flow will be explained below.

[0265] Step 1:

[0266] Data preparation (user)

[0267] Users prepare text files or documents detailing the service content and business procedures.

[0268] Example: "Service Contents_Business Procedures.docx" contains an overview of the service, daily business procedures, and past problems and their solutions.

[0269] Step 2:

[0270] Data upload (user)

[0271] The user uploads the prepared text files or documents to the server via the terminal.

[0272] Users transfer files to the server using a dedicated upload interface.

[0273] Step 3:

[0274] Data learning (server)

[0275] The server receives the uploaded documents and feeds them into the AI ​​learning model.

[0276] The server builds a knowledge base by having the AI ​​learn business procedures and problem-solving measures.

[0277] Step 4:

[0278] Information collection in the event of an accident (terminal)

[0279] When an accident occurs, users report the details of the accident using a chat system or email.

[0280] The device records these interactions as text data in real time.

[0281] Step 5:

[0282] Data transmission (terminal)

[0283] The terminal automatically transmits the recorded text data to the server.

[0284] The transmission process is performed by periodic synchronization or trigger events.

[0285] Step 6:

[0286] Receive text data (server)

[0287] The server receives the text data sent from the terminal.

[0288] The received data includes details such as the time of the accident, the extent of the impact, and the cause.

[0289] Step 7:

[0290] Text analysis (server)

[0291] The server inputs the received text data into an AI analysis engine and performs the analysis.

[0292] AI extracts details of the accident, the type of malfunction, the extent of the impact, and the cause.

[0293] Step 8:

[0294] Sentiment analysis (server)

[0295] The server utilizes an emotion engine to analyze the user's emotional state from the text data.

[0296] For example, it can determine whether a user is feeling anxious or stressed from the tone of the text or specific keywords.

[0297] Step 9:

[0298] Organizing analysis results (server)

[0299] The server organizes the analysis results based on the information extracted by the AI.

[0300] This includes not only details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, but also the user's emotional state.

[0301] Step 10:

[0302] Report template generation (server)

[0303] The server generates a report template based on the organized information.

[0304] The template applies a prescribed format and also adjusts the tone based on emotion.

[0305] Step 11:

[0306] Final check (server)

[0307] The server performs a final check of the generated report template to check for any defects.

[0308] If an error is detected, data analysis and sentiment analysis are performed again.

[0309] Step 12:

[0310] Report storage (server)

[0311] The server stores the final verified report in PDF format.

[0312] The saved file contains detailed information about the accident, including an overview of the incident, the extent of the impact, the cause, countermeasures, and the results of user sentiment analysis.

[0313] Step 13:

[0314] Sending reports (server)

[0315] The server automatically sends the generated report to the user.

[0316] Typically, email is used to send reports and confirm receipt of the reports.

[0317] Step 14:

[0318] User Verification (User)

[0319] The user checks the report received by email to ensure there are no errors in the content.

[0320] Make any necessary corrections or comments, and share the final report internally.

[0321] Example 2

[0322] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0323] While it is necessary to take prompt and accurate countermeasures when an accident occurs during service operation, many systems require time-consuming manual report creation and the formulation of preventive measures, which can increase user dissatisfaction and stress.Furthermore, it is difficult to create reports that take emotional evaluation into account, and reports are not always written in an appropriate tone or with appropriate expressions.

[0324] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an information processing means that has previously learned the service content and business procedures, a data collection means that collects exchanges via communication means after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report containing details of the malfunction, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an emotion analysis means that analyzes the emotional state of the user and adjusts the tone and expression of the report. This makes it possible to automatically generate a quick and accurate report when an accident occurs and to report in an appropriate tone that takes emotions into consideration.

[0325] "Information processing means" refers to a method or device for learning service content and business procedures in advance.

[0326] "Data collection means" refers to a method or device for collecting communication via means of communication after an accident occurs as text data.

[0327] "Analysis means" refers to a method or device for analyzing collected text data and automatically generating a report on the details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0328] "Output means" refers to a method or device for outputting the automatically generated report content.

[0329] "Emotion analysis means" refers to a method or device for analyzing a user's emotional state and adjusting the tone and expression of the report.

[0330] This invention is a system that automatically generates report content and preventive measures quickly and efficiently when an accident occurs during service operation. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the tone and expression of the report content, enabling more appropriate responses.

[0331] Specifically, the system includes "information processing means," "data collection means," "analysis means," "output means," and "emotion analysis means."

[0332] First, the user prepares a text file or document (e.g., PDF or Word file) detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The information processing means used for the hardware or software includes natural language processing libraries (e.g., NLTK, SpaCy) and machine learning frameworks (e.g., TensorFlow, PyTorch). The server trains an AI on the uploaded document and builds a knowledge base that determines how to respond when a system abnormality occurs.

[0333] Next, when an accident occurs, the user reports the details of the accident through a communication method such as a chat system or email. The device records this report in real time as text data and sends it to the server. Specifically, the user reports, for example, "The system went down at 1:00 PM," "All users are affected," and "The cause was a server overload."

[0334] The server uses the received text data as an analytical tool, and the AI ​​begins its analysis. Software used includes text analysis tools (e.g., ElasticSearch, Apache Lucene). Details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence are extracted from the text data and automatically generated as a report.

[0335] The generated report content is analyzed using a sentiment analysis means to determine the emotional state of the user's interactions. For example, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) to read "stress" or "urgency" from the user's message and reflects the results in the report content. The sentiment analysis means adjusts the tone and expression of the report content as necessary and converts it into a more appropriate format.

[0336] Finally, the server saves the generated report in a specified format (e.g., PDF) and sends it to the user, using software such as document generation tools (e.g., LaTeX, ReportLab). Finally, the user receives the report and can make additional corrections or comments if necessary.

[0337] Prompt Sentence Examples

[0338] Examples of prompts for specific scenarios:

[0339] "The system went down at 1:00 PM, affecting all users. The cause was server overload. Please automatically generate a report outlining effective measures to prevent recurrence."

[0340] As a result, not only can responses after an accident be made more quickly, but more appropriate responses can be made that take into account the user's emotions.

[0341] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0342] Step 1: Prepare and upload your documents

[0343] The user prepares a text file or document (e.g., PDF or Word file) that describes the service content and business procedures. Specifically, the user prepares their company's service manual or process document.

[0344] The user uploads the prepared document to the server via the terminal. The input is a file containing a service manual or procedure manual. The output is the document uploaded to the server.

[0345] Step 2: The learning process

[0346] The server uses the received documents as a means of information processing and trains the AI. Specifically, it analyzes the document content using natural language processing libraries (e.g., NLTK, SpaCy) and machine learning frameworks (e.g., TensorFlow, PyTorch) and adds it to the training dataset.

[0347] The server builds a knowledge base based on what the AI ​​has learned. The uploaded documents are used as input, and the output is an AI model that has learned how to respond to system anomalies.

[0348] Step 3: Report the incident

[0349] When an accident occurs, users report details using communication methods such as chat systems or email. Specifically, users send information such as "The system went down at 13:00," "All users are affected," and "The cause is server overload" via chat messages or email.

[0350] The input is text data describing the details of the accident, and the output is text data in which the report content is recorded in real time.

[0351] Step 4: Data collection

[0352] The device records the accident report exchange as text data in real time and sends it to the server. Specifically, the device automatically captures chat logs and email content, organizes it into an appropriate format, and uploads it to the server.

[0353] The input is the text data of the accident report submitted by the user, and the output is well-formed text data sent to the server.

[0354] Step 5: Data analysis

[0355] The server uses the received text data as an analytical tool, and the AI ​​begins its analysis. Specifically, it uses a text analysis tool (e.g., ElasticSearch, Apache Lucene) to extract important information from the received data, such as "system down," "affecting all users," and "cause of server overload."

[0356] The server updates the knowledge base based on the analysis results and formats them appropriately. The input is the text data received by the server, and the output is a draft of the accident report.

[0357] Step 6: Emotion analysis and tone adjustment

[0358] The server uses an emotion engine to analyze the user's emotional state from their interactions. Specifically, the emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) analyzes emotions such as "stress" and "urgency" from the user's message and generates a score.

[0359] The server adjusts the tone of the report based on the emotional information: the inputs are the analyzed emotional scores and the draft incident report, and the output is the emotionally adjusted final report.

[0360] Step 7: Automatic report generation

[0361] The server automatically generates a final report based on the extracted information and the results of sentiment analysis. Specifically, it uses document generation tools such as LaTeX and ReportLab to format the text data and generate the report.

[0362] The inputs are the sentiment analysis results and the contents of the incident report, and the output is the final report in a digital format (e.g., PDF).

[0363] Step 8: Print and distribute the report

[0364] The server saves the generated report in a specified format (e.g. PDF) and sends it to the user. Specifically, the server saves the generated report in a specified directory and sends it to the user via email or system notification.

[0365] The user reviews the received report and makes any necessary corrections or comments. The generated report is used as input, and the final report including the user's feedback is obtained as output.

[0366] (Application example 2)

[0367] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0368] When a system failure or accident occurs at a logistics center, a prompt and appropriate response is required. However, conventional methods have the drawback of taking time to create a report and formulate measures to prevent recurrence, and it is also difficult to respond in a way that appropriately reflects the stress and impatience of the person in charge. To solve these problems, the present invention aims to provide a system that quickly and automatically generates accident report content and adjusts the tone of the report taking into account the user's emotional state.

[0369] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0370] In this invention, the server includes an information processing means that has learned service content and business procedures in advance, a data collection means that collects exchanges via communication tools after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report containing details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, an emotion analysis means that adjusts the tone and expression of the automatically generated report, and an output means that outputs the automatically generated report. This enables the rapid automatic generation of accident report content, and further enables a more appropriate response by appropriately adjusting the tone to reflect the user's emotional state.

[0371] "Information processing means" refers to a means for learning service content and business procedures in advance.

[0372] "Data collection means" refers to a means of collecting exchanges via communication tools after an accident occurs as text data.

[0373] The "analysis means" is a means for analyzing the collected text data and automatically generating a report containing details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0374] "Emotion analysis means" is a means for analyzing the user's emotional state in order to adjust the tone and expression of the automatically generated report content.

[0375] The "output means" is a means for converting the automatically generated report content into a predetermined format and sending it to the user.

[0376] The present invention is a system for automatically generating report content and preventive measures in the event of an accident at a logistics center in a prompt and appropriate manner. A specific embodiment of the system will be described below.

[0377] System Configuration

[0378] The system consists of the following main components:

[0379] Information processing means: A means of learning service content and business procedures in advance. For example, uploading business manuals and abnormality response procedures to an AI model on a server and having it learn the information.

[0380] Data collection method: A method for collecting text data from communication tools (e.g., chat systems, emails) after an accident occurs. For example, data entered on a smartphone or device is sent to a server in real time.

[0381] Analysis method: Analyzes collected text data and automatically generates a report containing details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence. This is done using an AI model (e.g., OpenAI GPT-3).

[0382] Sentiment analysis: Analyzing the user's emotional state in order to adjust the tone and expression of the automatically generated report. For example, using a sentiment analysis tool such as TextBlob.

[0383] Output means: A means to convert the automatically generated report content into a specified format (e.g. PDF) and send it to the user. For example, generate a PDF using the FPDF library.

[0384] Program processing explanation

[0385] The server first learns the logistics center's operational procedures and abnormality response procedures as an information processing tool in advance, allowing the AI ​​model on the server to understand basic response methods for various accidents and malfunctions.

[0386] When an accident occurs, users report the details of the accident using the communication tools on their smartphones. This data is collected as text data by the smartphone as a data collection means and sent to the server in real time.

[0387] The server analyzes the received text data using an AI model (OpenAI GPT-3), which extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and automatically generates a report.

[0388] The automatically generated report content is analyzed using emotion analysis to detect the user's emotional state (e.g., stress or impatience from the text) and adjust the tone and expression accordingly. For example, TextBlob is used to analyze the user's emotional state.

[0389] Finally, the server formats the report content (e.g., PDF) and sends it to the user via an output means, which uses the FPDF library to generate the PDF.

[0390] Examples of concrete examples and prompts

[0391] In a specific scenario, if a system error occurs at a distribution center, an employee enters the following details into their smartphone:

[0392] Example: "At 2:30 PM, shipping processing was halted due to a system error. All centers were affected. The cause was a database overload. The error is expected to be resolved by 3:30 PM."

[0393] This data is sent in real time to a server where an AI model generates the following prompts and creates a report:

[0394] Example prompt: "At 2:30 PM, a system error halted shipping processing. This affected all centers. The cause was a database overload. The error is expected to be resolved by 3:30 PM. Please use these details to create an incident report for the distribution center."

[0395] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0396] Step 1:

[0397] The user uploads the logistics center's work procedures and anomaly response procedures to the server. The server receives this as an information processing tool and trains the AI ​​model. The input is the work procedures and anomaly response procedures file, and the output is the trained AI model. The specific operations performed in this step are for the server to receive the files, read them sequentially into the AI ​​model, and have it learn the service content and work procedures.

[0398] Step 2:

[0399] When an accident occurs, the user uses a smartphone communication tool to input details of the accident (e.g., time of occurrence, extent of impact, cause, estimated time to resolve, etc.). The input is detailed information about the accident entered by the user, and the output is the accident information as text data. Specifically, the user uses the smartphone's chat system or email to enter the details of the accident in text format, which is then recorded on the device.

[0400] Step 3:

[0401] The terminal transmits the collected text data to the server in real time. The input is the text data generated in step 2, and the output is the text data transmitted to the server. The specific operation performed in this step is that the terminal transmits the text data to the server using an appropriate network protocol.

[0402] Step 4:

[0403] The server uses an AI model to analyze the received text data. The input is the text data sent to the server, and the output is the analysis results regarding the details of the defect, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence. Specifically, the AI ​​model (e.g., OpenAI GPT-3) analyzes the text data, extracts each item, and automatically generates the report content.

[0404] Step 5:

[0405] The automatically generated report content uses emotion analysis tools to analyze the user's emotional state (e.g., stress or impatience) and adjusts the tone and expression accordingly. The input is the automatically generated report content and text data indicating the user's emotional state, and the output is the report content with the adjusted tone and expression. Specifically, it uses emotion analysis tools such as TextBlob to analyze the user's emotional state, and the AI ​​model adjusts the vocabulary and style to be appropriate.

[0406] Step 6:

[0407] The server finally formats the report content into a specified format (e.g. PDF) and sends it to the user. The input is the report content with adjusted tone and expression, and the output is a report formatted in the specified format (PDF). Specifically, the server uses the FPDF library to generate the report content as a PDF and sends it to the user via email or other means.

[0408] This will enable the logistics center to respond to accident reports quickly and appropriately.

[0409] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0410] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0411] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0412] [Second embodiment]

[0413] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0414] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0415] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0416] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0417] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0418] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0419] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0420] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0421] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0422] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0423] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0424] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0425] The present invention provides a system for automatically generating report content and preventive measures quickly and efficiently when an unexpected accident occurs during service operation. The system includes an information processing unit, a data collection unit, an analysis unit, and an output unit.

[0426] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The server uses this as an information processing tool and has the AI ​​learn the contents of the document. Based on the learned service content and business procedures, the AI ​​builds a knowledge base to quickly derive appropriate countermeasures.

[0427] Next, when an accident occurs, the user reports the details of the accident through a communication tool (e.g., a chat system or email). The device uses this communication as a means of collecting data and records it as text data in real time. The recorded data is automatically sent to the server.

[0428] The server uses the transmitted text data as an analytical tool, and the AI ​​begins its analysis. The AI ​​extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence from the text data, and automatically generates a report. This report is then formatted appropriately based on the analysis results.

[0429] The server then uses the prepared report content as an output means and saves it in a specified format (e.g., PDF).Finally, the automatically generated report is sent to the user, who can check the report and make additional corrections or comments as necessary.

[0430] Specific examples

[0431] 1. Initial Setup:

[0432] The user prepares an operation manual and an abnormality response procedure manual for the "customer support system" and uploads them to the server.

[0433] The server uses AI to learn from the uploaded documents and understand how to respond if a system abnormality occurs.

[0434] 2. Information gathering after an accident:

[0435] Users can use the chat system to report:

[0436] "System went down at 13:00"

[0437] "All users are affected"

[0438] "The cause is server overload"

[0439] The device automatically records this exchange as text data and sends it to the server.

[0440] 3. Data Analysis:

[0441] The server uses AI to analyze the recorded text data.

[0442] On the server, AI extracts from the text data the following: "System down," "Affecting all users," "Cause is server overload," "Estimated time of resolution is 2:00 p.m.", and "Increasing server resources to prevent recurrence."

[0443] 4. Automatic report generation:

[0444] The server automatically generates a report based on the extracted information.

[0445] Example: "A system outage occurred on October 12, 2023 at 1:00 PM. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence."

[0446] 5. Report printing and distribution:

[0447] The server saves the generated report in PDF format and sends it to the user.

[0448] The user checks the report received by email and makes corrections or comments as necessary.

[0449] This will speed up the response after an accident occurs and significantly reduce the effort required by the user.

[0450] The processing flow will be explained below.

[0451] Step 1:

[0452] Data preparation (user)

[0453] The user prepares a text file or document that specifically describes the service content and business procedures.

[0454] Example: "Service Contents_Business Procedures.docx" contains an overview of the service, daily business procedures, and common problems and their solutions.

[0455] Step 2:

[0456] Data upload (user)

[0457] The user uploads the prepared text files or documents to the server via the terminal.

[0458] Uploading is done using a dedicated upload function.

[0459] Step 3:

[0460] Data learning (server)

[0461] The server takes the uploaded documents and feeds them into an AI model, which learns important information.

[0462] The information to be learned includes business procedures, how to respond to errors, and examples of past accidents.

[0463] Step 4:

[0464] Information collection in the event of an accident (terminal)

[0465] When an accident occurs, users report the details of the accident using a chat system or email.

[0466] The device records these interactions as text data in real time.

[0467] Step 5:

[0468] Data transmission (terminal)

[0469] The terminal automatically transmits the recorded text data to the server.

[0470] The transmission can be by a periodically executed process or by a trigger event.

[0471] Step 6:

[0472] Data reception (server)

[0473] The server receives the text data sent from the terminal.

[0474] The received data includes detailed information such as the time of the accident, the extent of the impact, and the cause.

[0475] Step 7:

[0476] Text analysis (server)

[0477] The server inputs the received text data into the AI ​​and analyzes the details of the accident, the type of malfunction, the extent of the impact, the cause, etc.

[0478] The AI ​​uses natural language processing techniques to extract important keywords and phrases.

[0479] Step 8:

[0480] Organizing analysis results (server)

[0481] The server organizes the report content based on the information extracted by the AI.

[0482] Specifically, it summarizes details of the problem, the scope of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0483] Step 9:

[0484] Report template generation (server)

[0485] The server generates a report template based on the organized information.

[0486] The template applies pre-trained formats.

[0487] Step 10:

[0488] Final check (server)

[0489] The server performs a final check on the generated report template to check for errors.

[0490] Step 11:

[0491] Report storage (server)

[0492] The server stores the final verified report in a format such as PDF.

[0493] The saved files contain detailed information about the accident, its scope of impact, causes, and countermeasures.

[0494] Step 12:

[0495] Sending reports (server)

[0496] The server automatically sends the generated report to the user.

[0497] It is usually sent through communication tools such as email.

[0498] Step 13:

[0499] User Verification (User)

[0500] The user checks the report received by email and makes additional corrections or comments as necessary.

[0501] Once the final report is completed, it will be shared with internal stakeholders.

[0502] Example 1

[0503] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0504] In modern service operations, when unexpected accidents occur, a rapid and accurate response is required. Traditional manual methods of creating reports and documenting preventative measures require a lot of time and effort, and there is also a risk of information being overlooked or mistyped. This can delay the response to the accident and cause further problems. To address these issues, this invention aims to provide a system that automatically generates rapid and efficient report content and preventative measures when an accident occurs.

[0505] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0506] In this invention, the server includes an information processing means that has learned the service content and business procedures in advance, a data collection means that collects communication via the communication means after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report on the details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an output means that saves the automatically generated report in a predetermined format and provides the information. This enables a quick response after an accident occurs and efficient report creation.

[0507] "Information processing means" refers to devices and programs that allow AI to learn service content and business procedures.

[0508] "Data collection means" refers to a device and program that collects text data exchanged through communication means after an accident occurs.

[0509] "Analysis means" refers to a device and program that analyzes collected text data, extracts details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence, and automatically generates report content.

[0510] "Output means" refers to a device and program that saves the automatically generated report content in a predetermined format and provides the information.

[0511] "Service Content" refers to the full range of functionality and support provided by a particular Service.

[0512] "Business procedures" refers to documents that describe specific work procedures and response methods for service operation.

[0513] "Means of communication" refers to tools for exchanging text data, such as chat systems and email.

[0514] "Text data" refers to character data sent and received via communication means.

[0515] "Details of the malfunction" refers to the specific content and circumstances of the accident or problem.

[0516] "Scope of impact" refers to the range and scale of the impact caused by the malfunction.

[0517] "Cause" refers to the reason or background behind the occurrence of the defect.

[0518] "Resolution date and time" refers to the time when the defect is scheduled to be resolved or the time when it is actually resolved.

[0519] "Measures to prevent recurrence" refers to specific measures to prevent the recurrence of similar defects.

[0520] "Report" refers to a detailed written report of a defect generated by the analysis means.

[0521] "Prescribed format" refers to the standard file format (e.g., PDF) in which the generated report content is stored and provided.

[0522] The present invention provides a system that automatically generates report content and preventive measures quickly and efficiently when an unexpected accident occurs during service operation. This system includes an information processing unit, a data collection unit, an analysis unit, and an output unit. Specific embodiments of the system are described below.

[0523] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of an accident and how to respond. Specifically, the user uses a text editor or similar tool to create an operation manual for the "customer support system" or an abnormality response procedure manual, and then uploads it to the server.

[0524] The server uses the uploaded documents as a means of information processing and uses a generative AI model (e.g., BERT or GPT) to learn the contents of the documents, allowing the AI ​​to build a knowledge base that can quickly derive countermeasures based on service content and business procedures.

[0525] Next, when an accident occurs, the user reports the details of the accident using a communication method such as a chat system or email. For example, they might report something like, "The system went down at 1:00 PM," "All users are affected," or "The cause was a server overload." The device uses this exchange as a means of collecting data and records it as text data. This recorded data is automatically sent to the server.

[0526] The server uses the text data as an analytical tool, and the AI ​​begins analyzing it. In the analytical tool, the AI ​​extracts important information from the text data, such as "System down," "All users affected," "Cause is server overload," "Estimated resolution time is 2:00 PM," and "Server resources will be increased to prevent recurrence."

[0527] The server then automatically generates a report based on the extracted information. The generated report is formatted using a template engine. Specifically, the report generated looks like this:

[0528] "A system outage occurred at 1:00 PM on October 12, 2023. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence."

[0529] The server saves the report in a predetermined format, such as PDF, and sends it to the user. A PDF generator library (e.g., PDFKit or ReportLab) is used for saving the report. The user can then review the report received by email and make any necessary corrections or comments.

[0530] This will speed up the response after an accident occurs and significantly reduce the effort required by the user.

[0531] Example prompt sentence:

[0532] "The system went down at 13:00. All users are affected. The cause was server overload."

[0533] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0534] Step 1:

[0535] The user prepares and creates text files and documents that detail the service content and business procedures. These include system operation manuals and abnormality response procedures. Specifically, the user uses a text editor to create a detailed business procedure manual that describes how to operate the "customer support system" and the response procedures in the event of an abnormality. This document becomes the input data.

[0536] Step 2:

[0537] Users upload text files or documents they have created to a server via their terminal. Specifically, they use a web interface or dedicated upload tool to send the document to a specified location. At this stage, the input data is the text file or document, and the output is a notification that the upload has been completed.

[0538] Step 3:

[0539] The server uses the uploaded document as a means of information processing, learning the document's contents using a generative AI model (e.g., BERT or GPT). The input here is the document uploaded by the user, and the output is a knowledge base in which the AI ​​understands the service content and business procedures. Specifically, the server performs text analysis of the document's contents and stores them in a database using a learning algorithm.

[0540] Step 4:

[0541] When an accident occurs, the user reports the details of the accident using a communication method such as a chat system or email. The specific report content is "The system went down at 13:00," "All users are affected," and "The cause was a server overload." The input in this step is a text message containing the details of the accident, and the output is the generation of text data.

[0542] Step 5:

[0543] The device uses this exchange as a data collection tool and records it as text data in real time. The input is the text message sent and received via the communication tool, and the output is the recorded text data. Specific operations include recording the contents of chats and emails in a database using system logs and storage functions.

[0544] Step 6:

[0545] The recorded text data is automatically sent to the server, which receives it. The input here is the text data sent from the device, and the output is the text data saved on the server. Specifically, the server receives the data using an API or data transfer service and stores it in a database.

[0546] Step 7:

[0547] The server uses the transmitted text data as an analytical tool and begins analysis using a generative AI model. During this analysis, important information is extracted from the text data, such as "System down," "All users affected," "Cause is server overload," "Estimated resolution time is 2:00 PM," and "Server resources will be increased to prevent recurrence." The input is the received text data, and the output is the extracted important information. Specifically, the data is analyzed using a pixel processing engine and natural language processing algorithms.

[0548] Step 8:

[0549] The server automatically generates a report based on the extracted information. The input is the key information extracted through analysis, and the output is the report content arranged in a report template. Specifically, a template engine is used to embed the extracted information into a specified report format.

[0550] Step 9:

[0551] The server saves the generated report in PDF format. The tool used here is a PDF generator library (e.g. PDFKit or ReportLab). The input is the formatted report content, and the output is a PDF file. Specifically, the report content is formatted using a template engine, and the file is generated using a PDF generator.

[0552] Step 10:

[0553] Finally, the server sends the generated PDF to the user. The input is the PDF file, and the output is a notification of completion of sending. Specifically, it uses a mail library (e.g., SMTP) to send an email with the PDF file attached to the user's address. The user checks the received report and makes additional corrections or comments as necessary.

[0554] (Application example 1)

[0555] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0556] It is extremely important to quickly and efficiently respond to quality and production line problems that occur within a factory and to appropriately implement measures to prevent recurrence. However, with conventional systems, it took a long time to report accidents and formulate preventive measures, and there was a tendency for human error and omissions to occur. In particular, manually creating complex accident reports and preventive measures required a great deal of effort and time, which was a major obstacle in workplaces where a rapid response was required. Given this current situation, there was a need for a system that could automatically create detailed reports when an accident occurred and propose efficient preventive measures.

[0557] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0558] In this invention, the server includes an information processing means that has been trained on service content and business procedures in advance, a data collection means that collects exchanges via communication tools after an accident occurs as text data, an analysis means that uses a generative AI model to analyze the collected text data and automatically generate a report on the details of the defect, the scope of impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an output means that converts the automatically generated report into a PDF in a predetermined format and outputs it. This makes it possible to quickly and efficiently create a detailed report and propose measures to prevent recurrence when an accident occurs in a factory.

[0559] "Information processing means" refers to a means for learning the service content and business procedures in advance and then performing processing to derive countermeasures based on that information.

[0560] "Data collection means" refers to a means of collecting exchanges via communication tools after an accident occurs as text data.

[0561] A "generative AI model" is an artificial intelligence model that analyzes collected data and automatically generates report content.

[0562] The "analysis means" is a means for analyzing collected text data using a generative AI model and automatically generating a report containing details of the defect, the scope of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0563] The "output means" is a means for converting the automatically generated report into a PDF in a predetermined format and saving or transmitting it to the user.

[0564] "PDF" stands for Portable Document Format, a format for electronically storing and distributing documents while preserving their layout.

[0565] This invention is a "Smart Factory Incident Manager" system that responds quickly and efficiently to quality and production line problems that occur within a factory. Specific processing procedures for implementing this system will be described below.

[0566] System Overview

[0567] The system mainly consists of the following elements:

[0568] 1. Information processing method: Study documents such as factory operation manuals and abnormality response procedures in advance to build a knowledge base.

[0569] 2. Data collection method: Collect text data from interactions using communication tools after the accident.

[0570] 3. Analysis method: The collected text data is analyzed using a generative AI model to automatically generate a report containing details of the defect, the scope of impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0571] 4. Output method: The automatically generated report is converted into a PDF in a specified format and saved or sent to the user.

[0572] Hardware and Software

[0573] The hardware and software used to implement this system are as follows:

[0574] Hardware: Factory robots (e.g. KUKA, Fanuc)

[0575] software:

[0576] Python: a programming language

[0577] OpenAI GPT-3: Generative AI model

[0578] pdfkit: A library for converting HTML and strings to PDF

[0579] Detailed procedure

[0580] 1. Information gathering and learning

[0581] The user prepares documents such as operation manuals and abnormality response procedures and uploads them to the server.

[0582] The server reads these documents and builds a knowledge base by training the AI.

[0583] 2. Collecting accident information

[0584] When an accident occurs, users can report the details of the accident via chat system or email. For example, "Production line 2 stopped at 14:00 on October 12, 2023. The cause was a robot arm malfunction. The expected time of resolution is 15:30."

[0585] The terminal records this exchange as text data and transmits it to the server.

[0586] 3. Analysis and report generation

[0587] The server analyzes the transmitted text data using a generative AI model (OpenAI GPT-3) to extract details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0588] Report content is automatically generated based on the collected data.

[0589] 4. PDF Output

[0590] The server converts the generated report content into a PDF in a predetermined format and saves it using an output means.

[0591] If necessary, the server sends the PDF to the user.

[0592] Specific examples

[0593] For example, based on the accident information "Occurrence date and time: October 12, 2023, 14:00," "Affected area: Production line 2 stopped," "Cause: Robot arm failure," and "Estimated time of resolution: October 12, 2023, 15:30," the following prompt sentence can be used to have the AI ​​generate a report:

[0594] Prompt Sentence Examples

[0595] Date and time of occurrence: October 12, 2023, 14:00

[0596] Affected area: Production line 2 stopped

[0597] Cause: Robot arm malfunction

[0598] Estimated time of resolution: October 12, 2023, 15:30

[0599] Use this information to generate a report that includes details of the incident, the extent of the impact, the cause, how it was resolved, and how to prevent it from happening again.

[0600] This makes it possible to quickly and efficiently prepare detailed reports and propose measures to prevent recurrence when an accident occurs within a factory.

[0601] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0602] Step 1:

[0603] The user prepares documents such as operation manuals and abnormality response procedures and uploads them to the server.

[0604] Input: Documents (text files) such as operation manuals and abnormality response procedures

[0605] Processing: The server loads these documents and trains a generative AI model to build a knowledge base.

[0606] Output: Trained knowledge base

[0607] Step 2:

[0608] If an accident occurs, users can report the details of the accident via a chat system or email.

[0609] Input: Detailed information about the accident (e.g., "Production Line 2 stopped at 14:00 on October 12, 2023. The cause was a robot arm malfunction. The estimated time of resolution is 15:30.")

[0610] Processing: The device records this exchange as text data and sends it to the server.

[0611] Output: Collected accident report text data

[0612] Step 3:

[0613] The server analyzes the transmitted text data using a generative AI model to extract details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0614] Input: Collected accident report text data

[0615] Processing: The generative AI model analyzes the text data and extracts information such as defect details, scope of impact, cause, resolution date and time, and measures to prevent recurrence.

[0616] Output: Extracted information (details of the defect, scope of impact, cause, resolution date and time, measures to prevent recurrence)

[0617] Step 4:

[0618] The server automatically generates a report based on the extracted information.

[0619] Input: Extracted information

[0620] Processing: The generative AI model automatically generates report content in a specified format based on the extracted information.

[0621] Output: Auto-generated report text

[0622] Step 5:

[0623] The server converts the automatically generated report into a PDF in a predetermined format and saves or transmits it to the user.

[0624] Input: Auto-generated report text

[0625] Processing: The server converts the report to PDF using the pdfkit library, saves it in the required format, and sends the PDF to the user if necessary.

[0626] Output: Report in PDF format

[0627] In this way, the system automates all processes, making it possible to quickly and efficiently create accident reports and implement measures to prevent recurrence.

[0628] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0629] The present invention is a system that automatically generates report content and preventive measures quickly and efficiently when an accident occurs during service operation. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the tone and expression of the report content, enabling a more appropriate response. The system of the present invention has information processing means, data collection means, analysis means, output means, and an emotion engine.

[0630] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The server uses this as an information processing tool and has the AI ​​learn the contents of the document. Based on the learned service content and business procedures, the AI ​​builds a knowledge base to quickly derive appropriate countermeasures.

[0631] Next, when an accident occurs, the user reports the details of the accident through a communication tool (e.g., a chat system or email). The device uses this communication as a means of collecting data and records it as text data in real time. The recorded data is automatically sent to the server.

[0632] The server uses the transmitted text data as an analytical tool, and the AI ​​begins its analysis. The AI ​​extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence from the text data, and automatically generates a report. This report is then formatted appropriately based on the analysis results and passed to the emotion engine.

[0633] The emotion engine analyzes the user's emotional state from their interactions. For example, it reads emotions such as stress or impatience from the user's writing and reflects them in the analysis results. If necessary, it adjusts the tone and expression of the report and converts it into a more appropriate format.

[0634] The server then uses the prepared report content as an output means and saves it in a specified format (e.g., PDF).Finally, the automatically generated report is sent to the user, who can check the report and make additional corrections or comments as necessary.

[0635] Specific examples

[0636] 1. Initial Setup:

[0637] The user prepares an operation manual and an abnormality response procedure manual for the "customer support system" and uploads them to the server.

[0638] The server uses AI to learn from the uploaded documents and understand how to respond if a system abnormality occurs.

[0639] 2. Information gathering after an accident:

[0640] Users can use the chat system to report:

[0641] "System went down at 13:00"

[0642] "All users are affected"

[0643] "The cause is server overload"

[0644] The device automatically records this exchange as text data and sends it to the server.

[0645] 3. Data Analysis:

[0646] The server uses AI to analyze the recorded text data.

[0647] On the server, AI extracts from the text data the following: "System down," "Affecting all users," "Cause is server overload," "Estimated time of resolution is 2:00 p.m.", and "Increasing server resources to prevent recurrence."

[0648] 4. Sentiment analysis and adjustment:

[0649] The server uses an emotion engine to analyze emotions such as "stress" and "anxiety" from user interactions.

[0650] The server adjusts the tone of the report based on the emotional information. For example, if an urgent part expresses strong emotions, it will describe that part in more detail and add expressions to soften the emotions.

[0651] 5. Automatic report generation:

[0652] The server automatically generates a final report based on the extracted information and the tone adjusted by the emotion engine.

[0653] Example: "A system outage occurred on October 12, 2023 at 1:00 PM. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence. Users have reported that the issue is urgent and causing increased stress, so special attention is required."

[0654] 6. Report printing and distribution:

[0655] The server saves the generated report in PDF format and sends it to the user.

[0656] The user checks the report received by email and makes corrections or comments as necessary.

[0657] This not only speeds up response after an accident occurs, but also enables more appropriate responses that take into account the user's emotions.

[0658] The processing flow will be explained below.

[0659] Step 1:

[0660] Data preparation (user)

[0661] Users prepare text files or documents detailing the service content and business procedures.

[0662] Example: "Service Contents_Business Procedures.docx" contains an overview of the service, daily business procedures, and past problems and their solutions.

[0663] Step 2:

[0664] Data upload (user)

[0665] The user uploads the prepared text files or documents to the server via the terminal.

[0666] Users transfer files to the server using a dedicated upload interface.

[0667] Step 3:

[0668] Data learning (server)

[0669] The server receives the uploaded documents and feeds them into the AI ​​learning model.

[0670] The server builds a knowledge base by having the AI ​​learn business procedures and problem-solving measures.

[0671] Step 4:

[0672] Information collection in the event of an accident (terminal)

[0673] When an accident occurs, users report the details of the accident using a chat system or email.

[0674] The device records these interactions as text data in real time.

[0675] Step 5:

[0676] Data transmission (terminal)

[0677] The terminal automatically transmits the recorded text data to the server.

[0678] The transmission process is performed by periodic synchronization or trigger events.

[0679] Step 6:

[0680] Receive text data (server)

[0681] The server receives the text data sent from the terminal.

[0682] The received data includes details such as the time of the accident, the extent of the impact, and the cause.

[0683] Step 7:

[0684] Text analysis (server)

[0685] The server inputs the received text data into an AI analysis engine and performs the analysis.

[0686] AI extracts details of the accident, the type of malfunction, the extent of the impact, and the cause.

[0687] Step 8:

[0688] Sentiment analysis (server)

[0689] The server utilizes an emotion engine to analyze the user's emotional state from the text data.

[0690] For example, it can determine whether a user is feeling anxious or stressed from the tone of the text or specific keywords.

[0691] Step 9:

[0692] Organizing analysis results (server)

[0693] The server organizes the analysis results based on the information extracted by the AI.

[0694] This includes not only details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, but also the user's emotional state.

[0695] Step 10:

[0696] Report template generation (server)

[0697] The server generates a report template based on the organized information.

[0698] The template applies a prescribed format and also adjusts the tone based on emotion.

[0699] Step 11:

[0700] Final check (server)

[0701] The server performs a final check of the generated report template to check for any defects.

[0702] If an error is detected, data analysis and sentiment analysis are performed again.

[0703] Step 12:

[0704] Report storage (server)

[0705] The server stores the final verified report in PDF format.

[0706] The saved file contains detailed information about the accident, including an overview of the incident, the extent of the impact, the cause, countermeasures, and the results of user sentiment analysis.

[0707] Step 13:

[0708] Sending reports (server)

[0709] The server automatically sends the generated report to the user.

[0710] Typically, email is used to send reports and confirm receipt of the reports.

[0711] Step 14:

[0712] User Verification (User)

[0713] The user checks the report received by email to ensure there are no errors in the content.

[0714] Make any necessary corrections or comments, and share the final report internally.

[0715] Example 2

[0716] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0717] While it is necessary to take prompt and accurate countermeasures when an accident occurs during service operation, many systems require time-consuming manual report creation and the formulation of preventive measures, which can increase user dissatisfaction and stress.Furthermore, it is difficult to create reports that take emotional evaluation into account, and reports are not always written in an appropriate tone or with appropriate expressions.

[0718] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an information processing means that has previously learned the service content and business procedures, a data collection means that collects exchanges via communication means after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report containing details of the malfunction, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an emotion analysis means that analyzes the emotional state of the user and adjusts the tone and expression of the report. This makes it possible to automatically generate a quick and accurate report when an accident occurs and to report in an appropriate tone that takes emotions into consideration.

[0719] "Information processing means" refers to a method or device for learning service content and business procedures in advance.

[0720] "Data collection means" refers to a method or device for collecting communication via means of communication after an accident occurs as text data.

[0721] "Analysis means" refers to a method or device for analyzing collected text data and automatically generating a report on the details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0722] "Output means" refers to a method or device for outputting the automatically generated report content.

[0723] "Emotion analysis means" refers to a method or device for analyzing a user's emotional state and adjusting the tone and expression of the report.

[0724] This invention is a system that automatically generates report content and preventive measures quickly and efficiently when an accident occurs during service operation. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the tone and expression of the report content, enabling more appropriate responses.

[0725] Specifically, the system includes "information processing means," "data collection means," "analysis means," "output means," and "emotion analysis means."

[0726] First, the user prepares a text file or document (e.g., PDF or Word file) detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The information processing means used for the hardware or software includes natural language processing libraries (e.g., NLTK, SpaCy) and machine learning frameworks (e.g., TensorFlow, PyTorch). The server trains an AI on the uploaded document and builds a knowledge base that determines how to respond when a system abnormality occurs.

[0727] Next, when an accident occurs, the user reports the details of the accident through a communication method such as a chat system or email. The device records this report in real time as text data and sends it to the server. Specifically, the user reports, for example, "The system went down at 1:00 PM," "All users are affected," and "The cause was a server overload."

[0728] The server uses the received text data as an analytical tool, and the AI ​​begins its analysis. Software used includes text analysis tools (e.g., ElasticSearch, Apache Lucene). Details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence are extracted from the text data and automatically generated as a report.

[0729] The generated report content is analyzed using a sentiment analysis means to determine the emotional state of the user's interactions. For example, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) to read "stress" or "urgency" from the user's message and reflects the results in the report content. The sentiment analysis means adjusts the tone and expression of the report content as necessary and converts it into a more appropriate format.

[0730] Finally, the server saves the generated report in a specified format (e.g., PDF) and sends it to the user, using software such as document generation tools (e.g., LaTeX, ReportLab). Finally, the user receives the report and can make additional corrections or comments if necessary.

[0731] Prompt Sentence Examples

[0732] Examples of prompts for specific scenarios:

[0733] "The system went down at 1:00 PM, affecting all users. The cause was server overload. Please automatically generate a report outlining effective measures to prevent recurrence."

[0734] As a result, not only can responses after an accident be made more quickly, but more appropriate responses can be made that take into account the user's emotions.

[0735] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0736] Step 1: Prepare and upload your documents

[0737] The user prepares a text file or document (e.g., PDF or Word file) that describes the service content and business procedures. Specifically, the user prepares their company's service manual or process document.

[0738] The user uploads the prepared document to the server via the terminal. The input is a file containing a service manual or procedure manual. The output is the document uploaded to the server.

[0739] Step 2: The learning process

[0740] The server uses the received documents as a means of information processing and trains the AI. Specifically, it analyzes the document content using natural language processing libraries (e.g., NLTK, SpaCy) and machine learning frameworks (e.g., TensorFlow, PyTorch) and adds it to the training dataset.

[0741] The server builds a knowledge base based on what the AI ​​has learned. The uploaded documents are used as input, and the output is an AI model that has learned how to respond to system anomalies.

[0742] Step 3: Report the incident

[0743] When an accident occurs, users report details using communication methods such as chat systems or email. Specifically, users send information such as "The system went down at 13:00," "All users are affected," and "The cause is server overload" via chat messages or email.

[0744] The input is text data describing the details of the accident, and the output is text data in which the report content is recorded in real time.

[0745] Step 4: Data collection

[0746] The device records the accident report exchange as text data in real time and sends it to the server. Specifically, the device automatically captures chat logs and email content, organizes it into an appropriate format, and uploads it to the server.

[0747] The input is the text data of the accident report submitted by the user, and the output is well-formed text data sent to the server.

[0748] Step 5: Data analysis

[0749] The server uses the received text data as an analytical tool, and the AI ​​begins its analysis. Specifically, it uses a text analysis tool (e.g., ElasticSearch, Apache Lucene) to extract important information from the received data, such as "system down," "affecting all users," and "cause of server overload."

[0750] The server updates the knowledge base based on the analysis results and formats them appropriately. The input is the text data received by the server, and the output is a draft of the accident report.

[0751] Step 6: Emotion analysis and tone adjustment

[0752] The server uses an emotion engine to analyze the user's emotional state from their interactions. Specifically, the emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) analyzes emotions such as "stress" and "urgency" from the user's message and generates a score.

[0753] The server adjusts the tone of the report based on the emotional information: the inputs are the analyzed emotional scores and the draft incident report, and the output is the emotionally adjusted final report.

[0754] Step 7: Automatic report generation

[0755] The server automatically generates a final report based on the extracted information and the results of sentiment analysis. Specifically, it uses document generation tools such as LaTeX and ReportLab to format the text data and generate the report.

[0756] The inputs are the sentiment analysis results and the contents of the incident report, and the output is the final report in a digital format (e.g., PDF).

[0757] Step 8: Print and distribute the report

[0758] The server saves the generated report in a specified format (e.g. PDF) and sends it to the user. Specifically, the server saves the generated report in a specified directory and sends it to the user via email or system notification.

[0759] The user reviews the received report and makes any necessary corrections or comments. The generated report is used as input, and the final report including the user's feedback is obtained as output.

[0760] (Application example 2)

[0761] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0762] When a system failure or accident occurs at a logistics center, a prompt and appropriate response is required. However, conventional methods have the drawback of taking time to create a report and formulate measures to prevent recurrence, and it is also difficult to respond in a way that appropriately reflects the stress and impatience of the person in charge. To solve these problems, the present invention aims to provide a system that quickly and automatically generates accident report content and adjusts the tone of the report taking into account the user's emotional state.

[0763] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0764] In this invention, the server includes an information processing means that has learned service content and business procedures in advance, a data collection means that collects exchanges via communication tools after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report containing details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, an emotion analysis means that adjusts the tone and expression of the automatically generated report, and an output means that outputs the automatically generated report. This enables the rapid automatic generation of accident report content, and further enables a more appropriate response by appropriately adjusting the tone to reflect the user's emotional state.

[0765] "Information processing means" refers to a means for learning service content and business procedures in advance.

[0766] "Data collection means" refers to a means of collecting exchanges via communication tools after an accident occurs as text data.

[0767] The "analysis means" is a means for analyzing the collected text data and automatically generating a report containing details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0768] "Emotion analysis means" is a means for analyzing the user's emotional state in order to adjust the tone and expression of the automatically generated report content.

[0769] The "output means" is a means for converting the automatically generated report content into a predetermined format and sending it to the user.

[0770] The present invention is a system for automatically generating report content and preventive measures in the event of an accident at a logistics center in a prompt and appropriate manner. A specific embodiment of the system will be described below.

[0771] System Configuration

[0772] The system consists of the following main components:

[0773] Information processing means: A means of learning service content and business procedures in advance. For example, uploading business manuals and abnormality response procedures to an AI model on a server and having it learn the information.

[0774] Data collection method: A method for collecting text data from communication tools (e.g., chat systems, emails) after an accident occurs. For example, data entered on a smartphone or device is sent to a server in real time.

[0775] Analysis method: Analyzes collected text data and automatically generates a report containing details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence. This is done using an AI model (e.g., OpenAI GPT-3).

[0776] Sentiment analysis: Analyzing the user's emotional state in order to adjust the tone and expression of the automatically generated report. For example, using a sentiment analysis tool such as TextBlob.

[0777] Output means: A means to convert the automatically generated report content into a specified format (e.g. PDF) and send it to the user. For example, generate a PDF using the FPDF library.

[0778] Program processing explanation

[0779] The server first learns the logistics center's operational procedures and abnormality response procedures as an information processing tool in advance, allowing the AI ​​model on the server to understand basic response methods for various accidents and malfunctions.

[0780] When an accident occurs, users report the details of the accident using the communication tools on their smartphones. This data is collected as text data by the smartphone as a data collection means and sent to the server in real time.

[0781] The server analyzes the received text data using an AI model (OpenAI GPT-3), which extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and automatically generates a report.

[0782] The automatically generated report content is analyzed using emotion analysis to detect the user's emotional state (e.g., stress or impatience from the text) and adjust the tone and expression accordingly. For example, TextBlob is used to analyze the user's emotional state.

[0783] Finally, the server formats the report content (e.g., PDF) and sends it to the user via an output means, which uses the FPDF library to generate the PDF.

[0784] Examples of concrete examples and prompts

[0785] In a specific scenario, if a system error occurs at a distribution center, an employee enters the following details into their smartphone:

[0786] Example: "At 2:30 PM, shipping processing was halted due to a system error. All centers were affected. The cause was a database overload. The error is expected to be resolved by 3:30 PM."

[0787] This data is sent in real time to a server where an AI model generates the following prompts and creates a report:

[0788] Example prompt: "At 2:30 PM, a system error halted shipping processing. This affected all centers. The cause was a database overload. The error is expected to be resolved by 3:30 PM. Please use these details to create an incident report for the distribution center."

[0789] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0790] Step 1:

[0791] The user uploads the logistics center's work procedures and anomaly response procedures to the server. The server receives this as an information processing tool and trains the AI ​​model. The input is the work procedures and anomaly response procedures file, and the output is the trained AI model. The specific operations performed in this step are for the server to receive the files, read them sequentially into the AI ​​model, and have it learn the service content and work procedures.

[0792] Step 2:

[0793] When an accident occurs, the user uses a smartphone communication tool to input details of the accident (e.g., time of occurrence, extent of impact, cause, estimated time to resolve, etc.). The input is detailed information about the accident entered by the user, and the output is the accident information as text data. Specifically, the user uses the smartphone's chat system or email to enter the details of the accident in text format, which is then recorded on the device.

[0794] Step 3:

[0795] The terminal transmits the collected text data to the server in real time. The input is the text data generated in step 2, and the output is the text data transmitted to the server. The specific operation performed in this step is that the terminal transmits the text data to the server using an appropriate network protocol.

[0796] Step 4:

[0797] The server uses an AI model to analyze the received text data. The input is the text data sent to the server, and the output is the analysis results regarding the details of the defect, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence. Specifically, the AI ​​model (e.g., OpenAI GPT-3) analyzes the text data, extracts each item, and automatically generates the report content.

[0798] Step 5:

[0799] The automatically generated report content uses emotion analysis tools to analyze the user's emotional state (e.g., stress or impatience) and adjusts the tone and expression accordingly. The input is the automatically generated report content and text data indicating the user's emotional state, and the output is the report content with the adjusted tone and expression. Specifically, it uses emotion analysis tools such as TextBlob to analyze the user's emotional state, and the AI ​​model adjusts the vocabulary and style to be appropriate.

[0800] Step 6:

[0801] The server finally formats the report content into a specified format (e.g. PDF) and sends it to the user. The input is the report content with adjusted tone and expression, and the output is a report formatted in the specified format (PDF). Specifically, the server uses the FPDF library to generate the report content as a PDF and sends it to the user via email or other means.

[0802] This will enable the logistics center to respond to accident reports quickly and appropriately.

[0803] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0804] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0805] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0806] [Third embodiment]

[0807] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0808] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0809] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0810] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0811] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0812] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0813] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0814] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0815] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0816] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0817] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0818] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0819] The present invention provides a system for automatically generating report content and preventive measures quickly and efficiently when an unexpected accident occurs during service operation. The system includes an information processing unit, a data collection unit, an analysis unit, and an output unit.

[0820] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The server uses this as an information processing tool and has the AI ​​learn the contents of the document. Based on the learned service content and business procedures, the AI ​​builds a knowledge base to quickly derive appropriate countermeasures.

[0821] Next, when an accident occurs, the user reports the details of the accident through a communication tool (e.g., a chat system or email). The device uses this communication as a means of collecting data and records it as text data in real time. The recorded data is automatically sent to the server.

[0822] The server uses the transmitted text data as an analytical tool, and the AI ​​begins its analysis. The AI ​​extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence from the text data, and automatically generates a report. This report is then formatted appropriately based on the analysis results.

[0823] The server then uses the prepared report content as an output means and saves it in a specified format (e.g., PDF).Finally, the automatically generated report is sent to the user, who can check the report and make additional corrections or comments as necessary.

[0824] Specific examples

[0825] 1. Initial Setup:

[0826] The user prepares an operation manual and an abnormality response procedure manual for the "customer support system" and uploads them to the server.

[0827] The server uses AI to learn from the uploaded documents and understand how to respond if a system abnormality occurs.

[0828] 2. Information gathering after an accident:

[0829] Users can use the chat system to report:

[0830] "System went down at 13:00"

[0831] "All users are affected"

[0832] "The cause is server overload"

[0833] The device automatically records this exchange as text data and sends it to the server.

[0834] 3. Data Analysis:

[0835] The server uses AI to analyze the recorded text data.

[0836] On the server, AI extracts from the text data the following: "System down," "Affecting all users," "Cause is server overload," "Estimated time of resolution is 2:00 p.m.", and "Increasing server resources to prevent recurrence."

[0837] 4. Automatic report generation:

[0838] The server automatically generates a report based on the extracted information.

[0839] Example: "A system outage occurred on October 12, 2023 at 1:00 PM. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence."

[0840] 5. Report printing and distribution:

[0841] The server saves the generated report in PDF format and sends it to the user.

[0842] The user checks the report received by email and makes corrections or comments as necessary.

[0843] This will speed up the response after an accident occurs and significantly reduce the effort required by the user.

[0844] The processing flow will be explained below.

[0845] Step 1:

[0846] Data preparation (user)

[0847] The user prepares a text file or document that specifically describes the service content and business procedures.

[0848] Example: "Service Contents_Business Procedures.docx" contains an overview of the service, daily business procedures, and common problems and their solutions.

[0849] Step 2:

[0850] Data upload (user)

[0851] The user uploads the prepared text files or documents to the server via the terminal.

[0852] Uploading is done using a dedicated upload function.

[0853] Step 3:

[0854] Data learning (server)

[0855] The server takes the uploaded documents and feeds them into an AI model, which learns important information.

[0856] The information to be learned includes business procedures, how to respond to errors, and examples of past accidents.

[0857] Step 4:

[0858] Information collection in the event of an accident (terminal)

[0859] When an accident occurs, users report the details of the accident using a chat system or email.

[0860] The device records these interactions as text data in real time.

[0861] Step 5:

[0862] Data transmission (terminal)

[0863] The terminal automatically transmits the recorded text data to the server.

[0864] The transmission can be by a periodically executed process or by a trigger event.

[0865] Step 6:

[0866] Data reception (server)

[0867] The server receives the text data sent from the terminal.

[0868] The received data includes detailed information such as the time of the accident, the extent of the impact, and the cause.

[0869] Step 7:

[0870] Text analysis (server)

[0871] The server inputs the received text data into the AI ​​and analyzes the details of the accident, the type of malfunction, the extent of the impact, the cause, etc.

[0872] The AI ​​uses natural language processing techniques to extract important keywords and phrases.

[0873] Step 8:

[0874] Organizing analysis results (server)

[0875] The server organizes the report content based on the information extracted by the AI.

[0876] Specifically, it summarizes details of the problem, the scope of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0877] Step 9:

[0878] Report template generation (server)

[0879] The server generates a report template based on the organized information.

[0880] The template applies pre-trained formats.

[0881] Step 10:

[0882] Final check (server)

[0883] The server performs a final check on the generated report template to check for errors.

[0884] Step 11:

[0885] Report storage (server)

[0886] The server stores the final verified report in a format such as PDF.

[0887] The saved files contain detailed information about the accident, its scope of impact, causes, and countermeasures.

[0888] Step 12:

[0889] Sending reports (server)

[0890] The server automatically sends the generated report to the user.

[0891] It is usually sent through communication tools such as email.

[0892] Step 13:

[0893] User Verification (User)

[0894] The user checks the report received by email and makes additional corrections or comments as necessary.

[0895] Once the final report is completed, it will be shared with internal stakeholders.

[0896] Example 1

[0897] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0898] In modern service operations, when unexpected accidents occur, a rapid and accurate response is required. Traditional manual methods of creating reports and documenting preventative measures require a lot of time and effort, and there is also a risk of information being overlooked or mistyped. This can delay the response to the accident and cause further problems. To address these issues, this invention aims to provide a system that automatically generates rapid and efficient report content and preventative measures when an accident occurs.

[0899] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0900] In this invention, the server includes an information processing means that has learned the service content and business procedures in advance, a data collection means that collects communication via the communication means after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report on the details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an output means that saves the automatically generated report in a predetermined format and provides the information. This enables a quick response after an accident occurs and efficient report creation.

[0901] "Information processing means" refers to devices and programs that allow AI to learn service content and business procedures.

[0902] "Data collection means" refers to a device and program that collects text data exchanged through communication means after an accident occurs.

[0903] "Analysis means" refers to a device and program that analyzes collected text data, extracts details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence, and automatically generates report content.

[0904] "Output means" refers to a device and program that saves the automatically generated report content in a predetermined format and provides the information.

[0905] "Service Content" refers to the full range of functionality and support provided by a particular Service.

[0906] "Business procedures" refers to documents that describe specific work procedures and response methods for service operation.

[0907] "Means of communication" refers to tools for exchanging text data, such as chat systems and email.

[0908] "Text data" refers to character data sent and received via communication means.

[0909] "Details of the malfunction" refers to the specific content and circumstances of the accident or problem.

[0910] "Scope of impact" refers to the range and scale of the impact caused by the malfunction.

[0911] "Cause" refers to the reason or background behind the occurrence of the defect.

[0912] "Resolution date and time" refers to the time when the defect is scheduled to be resolved or the time when it is actually resolved.

[0913] "Measures to prevent recurrence" refers to specific measures to prevent the recurrence of similar defects.

[0914] "Report" refers to a detailed written report of a defect generated by the analysis means.

[0915] "Prescribed format" refers to the standard file format (e.g., PDF) in which the generated report content is stored and provided.

[0916] The present invention provides a system that automatically generates report content and preventive measures quickly and efficiently when an unexpected accident occurs during service operation. This system includes an information processing unit, a data collection unit, an analysis unit, and an output unit. Specific embodiments of the system are described below.

[0917] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of an accident and how to respond. Specifically, the user uses a text editor or similar tool to create an operation manual for the "customer support system" or an abnormality response procedure manual, and then uploads it to the server.

[0918] The server uses the uploaded documents as a means of information processing and uses a generative AI model (e.g., BERT or GPT) to learn the contents of the documents, allowing the AI ​​to build a knowledge base that can quickly derive countermeasures based on service content and business procedures.

[0919] Next, when an accident occurs, the user reports the details of the accident using a communication method such as a chat system or email. For example, they might report something like, "The system went down at 1:00 PM," "All users are affected," or "The cause was a server overload." The device uses this exchange as a means of collecting data and records it as text data. This recorded data is automatically sent to the server.

[0920] The server uses the text data as an analytical tool, and the AI ​​begins analyzing it. In the analytical tool, the AI ​​extracts important information from the text data, such as "System down," "All users affected," "Cause is server overload," "Estimated resolution time is 2:00 PM," and "Server resources will be increased to prevent recurrence."

[0921] The server then automatically generates a report based on the extracted information. The generated report is formatted using a template engine. Specifically, the report generated looks like this:

[0922] "A system outage occurred at 1:00 PM on October 12, 2023. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence."

[0923] The server saves the report in a predetermined format, such as PDF, and sends it to the user. A PDF generator library (e.g., PDFKit or ReportLab) is used for saving the report. The user can then review the report received by email and make any necessary corrections or comments.

[0924] This will speed up the response after an accident occurs and significantly reduce the effort required by the user.

[0925] Example prompt sentence:

[0926] "The system went down at 13:00. All users are affected. The cause was server overload."

[0927] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0928] Step 1:

[0929] The user prepares and creates text files and documents that detail the service content and business procedures. These include system operation manuals and abnormality response procedures. Specifically, the user uses a text editor to create a detailed business procedure manual that describes how to operate the "customer support system" and the response procedures in the event of an abnormality. This document becomes the input data.

[0930] Step 2:

[0931] Users upload text files or documents they have created to a server via their terminal. Specifically, they use a web interface or dedicated upload tool to send the document to a specified location. At this stage, the input data is the text file or document, and the output is a notification that the upload has been completed.

[0932] Step 3:

[0933] The server uses the uploaded document as a means of information processing, learning the document's contents using a generative AI model (e.g., BERT or GPT). The input here is the document uploaded by the user, and the output is a knowledge base in which the AI ​​understands the service content and business procedures. Specifically, the server performs text analysis of the document's contents and stores them in a database using a learning algorithm.

[0934] Step 4:

[0935] When an accident occurs, the user reports the details of the accident using a communication method such as a chat system or email. The specific report content is "The system went down at 13:00," "All users are affected," and "The cause was a server overload." The input in this step is a text message containing the details of the accident, and the output is the generation of text data.

[0936] Step 5:

[0937] The device uses this exchange as a data collection tool and records it as text data in real time. The input is the text message sent and received via the communication tool, and the output is the recorded text data. Specific operations include recording the contents of chats and emails in a database using system logs and storage functions.

[0938] Step 6:

[0939] The recorded text data is automatically sent to the server, which receives it. The input here is the text data sent from the device, and the output is the text data saved on the server. Specifically, the server receives the data using an API or data transfer service and stores it in a database.

[0940] Step 7:

[0941] The server uses the transmitted text data as an analytical tool and begins analysis using a generative AI model. During this analysis, important information is extracted from the text data, such as "System down," "All users affected," "Cause is server overload," "Estimated resolution time is 2:00 PM," and "Server resources will be increased to prevent recurrence." The input is the received text data, and the output is the extracted important information. Specifically, the data is analyzed using a pixel processing engine and natural language processing algorithms.

[0942] Step 8:

[0943] The server automatically generates a report based on the extracted information. The input is the key information extracted through analysis, and the output is the report content arranged in a report template. Specifically, a template engine is used to embed the extracted information into a specified report format.

[0944] Step 9:

[0945] The server saves the generated report in PDF format. The tool used here is a PDF generator library (e.g. PDFKit or ReportLab). The input is the formatted report content, and the output is a PDF file. Specifically, the report content is formatted using a template engine, and the file is generated using a PDF generator.

[0946] Step 10:

[0947] Finally, the server sends the generated PDF to the user. The input is the PDF file, and the output is a notification of completion of sending. Specifically, it uses a mail library (e.g., SMTP) to send an email with the PDF file attached to the user's address. The user checks the received report and makes additional corrections or comments as necessary.

[0948] (Application example 1)

[0949] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0950] It is extremely important to quickly and efficiently respond to quality and production line problems that occur within a factory and to appropriately implement measures to prevent recurrence. However, with conventional systems, it took a long time to report accidents and formulate preventive measures, and there was a tendency for human error and omissions to occur. In particular, manually creating complex accident reports and preventive measures required a great deal of effort and time, which was a major obstacle in workplaces where a rapid response was required. Given this current situation, there was a need for a system that could automatically create detailed reports when an accident occurred and propose efficient preventive measures.

[0951] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0952] In this invention, the server includes an information processing means that has been trained on service content and business procedures in advance, a data collection means that collects exchanges via communication tools after an accident occurs as text data, an analysis means that uses a generative AI model to analyze the collected text data and automatically generate a report on the details of the defect, the scope of impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an output means that converts the automatically generated report into a PDF in a predetermined format and outputs it. This makes it possible to quickly and efficiently create a detailed report and propose measures to prevent recurrence when an accident occurs in a factory.

[0953] "Information processing means" refers to a means for learning the service content and business procedures in advance and then performing processing to derive countermeasures based on that information.

[0954] "Data collection means" refers to a means of collecting exchanges via communication tools after an accident occurs as text data.

[0955] A "generative AI model" is an artificial intelligence model that analyzes collected data and automatically generates report content.

[0956] The "analysis means" is a means for analyzing collected text data using a generative AI model and automatically generating a report containing details of the defect, the scope of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0957] The "output means" is a means for converting the automatically generated report into a PDF in a predetermined format and saving or transmitting it to the user.

[0958] "PDF" stands for Portable Document Format, a format for electronically storing and distributing documents while preserving their layout.

[0959] This invention is a "Smart Factory Incident Manager" system that responds quickly and efficiently to quality and production line problems that occur within a factory. Specific processing procedures for implementing this system will be described below.

[0960] System Overview

[0961] The system mainly consists of the following elements:

[0962] 1. Information processing method: Study documents such as factory operation manuals and abnormality response procedures in advance to build a knowledge base.

[0963] 2. Data collection method: Collect text data from interactions using communication tools after the accident.

[0964] 3. Analysis method: The collected text data is analyzed using a generative AI model to automatically generate a report containing details of the defect, the scope of impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0965] 4. Output method: The automatically generated report is converted into a PDF in a specified format and saved or sent to the user.

[0966] Hardware and Software

[0967] The hardware and software used to implement this system are as follows:

[0968] Hardware: Factory robots (e.g. KUKA, Fanuc)

[0969] software:

[0970] Python: a programming language

[0971] OpenAI GPT-3: Generative AI model

[0972] pdfkit: A library for converting HTML and strings to PDF

[0973] Detailed procedure

[0974] 1. Information gathering and learning

[0975] The user prepares documents such as operation manuals and abnormality response procedures and uploads them to the server.

[0976] The server reads these documents and builds a knowledge base by training the AI.

[0977] 2. Collecting accident information

[0978] When an accident occurs, users can report the details of the accident via chat system or email. For example, "Production line 2 stopped at 14:00 on October 12, 2023. The cause was a robot arm malfunction. The expected time of resolution is 15:30."

[0979] The terminal records this exchange as text data and transmits it to the server.

[0980] 3. Analysis and report generation

[0981] The server analyzes the transmitted text data using a generative AI model (OpenAI GPT-3) to extract details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[0982] Report content is automatically generated based on the collected data.

[0983] 4. PDF Output

[0984] The server converts the generated report content into a PDF in a predetermined format and saves it using an output means.

[0985] If necessary, the server sends the PDF to the user.

[0986] Specific examples

[0987] For example, based on the accident information "Occurrence date and time: October 12, 2023, 14:00," "Affected area: Production line 2 stopped," "Cause: Robot arm failure," and "Estimated time of resolution: October 12, 2023, 15:30," the following prompt sentence can be used to have the AI ​​generate a report:

[0988] Prompt Sentence Examples

[0989] Date and time of occurrence: October 12, 2023, 14:00

[0990] Affected area: Production line 2 stopped

[0991] Cause: Robot arm malfunction

[0992] Estimated time of resolution: October 12, 2023, 15:30

[0993] Use this information to generate a report that includes details of the incident, the extent of the impact, the cause, how it was resolved, and how to prevent it from happening again.

[0994] This makes it possible to quickly and efficiently prepare detailed reports and propose measures to prevent recurrence when an accident occurs within a factory.

[0995] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0996] Step 1:

[0997] The user prepares documents such as operation manuals and abnormality response procedures and uploads them to the server.

[0998] Input: Documents (text files) such as operation manuals and abnormality response procedures

[0999] Processing: The server loads these documents and trains a generative AI model to build a knowledge base.

[1000] Output: Trained knowledge base

[1001] Step 2:

[1002] If an accident occurs, users can report the details of the accident via a chat system or email.

[1003] Input: Detailed information about the accident (e.g., "Production Line 2 stopped at 14:00 on October 12, 2023. The cause was a robot arm malfunction. The estimated time of resolution is 15:30.")

[1004] Processing: The device records this exchange as text data and sends it to the server.

[1005] Output: Collected accident report text data

[1006] Step 3:

[1007] The server analyzes the transmitted text data using a generative AI model to extract details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[1008] Input: Collected accident report text data

[1009] Processing: The generative AI model analyzes the text data and extracts information such as defect details, scope of impact, cause, resolution date and time, and measures to prevent recurrence.

[1010] Output: Extracted information (details of the defect, scope of impact, cause, resolution date and time, measures to prevent recurrence)

[1011] Step 4:

[1012] The server automatically generates a report based on the extracted information.

[1013] Input: Extracted information

[1014] Processing: The generative AI model automatically generates report content in a specified format based on the extracted information.

[1015] Output: Auto-generated report text

[1016] Step 5:

[1017] The server converts the automatically generated report into a PDF in a predetermined format and saves or transmits it to the user.

[1018] Input: Auto-generated report text

[1019] Processing: The server converts the report to PDF using the pdfkit library, saves it in the required format, and sends the PDF to the user if necessary.

[1020] Output: Report in PDF format

[1021] In this way, the system automates all processes, making it possible to quickly and efficiently create accident reports and implement measures to prevent recurrence.

[1022] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1023] The present invention is a system that automatically generates report content and preventive measures quickly and efficiently when an accident occurs during service operation. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the tone and expression of the report content, enabling a more appropriate response. The system of the present invention has information processing means, data collection means, analysis means, output means, and an emotion engine.

[1024] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The server uses this as an information processing tool and has the AI ​​learn the contents of the document. Based on the learned service content and business procedures, the AI ​​builds a knowledge base to quickly derive appropriate countermeasures.

[1025] Next, when an accident occurs, the user reports the details of the accident through a communication tool (e.g., a chat system or email). The device uses this communication as a means of collecting data and records it as text data in real time. The recorded data is automatically sent to the server.

[1026] The server uses the transmitted text data as an analytical tool, and the AI ​​begins its analysis. The AI ​​extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence from the text data, and automatically generates a report. This report is then formatted appropriately based on the analysis results and passed to the emotion engine.

[1027] The emotion engine analyzes the user's emotional state from their interactions. For example, it reads emotions such as stress or impatience from the user's writing and reflects them in the analysis results. If necessary, it adjusts the tone and expression of the report and converts it into a more appropriate format.

[1028] The server then uses the prepared report content as an output means and saves it in a specified format (e.g., PDF).Finally, the automatically generated report is sent to the user, who can check the report and make additional corrections or comments as necessary.

[1029] Specific examples

[1030] 1. Initial Setup:

[1031] The user prepares an operation manual and an abnormality response procedure manual for the "customer support system" and uploads them to the server.

[1032] The server uses AI to learn from the uploaded documents and understand how to respond if a system abnormality occurs.

[1033] 2. Information gathering after an accident:

[1034] Users can use the chat system to report:

[1035] "System went down at 13:00"

[1036] "All users are affected"

[1037] "The cause is server overload"

[1038] The device automatically records this exchange as text data and sends it to the server.

[1039] 3. Data Analysis:

[1040] The server uses AI to analyze the recorded text data.

[1041] On the server, AI extracts from the text data the following: "System down," "Affecting all users," "Cause is server overload," "Estimated time of resolution is 2:00 p.m.", and "Increasing server resources to prevent recurrence."

[1042] 4. Sentiment analysis and adjustment:

[1043] The server uses an emotion engine to analyze emotions such as "stress" and "anxiety" from user interactions.

[1044] The server adjusts the tone of the report based on the emotional information. For example, if an urgent part expresses strong emotions, it will describe that part in more detail and add expressions to soften the emotions.

[1045] 5. Automatic report generation:

[1046] The server automatically generates a final report based on the extracted information and the tone adjusted by the emotion engine.

[1047] Example: "A system outage occurred on October 12, 2023 at 1:00 PM. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence. Users have reported that the issue is urgent and causing increased stress, so special attention is required."

[1048] 6. Report printing and distribution:

[1049] The server saves the generated report in PDF format and sends it to the user.

[1050] The user checks the report received by email and makes corrections or comments as necessary.

[1051] This not only speeds up response after an accident occurs, but also enables more appropriate responses that take into account the user's emotions.

[1052] The processing flow will be explained below.

[1053] Step 1:

[1054] Data preparation (user)

[1055] Users prepare text files or documents detailing the service content and business procedures.

[1056] Example: "Service Contents_Business Procedures.docx" contains an overview of the service, daily business procedures, and past problems and their solutions.

[1057] Step 2:

[1058] Data upload (user)

[1059] The user uploads the prepared text files or documents to the server via the terminal.

[1060] Users transfer files to the server using a dedicated upload interface.

[1061] Step 3:

[1062] Data learning (server)

[1063] The server receives the uploaded documents and feeds them into the AI ​​learning model.

[1064] The server builds a knowledge base by having the AI ​​learn business procedures and problem-solving measures.

[1065] Step 4:

[1066] Information collection in the event of an accident (terminal)

[1067] When an accident occurs, users report the details of the accident using a chat system or email.

[1068] The device records these interactions as text data in real time.

[1069] Step 5:

[1070] Data transmission (terminal)

[1071] The terminal automatically transmits the recorded text data to the server.

[1072] The transmission process is performed by periodic synchronization or trigger events.

[1073] Step 6:

[1074] Receive text data (server)

[1075] The server receives the text data sent from the terminal.

[1076] The received data includes details such as the time of the accident, the extent of the impact, and the cause.

[1077] Step 7:

[1078] Text analysis (server)

[1079] The server inputs the received text data into an AI analysis engine and performs the analysis.

[1080] AI extracts details of the accident, the type of malfunction, the extent of the impact, and the cause.

[1081] Step 8:

[1082] Sentiment analysis (server)

[1083] The server utilizes an emotion engine to analyze the user's emotional state from the text data.

[1084] For example, it can determine whether a user is feeling anxious or stressed from the tone of the text or specific keywords.

[1085] Step 9:

[1086] Organizing analysis results (server)

[1087] The server organizes the analysis results based on the information extracted by the AI.

[1088] This includes not only details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, but also the user's emotional state.

[1089] Step 10:

[1090] Report template generation (server)

[1091] The server generates a report template based on the organized information.

[1092] The template applies a prescribed format and also adjusts the tone based on emotion.

[1093] Step 11:

[1094] Final check (server)

[1095] The server performs a final check of the generated report template to check for any defects.

[1096] If an error is detected, data analysis and sentiment analysis are performed again.

[1097] Step 12:

[1098] Report storage (server)

[1099] The server stores the final verified report in PDF format.

[1100] The saved file contains detailed information about the accident, including an overview of the incident, the extent of the impact, the cause, countermeasures, and the results of user sentiment analysis.

[1101] Step 13:

[1102] Sending reports (server)

[1103] The server automatically sends the generated report to the user.

[1104] Typically, email is used to send reports and confirm receipt of the reports.

[1105] Step 14:

[1106] User Verification (User)

[1107] The user checks the report received by email to ensure there are no errors in the content.

[1108] Make any necessary corrections or comments, and share the final report internally.

[1109] Example 2

[1110] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1111] While it is necessary to take prompt and accurate countermeasures when an accident occurs during service operation, many systems require time-consuming manual report creation and the formulation of preventive measures, which can increase user dissatisfaction and stress.Furthermore, it is difficult to create reports that take emotional evaluation into account, and reports are not always written in an appropriate tone or with appropriate expressions.

[1112] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an information processing means that has previously learned the service content and business procedures, a data collection means that collects exchanges via communication means after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report containing details of the malfunction, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an emotion analysis means that analyzes the emotional state of the user and adjusts the tone and expression of the report. This makes it possible to automatically generate a quick and accurate report when an accident occurs and to report in an appropriate tone that takes emotions into consideration.

[1113] "Information processing means" refers to a method or device for learning service content and business procedures in advance.

[1114] "Data collection means" refers to a method or device for collecting communication via means of communication after an accident occurs as text data.

[1115] "Analysis means" refers to a method or device for analyzing collected text data and automatically generating a report on the details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[1116] "Output means" refers to a method or device for outputting the automatically generated report content.

[1117] "Emotion analysis means" refers to a method or device for analyzing a user's emotional state and adjusting the tone and expression of the report.

[1118] This invention is a system that automatically generates report content and preventive measures quickly and efficiently when an accident occurs during service operation. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the tone and expression of the report content, enabling more appropriate responses.

[1119] Specifically, the system includes "information processing means," "data collection means," "analysis means," "output means," and "emotion analysis means."

[1120] First, the user prepares a text file or document (e.g., PDF or Word file) detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The information processing means used for the hardware or software includes natural language processing libraries (e.g., NLTK, SpaCy) and machine learning frameworks (e.g., TensorFlow, PyTorch). The server trains an AI on the uploaded document and builds a knowledge base that determines how to respond when a system abnormality occurs.

[1121] Next, when an accident occurs, the user reports the details of the accident through a communication method such as a chat system or email. The device records this report in real time as text data and sends it to the server. Specifically, the user reports, for example, "The system went down at 1:00 PM," "All users are affected," and "The cause was a server overload."

[1122] The server uses the received text data as an analytical tool, and the AI ​​begins its analysis. Software used includes text analysis tools (e.g., ElasticSearch, Apache Lucene). Details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence are extracted from the text data and automatically generated as a report.

[1123] The generated report content is analyzed using a sentiment analysis means to determine the emotional state of the user's interactions. For example, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) to read "stress" or "urgency" from the user's message and reflects the results in the report content. The sentiment analysis means adjusts the tone and expression of the report content as necessary and converts it into a more appropriate format.

[1124] Finally, the server saves the generated report in a specified format (e.g., PDF) and sends it to the user, using software such as document generation tools (e.g., LaTeX, ReportLab). Finally, the user receives the report and can make additional corrections or comments if necessary.

[1125] Prompt Sentence Examples

[1126] Examples of prompts for specific scenarios:

[1127] "The system went down at 1:00 PM, affecting all users. The cause was server overload. Please automatically generate a report outlining effective measures to prevent recurrence."

[1128] As a result, not only can responses after an accident be made more quickly, but more appropriate responses can be made that take into account the user's emotions.

[1129] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1130] Step 1: Prepare and upload your documents

[1131] The user prepares a text file or document (e.g., PDF or Word file) that describes the service content and business procedures. Specifically, the user prepares their company's service manual or process document.

[1132] The user uploads the prepared document to the server via the terminal. The input is a file containing a service manual or procedure manual. The output is the document uploaded to the server.

[1133] Step 2: The learning process

[1134] The server uses the received documents as a means of information processing and trains the AI. Specifically, it analyzes the document content using natural language processing libraries (e.g., NLTK, SpaCy) and machine learning frameworks (e.g., TensorFlow, PyTorch) and adds it to the training dataset.

[1135] The server builds a knowledge base based on what the AI ​​has learned. The uploaded documents are used as input, and the output is an AI model that has learned how to respond to system anomalies.

[1136] Step 3: Report the incident

[1137] When an accident occurs, users report details using communication methods such as chat systems or email. Specifically, users send information such as "The system went down at 13:00," "All users are affected," and "The cause is server overload" via chat messages or email.

[1138] The input is text data describing the details of the accident, and the output is text data in which the report content is recorded in real time.

[1139] Step 4: Data collection

[1140] The device records the accident report exchange as text data in real time and sends it to the server. Specifically, the device automatically captures chat logs and email content, organizes it into an appropriate format, and uploads it to the server.

[1141] The input is the text data of the accident report submitted by the user, and the output is well-formed text data sent to the server.

[1142] Step 5: Data analysis

[1143] The server uses the received text data as an analytical tool, and the AI ​​begins its analysis. Specifically, it uses a text analysis tool (e.g., ElasticSearch, Apache Lucene) to extract important information from the received data, such as "system down," "affecting all users," and "cause of server overload."

[1144] The server updates the knowledge base based on the analysis results and formats them appropriately. The input is the text data received by the server, and the output is a draft of the accident report.

[1145] Step 6: Emotion analysis and tone adjustment

[1146] The server uses an emotion engine to analyze the user's emotional state from their interactions. Specifically, the emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) analyzes emotions such as "stress" and "urgency" from the user's message and generates a score.

[1147] The server adjusts the tone of the report based on the emotional information: the inputs are the analyzed emotional scores and the draft incident report, and the output is the emotionally adjusted final report.

[1148] Step 7: Automatic report generation

[1149] The server automatically generates a final report based on the extracted information and the results of sentiment analysis. Specifically, it uses document generation tools such as LaTeX and ReportLab to format the text data and generate the report.

[1150] The inputs are the sentiment analysis results and the contents of the incident report, and the output is the final report in a digital format (e.g., PDF).

[1151] Step 8: Print and distribute the report

[1152] The server saves the generated report in a specified format (e.g. PDF) and sends it to the user. Specifically, the server saves the generated report in a specified directory and sends it to the user via email or system notification.

[1153] The user reviews the received report and makes any necessary corrections or comments. The generated report is used as input, and the final report including the user's feedback is obtained as output.

[1154] (Application example 2)

[1155] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1156] When a system failure or accident occurs at a logistics center, a prompt and appropriate response is required. However, conventional methods have the drawback of taking time to create a report and formulate measures to prevent recurrence, and it is also difficult to respond in a way that appropriately reflects the stress and impatience of the person in charge. To solve these problems, the present invention aims to provide a system that quickly and automatically generates accident report content and adjusts the tone of the report taking into account the user's emotional state.

[1157] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1158] In this invention, the server includes an information processing means that has learned service content and business procedures in advance, a data collection means that collects exchanges via communication tools after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report containing details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, an emotion analysis means that adjusts the tone and expression of the automatically generated report, and an output means that outputs the automatically generated report. This enables the rapid automatic generation of accident report content, and further enables a more appropriate response by appropriately adjusting the tone to reflect the user's emotional state.

[1159] "Information processing means" refers to a means for learning service content and business procedures in advance.

[1160] "Data collection means" refers to a means of collecting exchanges via communication tools after an accident occurs as text data.

[1161] The "analysis means" is a means for analyzing the collected text data and automatically generating a report containing details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[1162] "Emotion analysis means" is a means for analyzing the user's emotional state in order to adjust the tone and expression of the automatically generated report content.

[1163] The "output means" is a means for converting the automatically generated report content into a predetermined format and sending it to the user.

[1164] The present invention is a system for automatically generating report content and preventive measures in the event of an accident at a logistics center in a prompt and appropriate manner. A specific embodiment of the system will be described below.

[1165] System Configuration

[1166] The system consists of the following main components:

[1167] Information processing means: A means of learning service content and business procedures in advance. For example, uploading business manuals and abnormality response procedures to an AI model on a server and having it learn the information.

[1168] Data collection method: A method for collecting text data from communication tools (e.g., chat systems, emails) after an accident occurs. For example, data entered on a smartphone or device is sent to a server in real time.

[1169] Analysis method: Analyzes collected text data and automatically generates a report containing details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence. This is done using an AI model (e.g., OpenAI GPT-3).

[1170] Sentiment analysis: Analyzing the user's emotional state in order to adjust the tone and expression of the automatically generated report. For example, using a sentiment analysis tool such as TextBlob.

[1171] Output means: A means to convert the automatically generated report content into a specified format (e.g. PDF) and send it to the user. For example, generate a PDF using the FPDF library.

[1172] Program processing explanation

[1173] The server first learns the logistics center's operational procedures and abnormality response procedures as an information processing tool in advance, allowing the AI ​​model on the server to understand basic response methods for various accidents and malfunctions.

[1174] When an accident occurs, users report the details of the accident using the communication tools on their smartphones. This data is collected as text data by the smartphone as a data collection means and sent to the server in real time.

[1175] The server analyzes the received text data using an AI model (OpenAI GPT-3), which extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and automatically generates a report.

[1176] The automatically generated report content is analyzed using emotion analysis to detect the user's emotional state (e.g., stress or impatience from the text) and adjust the tone and expression accordingly. For example, TextBlob is used to analyze the user's emotional state.

[1177] Finally, the server formats the report content (e.g., PDF) and sends it to the user via an output means, which uses the FPDF library to generate the PDF.

[1178] Examples of concrete examples and prompts

[1179] In a specific scenario, if a system error occurs at a distribution center, an employee enters the following details into their smartphone:

[1180] Example: "At 2:30 PM, shipping processing was halted due to a system error. All centers were affected. The cause was a database overload. The error is expected to be resolved by 3:30 PM."

[1181] This data is sent in real time to a server where an AI model generates the following prompts and creates a report:

[1182] Example prompt: "At 2:30 PM, a system error halted shipping processing. This affected all centers. The cause was a database overload. The error is expected to be resolved by 3:30 PM. Please use these details to create an incident report for the distribution center."

[1183] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1184] Step 1:

[1185] The user uploads the logistics center's work procedures and anomaly response procedures to the server. The server receives this as an information processing tool and trains the AI ​​model. The input is the work procedures and anomaly response procedures file, and the output is the trained AI model. The specific operations performed in this step are for the server to receive the files, read them sequentially into the AI ​​model, and have it learn the service content and work procedures.

[1186] Step 2:

[1187] When an accident occurs, the user uses a smartphone communication tool to input details of the accident (e.g., time of occurrence, extent of impact, cause, estimated time to resolve, etc.). The input is detailed information about the accident entered by the user, and the output is the accident information as text data. Specifically, the user uses the smartphone's chat system or email to enter the details of the accident in text format, which is then recorded on the device.

[1188] Step 3:

[1189] The terminal transmits the collected text data to the server in real time. The input is the text data generated in step 2, and the output is the text data transmitted to the server. The specific operation performed in this step is that the terminal transmits the text data to the server using an appropriate network protocol.

[1190] Step 4:

[1191] The server uses an AI model to analyze the received text data. The input is the text data sent to the server, and the output is the analysis results regarding the details of the defect, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence. Specifically, the AI ​​model (e.g., OpenAI GPT-3) analyzes the text data, extracts each item, and automatically generates the report content.

[1192] Step 5:

[1193] The automatically generated report content uses emotion analysis tools to analyze the user's emotional state (e.g., stress or impatience) and adjusts the tone and expression accordingly. The input is the automatically generated report content and text data indicating the user's emotional state, and the output is the report content with the adjusted tone and expression. Specifically, it uses emotion analysis tools such as TextBlob to analyze the user's emotional state, and the AI ​​model adjusts the vocabulary and style to be appropriate.

[1194] Step 6:

[1195] The server finally formats the report content into a specified format (e.g. PDF) and sends it to the user. The input is the report content with adjusted tone and expression, and the output is a report formatted in the specified format (PDF). Specifically, the server uses the FPDF library to generate the report content as a PDF and sends it to the user via email or other means.

[1196] This will enable the logistics center to respond to accident reports quickly and appropriately.

[1197] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1198] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1199] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1200] [Fourth embodiment]

[1201] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1202] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1203] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1204] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1205] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1206] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1207] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1208] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1209] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1210] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1211] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1212] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1213] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1214] The present invention provides a system for automatically generating report content and preventive measures quickly and efficiently when an unexpected accident occurs during service operation. The system includes an information processing unit, a data collection unit, an analysis unit, and an output unit.

[1215] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The server uses this as an information processing tool and has the AI ​​learn the contents of the document. Based on the learned service content and business procedures, the AI ​​builds a knowledge base to quickly derive appropriate countermeasures.

[1216] Next, when an accident occurs, the user reports the details of the accident through a communication tool (e.g., a chat system or email). The device uses this communication as a means of collecting data and records it as text data in real time. The recorded data is automatically sent to the server.

[1217] The server uses the transmitted text data as an analytical tool, and the AI ​​begins its analysis. The AI ​​extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence from the text data, and automatically generates a report. This report is then formatted appropriately based on the analysis results.

[1218] The server then uses the prepared report content as an output means and saves it in a specified format (e.g., PDF).Finally, the automatically generated report is sent to the user, who can check the report and make additional corrections or comments as necessary.

[1219] Specific examples

[1220] 1. Initial Setup:

[1221] The user prepares an operation manual and an abnormality response procedure manual for the "customer support system" and uploads them to the server.

[1222] The server uses AI to learn from the uploaded documents and understand how to respond if a system abnormality occurs.

[1223] 2. Information gathering after an accident:

[1224] Users can use the chat system to report:

[1225] "System went down at 13:00"

[1226] "All users are affected"

[1227] "The cause is server overload"

[1228] The device automatically records this exchange as text data and sends it to the server.

[1229] 3. Data Analysis:

[1230] The server uses AI to analyze the recorded text data.

[1231] On the server, AI extracts from the text data the following: "System down," "Affecting all users," "Cause is server overload," "Estimated time of resolution is 2:00 p.m.", and "Increasing server resources to prevent recurrence."

[1232] 4. Automatic report generation:

[1233] The server automatically generates a report based on the extracted information.

[1234] Example: "A system outage occurred on October 12, 2023 at 1:00 PM. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence."

[1235] 5. Report printing and distribution:

[1236] The server saves the generated report in PDF format and sends it to the user.

[1237] The user checks the report received by email and makes corrections or comments as necessary.

[1238] This will speed up the response after an accident occurs and significantly reduce the effort required by the user.

[1239] The processing flow will be explained below.

[1240] Step 1:

[1241] Data preparation (user)

[1242] The user prepares a text file or document that specifically describes the service content and business procedures.

[1243] Example: "Service Contents_Business Procedures.docx" contains an overview of the service, daily business procedures, and common problems and their solutions.

[1244] Step 2:

[1245] Data upload (user)

[1246] The user uploads the prepared text files or documents to the server via the terminal.

[1247] Uploading is done using a dedicated upload function.

[1248] Step 3:

[1249] Data learning (server)

[1250] The server takes the uploaded documents and feeds them into an AI model, which learns important information.

[1251] The information to be learned includes business procedures, how to respond to errors, and examples of past accidents.

[1252] Step 4:

[1253] Information collection in the event of an accident (terminal)

[1254] When an accident occurs, users report the details of the accident using a chat system or email.

[1255] The device records these interactions as text data in real time.

[1256] Step 5:

[1257] Data transmission (terminal)

[1258] The terminal automatically transmits the recorded text data to the server.

[1259] The transmission can be by a periodically executed process or by a trigger event.

[1260] Step 6:

[1261] Data reception (server)

[1262] The server receives the text data sent from the terminal.

[1263] The received data includes detailed information such as the time of the accident, the extent of the impact, and the cause.

[1264] Step 7:

[1265] Text analysis (server)

[1266] The server inputs the received text data into the AI ​​and analyzes the details of the accident, the type of malfunction, the extent of the impact, the cause, etc.

[1267] The AI ​​uses natural language processing techniques to extract important keywords and phrases.

[1268] Step 8:

[1269] Organizing analysis results (server)

[1270] The server organizes the report content based on the information extracted by the AI.

[1271] Specifically, it summarizes details of the problem, the scope of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[1272] Step 9:

[1273] Report template generation (server)

[1274] The server generates a report template based on the organized information.

[1275] The template applies pre-trained formats.

[1276] Step 10:

[1277] Final check (server)

[1278] The server performs a final check on the generated report template to check for errors.

[1279] Step 11:

[1280] Report storage (server)

[1281] The server stores the final verified report in a format such as PDF.

[1282] The saved files contain detailed information about the accident, its scope of impact, causes, and countermeasures.

[1283] Step 12:

[1284] Sending reports (server)

[1285] The server automatically sends the generated report to the user.

[1286] It is usually sent through communication tools such as email.

[1287] Step 13:

[1288] User Verification (User)

[1289] The user checks the report received by email and makes additional corrections or comments as necessary.

[1290] Once the final report is completed, it will be shared with internal stakeholders.

[1291] Example 1

[1292] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1293] In modern service operations, when unexpected accidents occur, a rapid and accurate response is required. Traditional manual methods of creating reports and documenting preventative measures require a lot of time and effort, and there is also a risk of information being overlooked or mistyped. This can delay the response to the accident and cause further problems. To address these issues, this invention aims to provide a system that automatically generates rapid and efficient report content and preventative measures when an accident occurs.

[1294] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1295] In this invention, the server includes an information processing means that has learned the service content and business procedures in advance, a data collection means that collects communication via the communication means after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report on the details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an output means that saves the automatically generated report in a predetermined format and provides the information. This enables a quick response after an accident occurs and efficient report creation.

[1296] "Information processing means" refers to devices and programs that allow AI to learn service content and business procedures.

[1297] "Data collection means" refers to a device and program that collects text data exchanged through communication means after an accident occurs.

[1298] "Analysis means" refers to a device and program that analyzes collected text data, extracts details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence, and automatically generates report content.

[1299] "Output means" refers to a device and program that saves the automatically generated report content in a predetermined format and provides the information.

[1300] "Service Content" refers to the full range of functionality and support provided by a particular Service.

[1301] "Business procedures" refers to documents that describe specific work procedures and response methods for service operation.

[1302] "Means of communication" refers to tools for exchanging text data, such as chat systems and email.

[1303] "Text data" refers to character data sent and received via communication means.

[1304] "Details of the malfunction" refers to the specific content and circumstances of the accident or problem.

[1305] "Scope of impact" refers to the range and scale of the impact caused by the malfunction.

[1306] "Cause" refers to the reason or background behind the occurrence of the defect.

[1307] "Resolution date and time" refers to the time when the defect is scheduled to be resolved or the time when it is actually resolved.

[1308] "Measures to prevent recurrence" refers to specific measures to prevent the recurrence of similar defects.

[1309] "Report" refers to a detailed written report of a defect generated by the analysis means.

[1310] "Prescribed format" refers to the standard file format (e.g., PDF) in which the generated report content is stored and provided.

[1311] The present invention provides a system that automatically generates report content and preventive measures quickly and efficiently when an unexpected accident occurs during service operation. This system includes an information processing unit, a data collection unit, an analysis unit, and an output unit. Specific embodiments of the system are described below.

[1312] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of an accident and how to respond. Specifically, the user uses a text editor or similar tool to create an operation manual for the "customer support system" or an abnormality response procedure manual, and then uploads it to the server.

[1313] The server uses the uploaded documents as a means of information processing and uses a generative AI model (e.g., BERT or GPT) to learn the contents of the documents, allowing the AI ​​to build a knowledge base that can quickly derive countermeasures based on service content and business procedures.

[1314] Next, when an accident occurs, the user reports the details of the accident using a communication method such as a chat system or email. For example, they might report something like, "The system went down at 1:00 PM," "All users are affected," or "The cause was a server overload." The device uses this exchange as a means of collecting data and records it as text data. This recorded data is automatically sent to the server.

[1315] The server uses the text data as an analytical tool, and the AI ​​begins analyzing it. In the analytical tool, the AI ​​extracts important information from the text data, such as "System down," "All users affected," "Cause is server overload," "Estimated resolution time is 2:00 PM," and "Server resources will be increased to prevent recurrence."

[1316] The server then automatically generates a report based on the extracted information. The generated report is formatted using a template engine. Specifically, the report generated looks like this:

[1317] "A system outage occurred at 1:00 PM on October 12, 2023. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence."

[1318] The server saves the report in a predetermined format, such as PDF, and sends it to the user. A PDF generator library (e.g., PDFKit or ReportLab) is used for saving the report. The user can then review the report received by email and make any necessary corrections or comments.

[1319] This will speed up the response after an accident occurs and significantly reduce the effort required by the user.

[1320] Example prompt sentence:

[1321] "The system went down at 13:00. All users are affected. The cause was server overload."

[1322] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1323] Step 1:

[1324] The user prepares and creates text files and documents that detail the service content and business procedures. These include system operation manuals and abnormality response procedures. Specifically, the user uses a text editor to create a detailed business procedure manual that describes how to operate the "customer support system" and the response procedures in the event of an abnormality. This document becomes the input data.

[1325] Step 2:

[1326] Users upload text files or documents they have created to a server via their terminal. Specifically, they use a web interface or dedicated upload tool to send the document to a specified location. At this stage, the input data is the text file or document, and the output is a notification that the upload has been completed.

[1327] Step 3:

[1328] The server uses the uploaded document as a means of information processing, learning the document's contents using a generative AI model (e.g., BERT or GPT). The input here is the document uploaded by the user, and the output is a knowledge base in which the AI ​​understands the service content and business procedures. Specifically, the server performs text analysis of the document's contents and stores them in a database using a learning algorithm.

[1329] Step 4:

[1330] When an accident occurs, the user reports the details of the accident using a communication method such as a chat system or email. The specific report content is "The system went down at 13:00," "All users are affected," and "The cause was a server overload." The input in this step is a text message containing the details of the accident, and the output is the generation of text data.

[1331] Step 5:

[1332] The device uses this exchange as a data collection tool and records it as text data in real time. The input is the text message sent and received via the communication tool, and the output is the recorded text data. Specific operations include recording the contents of chats and emails in a database using system logs and storage functions.

[1333] Step 6:

[1334] The recorded text data is automatically sent to the server, which receives it. The input here is the text data sent from the device, and the output is the text data saved on the server. Specifically, the server receives the data using an API or data transfer service and stores it in a database.

[1335] Step 7:

[1336] The server uses the transmitted text data as an analytical tool and begins analysis using a generative AI model. During this analysis, important information is extracted from the text data, such as "System down," "All users affected," "Cause is server overload," "Estimated resolution time is 2:00 PM," and "Server resources will be increased to prevent recurrence." The input is the received text data, and the output is the extracted important information. Specifically, the data is analyzed using a pixel processing engine and natural language processing algorithms.

[1337] Step 8:

[1338] The server automatically generates a report based on the extracted information. The input is the key information extracted through analysis, and the output is the report content arranged in a report template. Specifically, a template engine is used to embed the extracted information into a specified report format.

[1339] Step 9:

[1340] The server saves the generated report in PDF format. The tool used here is a PDF generator library (e.g. PDFKit or ReportLab). The input is the formatted report content, and the output is a PDF file. Specifically, the report content is formatted using a template engine, and the file is generated using a PDF generator.

[1341] Step 10:

[1342] Finally, the server sends the generated PDF to the user. The input is the PDF file, and the output is a notification of completion of sending. Specifically, it uses a mail library (e.g., SMTP) to send an email with the PDF file attached to the user's address. The user checks the received report and makes additional corrections or comments as necessary.

[1343] (Application example 1)

[1344] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1345] It is extremely important to quickly and efficiently respond to quality and production line problems that occur within a factory and to appropriately implement measures to prevent recurrence. However, with conventional systems, it took a long time to report accidents and formulate preventive measures, and there was a tendency for human error and omissions to occur. In particular, manually creating complex accident reports and preventive measures required a great deal of effort and time, which was a major obstacle in workplaces where a rapid response was required. Given this current situation, there was a need for a system that could automatically create detailed reports when an accident occurred and propose efficient preventive measures.

[1346] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1347] In this invention, the server includes an information processing means that has been trained on service content and business procedures in advance, a data collection means that collects exchanges via communication tools after an accident occurs as text data, an analysis means that uses a generative AI model to analyze the collected text data and automatically generate a report on the details of the defect, the scope of impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an output means that converts the automatically generated report into a PDF in a predetermined format and outputs it. This makes it possible to quickly and efficiently create a detailed report and propose measures to prevent recurrence when an accident occurs in a factory.

[1348] "Information processing means" refers to a means for learning the service content and business procedures in advance and then performing processing to derive countermeasures based on that information.

[1349] "Data collection means" refers to a means of collecting exchanges via communication tools after an accident occurs as text data.

[1350] A "generative AI model" is an artificial intelligence model that analyzes collected data and automatically generates report content.

[1351] The "analysis means" is a means for analyzing collected text data using a generative AI model and automatically generating a report containing details of the defect, the scope of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[1352] The "output means" is a means for converting the automatically generated report into a PDF in a predetermined format and saving or transmitting it to the user.

[1353] "PDF" stands for Portable Document Format, a format for electronically storing and distributing documents while preserving their layout.

[1354] This invention is a "Smart Factory Incident Manager" system that responds quickly and efficiently to quality and production line problems that occur within a factory. Specific processing procedures for implementing this system will be described below.

[1355] System Overview

[1356] The system mainly consists of the following elements:

[1357] 1. Information processing method: Study documents such as factory operation manuals and abnormality response procedures in advance to build a knowledge base.

[1358] 2. Data collection method: Collect text data from interactions using communication tools after the accident.

[1359] 3. Analysis method: The collected text data is analyzed using a generative AI model to automatically generate a report containing details of the defect, the scope of impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[1360] 4. Output method: The automatically generated report is converted into a PDF in a specified format and saved or sent to the user.

[1361] Hardware and Software

[1362] The hardware and software used to implement this system are as follows:

[1363] Hardware: Factory robots (e.g. KUKA, Fanuc)

[1364] software:

[1365] Python: a programming language

[1366] OpenAI GPT-3: Generative AI model

[1367] pdfkit: A library for converting HTML and strings to PDF

[1368] Detailed procedure

[1369] 1. Information gathering and learning

[1370] The user prepares documents such as operation manuals and abnormality response procedures and uploads them to the server.

[1371] The server reads these documents and builds a knowledge base by training the AI.

[1372] 2. Collecting accident information

[1373] When an accident occurs, users can report the details of the accident via chat system or email. For example, "Production line 2 stopped at 14:00 on October 12, 2023. The cause was a robot arm malfunction. The expected time of resolution is 15:30."

[1374] The terminal records this exchange as text data and transmits it to the server.

[1375] 3. Analysis and report generation

[1376] The server analyzes the transmitted text data using a generative AI model (OpenAI GPT-3) to extract details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[1377] Report content is automatically generated based on the collected data.

[1378] 4. PDF Output

[1379] The server converts the generated report content into a PDF in a predetermined format and saves it using an output means.

[1380] If necessary, the server sends the PDF to the user.

[1381] Specific examples

[1382] For example, based on the accident information "Occurrence date and time: October 12, 2023, 14:00," "Affected area: Production line 2 stopped," "Cause: Robot arm failure," and "Estimated time of resolution: October 12, 2023, 15:30," the following prompt sentence can be used to have the AI ​​generate a report:

[1383] Prompt Sentence Examples

[1384] Date and time of occurrence: October 12, 2023, 14:00

[1385] Affected area: Production line 2 stopped

[1386] Cause: Robot arm malfunction

[1387] Estimated time of resolution: October 12, 2023, 15:30

[1388] Use this information to generate a report that includes details of the incident, the extent of the impact, the cause, how it was resolved, and how to prevent it from happening again.

[1389] This makes it possible to quickly and efficiently prepare detailed reports and propose measures to prevent recurrence when an accident occurs within a factory.

[1390] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1391] Step 1:

[1392] The user prepares documents such as operation manuals and abnormality response procedures and uploads them to the server.

[1393] Input: Documents (text files) such as operation manuals and abnormality response procedures

[1394] Processing: The server loads these documents and trains a generative AI model to build a knowledge base.

[1395] Output: Trained knowledge base

[1396] Step 2:

[1397] If an accident occurs, users can report the details of the accident via a chat system or email.

[1398] Input: Detailed information about the accident (e.g., "Production Line 2 stopped at 14:00 on October 12, 2023. The cause was a robot arm malfunction. The estimated time of resolution is 15:30.")

[1399] Processing: The device records this exchange as text data and sends it to the server.

[1400] Output: Collected accident report text data

[1401] Step 3:

[1402] The server analyzes the transmitted text data using a generative AI model to extract details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[1403] Input: Collected accident report text data

[1404] Processing: The generative AI model analyzes the text data and extracts information such as defect details, scope of impact, cause, resolution date and time, and measures to prevent recurrence.

[1405] Output: Extracted information (details of the defect, scope of impact, cause, resolution date and time, measures to prevent recurrence)

[1406] Step 4:

[1407] The server automatically generates a report based on the extracted information.

[1408] Input: Extracted information

[1409] Processing: The generative AI model automatically generates report content in a specified format based on the extracted information.

[1410] Output: Auto-generated report text

[1411] Step 5:

[1412] The server converts the automatically generated report into a PDF in a predetermined format and saves or transmits it to the user.

[1413] Input: Auto-generated report text

[1414] Processing: The server converts the report to PDF using the pdfkit library, saves it in the required format, and sends the PDF to the user if necessary.

[1415] Output: Report in PDF format

[1416] In this way, the system automates all processes, making it possible to quickly and efficiently create accident reports and implement measures to prevent recurrence.

[1417] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1418] The present invention is a system that automatically generates report content and preventive measures quickly and efficiently when an accident occurs during service operation. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the tone and expression of the report content, enabling a more appropriate response. The system of the present invention has information processing means, data collection means, analysis means, output means, and an emotion engine.

[1419] First, the user prepares a text file or document detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The server uses this as an information processing tool and has the AI ​​learn the contents of the document. Based on the learned service content and business procedures, the AI ​​builds a knowledge base to quickly derive appropriate countermeasures.

[1420] Next, when an accident occurs, the user reports the details of the accident through a communication tool (e.g., a chat system or email). The device uses this communication as a means of collecting data and records it as text data in real time. The recorded data is automatically sent to the server.

[1421] The server uses the transmitted text data as an analytical tool, and the AI ​​begins its analysis. The AI ​​extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence from the text data, and automatically generates a report. This report is then formatted appropriately based on the analysis results and passed to the emotion engine.

[1422] The emotion engine analyzes the user's emotional state from their interactions. For example, it reads emotions such as stress or impatience from the user's writing and reflects them in the analysis results. If necessary, it adjusts the tone and expression of the report and converts it into a more appropriate format.

[1423] The server then uses the prepared report content as an output means and saves it in a specified format (e.g., PDF).Finally, the automatically generated report is sent to the user, who can check the report and make additional corrections or comments as necessary.

[1424] Specific examples

[1425] 1. Initial Setup:

[1426] The user prepares an operation manual and an abnormality response procedure manual for the "customer support system" and uploads them to the server.

[1427] The server uses AI to learn from the uploaded documents and understand how to respond if a system abnormality occurs.

[1428] 2. Information gathering after an accident:

[1429] Users can use the chat system to report:

[1430] "System went down at 13:00"

[1431] "All users are affected"

[1432] "The cause is server overload"

[1433] The device automatically records this exchange as text data and sends it to the server.

[1434] 3. Data Analysis:

[1435] The server uses AI to analyze the recorded text data.

[1436] On the server, AI extracts from the text data the following: "System down," "Affecting all users," "Cause is server overload," "Estimated time of resolution is 2:00 p.m.", and "Increasing server resources to prevent recurrence."

[1437] 4. Sentiment analysis and adjustment:

[1438] The server uses an emotion engine to analyze emotions such as "stress" and "anxiety" from user interactions.

[1439] The server adjusts the tone of the report based on the emotional information. For example, if an urgent part expresses strong emotions, it will describe that part in more detail and add expressions to soften the emotions.

[1440] 5. Automatic report generation:

[1441] The server automatically generates a final report based on the extracted information and the tone adjusted by the emotion engine.

[1442] Example: "A system outage occurred on October 12, 2023 at 1:00 PM. All users were affected. The cause was server overload. The issue is expected to be resolved by 2:00 PM. Server resources will be increased to prevent recurrence. Users have reported that the issue is urgent and causing increased stress, so special attention is required."

[1443] 6. Report printing and distribution:

[1444] The server saves the generated report in PDF format and sends it to the user.

[1445] The user checks the report received by email and makes corrections or comments as necessary.

[1446] This not only speeds up response after an accident occurs, but also enables more appropriate responses that take into account the user's emotions.

[1447] The processing flow will be explained below.

[1448] Step 1:

[1449] Data preparation (user)

[1450] Users prepare text files or documents detailing the service content and business procedures.

[1451] Example: "Service Contents_Business Procedures.docx" contains an overview of the service, daily business procedures, and past problems and their solutions.

[1452] Step 2:

[1453] Data upload (user)

[1454] The user uploads the prepared text files or documents to the server via the terminal.

[1455] Users transfer files to the server using a dedicated upload interface.

[1456] Step 3:

[1457] Data learning (server)

[1458] The server receives the uploaded documents and feeds them into the AI ​​learning model.

[1459] The server builds a knowledge base by having the AI ​​learn business procedures and problem-solving measures.

[1460] Step 4:

[1461] Information collection in the event of an accident (terminal)

[1462] When an accident occurs, users report the details of the accident using a chat system or email.

[1463] The device records these interactions as text data in real time.

[1464] Step 5:

[1465] Data transmission (terminal)

[1466] The terminal automatically transmits the recorded text data to the server.

[1467] The transmission process is performed by periodic synchronization or trigger events.

[1468] Step 6:

[1469] Receive text data (server)

[1470] The server receives the text data sent from the terminal.

[1471] The received data includes details such as the time of the accident, the extent of the impact, and the cause.

[1472] Step 7:

[1473] Text analysis (server)

[1474] The server inputs the received text data into an AI analysis engine and performs the analysis.

[1475] AI extracts details of the accident, the type of malfunction, the extent of the impact, and the cause.

[1476] Step 8:

[1477] Sentiment analysis (server)

[1478] The server utilizes an emotion engine to analyze the user's emotional state from the text data.

[1479] For example, it can determine whether a user is feeling anxious or stressed from the tone of the text or specific keywords.

[1480] Step 9:

[1481] Organizing analysis results (server)

[1482] The server organizes the analysis results based on the information extracted by the AI.

[1483] This includes not only details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, but also the user's emotional state.

[1484] Step 10:

[1485] Report template generation (server)

[1486] The server generates a report template based on the organized information.

[1487] The template applies a prescribed format and also adjusts the tone based on emotion.

[1488] Step 11:

[1489] Final check (server)

[1490] The server performs a final check of the generated report template to check for any defects.

[1491] If an error is detected, data analysis and sentiment analysis are performed again.

[1492] Step 12:

[1493] Report storage (server)

[1494] The server stores the final verified report in PDF format.

[1495] The saved file contains detailed information about the accident, including an overview of the incident, the extent of the impact, the cause, countermeasures, and the results of user sentiment analysis.

[1496] Step 13:

[1497] Sending reports (server)

[1498] The server automatically sends the generated report to the user.

[1499] Typically, email is used to send reports and confirm receipt of the reports.

[1500] Step 14:

[1501] User Verification (User)

[1502] The user checks the report received by email to ensure there are no errors in the content.

[1503] Make any necessary corrections or comments, and share the final report internally.

[1504] Example 2

[1505] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1506] While it is necessary to take prompt and accurate countermeasures when an accident occurs during service operation, many systems require time-consuming manual report creation and the formulation of preventive measures, which can increase user dissatisfaction and stress.Furthermore, it is difficult to create reports that take emotional evaluation into account, and reports are not always written in an appropriate tone or with appropriate expressions.

[1507] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an information processing means that has previously learned the service content and business procedures, a data collection means that collects exchanges via communication means after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report containing details of the malfunction, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and an emotion analysis means that analyzes the emotional state of the user and adjusts the tone and expression of the report. This makes it possible to automatically generate a quick and accurate report when an accident occurs and to report in an appropriate tone that takes emotions into consideration.

[1508] "Information processing means" refers to a method or device for learning service content and business procedures in advance.

[1509] "Data collection means" refers to a method or device for collecting communication via means of communication after an accident occurs as text data.

[1510] "Analysis means" refers to a method or device for analyzing collected text data and automatically generating a report on the details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[1511] "Output means" refers to a method or device for outputting the automatically generated report content.

[1512] "Emotion analysis means" refers to a method or device for analyzing a user's emotional state and adjusting the tone and expression of the report.

[1513] This invention is a system that automatically generates report content and preventive measures quickly and efficiently when an accident occurs during service operation. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system can adjust the tone and expression of the report content, enabling more appropriate responses.

[1514] Specifically, the system includes "information processing means," "data collection means," "analysis means," "output means," and "emotion analysis means."

[1515] First, the user prepares a text file or document (e.g., PDF or Word file) detailing the service content and business procedures. This document details the circumstances of the accident and how to respond. The user then uploads the created document to the server via their device. The information processing means used for the hardware or software includes natural language processing libraries (e.g., NLTK, SpaCy) and machine learning frameworks (e.g., TensorFlow, PyTorch). The server trains an AI on the uploaded document and builds a knowledge base that determines how to respond when a system abnormality occurs.

[1516] Next, when an accident occurs, the user reports the details of the accident through a communication method such as a chat system or email. The device records this report in real time as text data and sends it to the server. Specifically, the user reports, for example, "The system went down at 1:00 PM," "All users are affected," and "The cause was a server overload."

[1517] The server uses the received text data as an analytical tool, and the AI ​​begins its analysis. Software used includes text analysis tools (e.g., ElasticSearch, Apache Lucene). Details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence are extracted from the text data and automatically generated as a report.

[1518] The generated report content is analyzed using a sentiment analysis means to determine the emotional state of the user's interactions. For example, the server uses an emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) to read "stress" or "urgency" from the user's message and reflects the results in the report content. The sentiment analysis means adjusts the tone and expression of the report content as necessary and converts it into a more appropriate format.

[1519] Finally, the server saves the generated report in a specified format (e.g., PDF) and sends it to the user, using software such as document generation tools (e.g., LaTeX, ReportLab). Finally, the user receives the report and can make additional corrections or comments if necessary.

[1520] Prompt Sentence Examples

[1521] Examples of prompts for specific scenarios:

[1522] "The system went down at 1:00 PM, affecting all users. The cause was server overload. Please automatically generate a report outlining effective measures to prevent recurrence."

[1523] As a result, not only can responses after an accident be made more quickly, but more appropriate responses can be made that take into account the user's emotions.

[1524] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1525] Step 1: Prepare and upload your documents

[1526] The user prepares a text file or document (e.g., PDF or Word file) that describes the service content and business procedures. Specifically, the user prepares their company's service manual or process document.

[1527] The user uploads the prepared document to the server via the terminal. The input is a file containing a service manual or procedure manual. The output is the document uploaded to the server.

[1528] Step 2: The learning process

[1529] The server uses the received documents as a means of information processing and trains the AI. Specifically, it analyzes the document content using natural language processing libraries (e.g., NLTK, SpaCy) and machine learning frameworks (e.g., TensorFlow, PyTorch) and adds it to the training dataset.

[1530] The server builds a knowledge base based on what the AI ​​has learned. The uploaded documents are used as input, and the output is an AI model that has learned how to respond to system anomalies.

[1531] Step 3: Report the incident

[1532] When an accident occurs, users report details using communication methods such as chat systems or email. Specifically, users send information such as "The system went down at 13:00," "All users are affected," and "The cause is server overload" via chat messages or email.

[1533] The input is text data describing the details of the accident, and the output is text data in which the report content is recorded in real time.

[1534] Step 4: Data collection

[1535] The device records the accident report exchange as text data in real time and sends it to the server. Specifically, the device automatically captures chat logs and email content, organizes it into an appropriate format, and uploads it to the server.

[1536] The input is the text data of the accident report submitted by the user, and the output is well-formed text data sent to the server.

[1537] Step 5: Data analysis

[1538] The server uses the received text data as an analytical tool, and the AI ​​begins its analysis. Specifically, it uses a text analysis tool (e.g., ElasticSearch, Apache Lucene) to extract important information from the received data, such as "system down," "affecting all users," and "cause of server overload."

[1539] The server updates the knowledge base based on the analysis results and formats them appropriately. The input is the text data received by the server, and the output is a draft of the accident report.

[1540] Step 6: Emotion analysis and tone adjustment

[1541] The server uses an emotion engine to analyze the user's emotional state from their interactions. Specifically, the emotion engine (e.g., IBM Watson Tone Analyzer, Microsoft Azure Text Analytics) analyzes emotions such as "stress" and "urgency" from the user's message and generates a score.

[1542] The server adjusts the tone of the report based on the emotional information: the inputs are the analyzed emotional scores and the draft incident report, and the output is the emotionally adjusted final report.

[1543] Step 7: Automatic report generation

[1544] The server automatically generates a final report based on the extracted information and the results of sentiment analysis. Specifically, it uses document generation tools such as LaTeX and ReportLab to format the text data and generate the report.

[1545] The inputs are the sentiment analysis results and the contents of the incident report, and the output is the final report in a digital format (e.g., PDF).

[1546] Step 8: Print and distribute the report

[1547] The server saves the generated report in a specified format (e.g. PDF) and sends it to the user. Specifically, the server saves the generated report in a specified directory and sends it to the user via email or system notification.

[1548] The user reviews the received report and makes any necessary corrections or comments. The generated report is used as input, and the final report including the user's feedback is obtained as output.

[1549] (Application example 2)

[1550] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1551] When a system failure or accident occurs at a logistics center, a prompt and appropriate response is required. However, conventional methods have the drawback of taking time to create a report and formulate measures to prevent recurrence, and it is also difficult to respond in a way that appropriately reflects the stress and impatience of the person in charge. To solve these problems, the present invention aims to provide a system that quickly and automatically generates accident report content and adjusts the tone of the report taking into account the user's emotional state.

[1552] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1553] In this invention, the server includes an information processing means that has learned service content and business procedures in advance, a data collection means that collects exchanges via communication tools after an accident occurs as text data, an analysis means that analyzes the collected text data and automatically generates a report containing details of the problem, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, an emotion analysis means that adjusts the tone and expression of the automatically generated report, and an output means that outputs the automatically generated report. This enables the rapid automatic generation of accident report content, and further enables a more appropriate response by appropriately adjusting the tone to reflect the user's emotional state.

[1554] "Information processing means" refers to a means for learning service content and business procedures in advance.

[1555] "Data collection means" refers to a means of collecting exchanges via communication tools after an accident occurs as text data.

[1556] The "analysis means" is a means for analyzing the collected text data and automatically generating a report containing details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence.

[1557] "Emotion analysis means" is a means for analyzing the user's emotional state in order to adjust the tone and expression of the automatically generated report content.

[1558] The "output means" is a means for converting the automatically generated report content into a predetermined format and sending it to the user.

[1559] The present invention is a system for automatically generating report content and preventive measures in the event of an accident at a logistics center in a prompt and appropriate manner. A specific embodiment of the system will be described below.

[1560] System Configuration

[1561] The system consists of the following main components:

[1562] Information processing means: A means of learning service content and business procedures in advance. For example, uploading business manuals and abnormality response procedures to an AI model on a server and having it learn the information.

[1563] Data collection method: A method for collecting text data from communication tools (e.g., chat systems, emails) after an accident occurs. For example, data entered on a smartphone or device is sent to a server in real time.

[1564] Analysis method: Analyzes collected text data and automatically generates a report containing details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence. This is done using an AI model (e.g., OpenAI GPT-3).

[1565] Sentiment analysis: Analyzing the user's emotional state in order to adjust the tone and expression of the automatically generated report. For example, using a sentiment analysis tool such as TextBlob.

[1566] Output means: A means to convert the automatically generated report content into a specified format (e.g. PDF) and send it to the user. For example, generate a PDF using the FPDF library.

[1567] Program processing explanation

[1568] The server first learns the logistics center's operational procedures and abnormality response procedures as an information processing tool in advance, allowing the AI ​​model on the server to understand basic response methods for various accidents and malfunctions.

[1569] When an accident occurs, users report the details of the accident using the communication tools on their smartphones. This data is collected as text data by the smartphone as a data collection means and sent to the server in real time.

[1570] The server analyzes the received text data using an AI model (OpenAI GPT-3), which extracts details of the accident, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence, and automatically generates a report.

[1571] The automatically generated report content is analyzed using emotion analysis to detect the user's emotional state (e.g., stress or impatience from the text) and adjust the tone and expression accordingly. For example, TextBlob is used to analyze the user's emotional state.

[1572] Finally, the server formats the report content (e.g., PDF) and sends it to the user via an output means, which uses the FPDF library to generate the PDF.

[1573] Examples of concrete examples and prompts

[1574] In a specific scenario, if a system error occurs at a distribution center, an employee enters the following details into their smartphone:

[1575] Example: "At 2:30 PM, shipping processing was halted due to a system error. All centers were affected. The cause was a database overload. The error is expected to be resolved by 3:30 PM."

[1576] This data is sent in real time to a server where an AI model generates the following prompts and creates a report:

[1577] Example prompt: "At 2:30 PM, a system error halted shipping processing. This affected all centers. The cause was a database overload. The error is expected to be resolved by 3:30 PM. Please use these details to create an incident report for the distribution center."

[1578] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1579] Step 1:

[1580] The user uploads the logistics center's work procedures and anomaly response procedures to the server. The server receives this as an information processing tool and trains the AI ​​model. The input is the work procedures and anomaly response procedures file, and the output is the trained AI model. The specific operations performed in this step are for the server to receive the files, read them sequentially into the AI ​​model, and have it learn the service content and work procedures.

[1581] Step 2:

[1582] When an accident occurs, the user uses a smartphone communication tool to input details of the accident (e.g., time of occurrence, extent of impact, cause, estimated time to resolve, etc.). The input is detailed information about the accident entered by the user, and the output is the accident information as text data. Specifically, the user uses the smartphone's chat system or email to enter the details of the accident in text format, which is then recorded on the device.

[1583] Step 3:

[1584] The terminal transmits the collected text data to the server in real time. The input is the text data generated in step 2, and the output is the text data transmitted to the server. The specific operation performed in this step is that the terminal transmits the text data to the server using an appropriate network protocol.

[1585] Step 4:

[1586] The server uses an AI model to analyze the received text data. The input is the text data sent to the server, and the output is the analysis results regarding the details of the defect, the extent of the impact, the cause, the date and time of resolution, and measures to prevent recurrence. Specifically, the AI ​​model (e.g., OpenAI GPT-3) analyzes the text data, extracts each item, and automatically generates the report content.

[1587] Step 5:

[1588] The automatically generated report content uses emotion analysis tools to analyze the user's emotional state (e.g., stress or impatience) and adjusts the tone and expression accordingly. The input is the automatically generated report content and text data indicating the user's emotional state, and the output is the report content with the adjusted tone and expression. Specifically, it uses emotion analysis tools such as TextBlob to analyze the user's emotional state, and the AI ​​model adjusts the vocabulary and style to be appropriate.

[1589] Step 6:

[1590] The server finally formats the report content into a specified format (e.g. PDF) and sends it to the user. The input is the report content with adjusted tone and expression, and the output is a report formatted in the specified format (PDF). Specifically, the server uses the FPDF library to generate the report content as a PDF and sends it to the user via email or other means.

[1591] This will enable the logistics center to respond to accident reports quickly and appropriately.

[1592] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1593] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1594] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1595] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1596] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1597] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1598] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1599] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1600] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1601] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1602] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1603] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1604] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1605] 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.

[1606] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1607] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1608] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1609] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1610] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1611] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1612] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1613] The following is further disclosed regarding the above embodiment.

[1614] (Claim 1)

[1615] An information processing means that has learned the service content and business procedures in advance,

[1616] A data collection method for collecting text data from communications made via communication tools after an accident occurs;

[1617] An analysis means for analyzing the collected text data and automatically generating a report on the details of the defect, the extent of its impact, the cause, the date and time of its resolution, and measures to prevent recurrence;

[1618] an output means for outputting the automatically generated report content;

[1619] A system including:

[1620] (Claim 2)

[1621] 2. The system according to claim 1, wherein the analysis means generates a report template including details of the report content, the extent of the impact of the defect, the cause, the date and time of resolution, and measures to prevent recurrence, and performs a final check.

[1622] (Claim 3)

[1623] 2. The system according to claim 1, wherein the output means includes a process for converting the automatically generated report into a predetermined format and transmitting the report to the user.

[1624] "Example 1"

[1625] (Claim 1)

[1626] An information processing means that has learned the service content and business procedures in advance,

[1627] A data collection means for collecting communication exchanges after an accident as text data;

[1628] An analysis means for analyzing the collected text data and automatically generating a report on the details of the defect, the extent of its impact, the cause, the date and time of its resolution, and measures to prevent recurrence;

[1629] an output means for saving the automatically generated report content in a predetermined format and providing the information;

[1630] A system including:

[1631] (Claim 2)

[1632] 2. The system according to claim 1, wherein the analysis means generates a report template including details of the report content, the extent of the impact of the defect, the cause, the date and time of resolution, and measures to prevent recurrence, and performs a final check.

[1633] (Claim 3)

[1634] 2. The system according to claim 1, wherein the output means includes a process for formatting the automatically generated report into a predetermined format and transmitting it to a recipient.

[1635] "Application Example 1"

[1636] (Claim 1)

[1637] An information processing means that has learned the service content and business procedures in advance,

[1638] A data collection method for collecting text data from communications made via communication tools after an accident occurs;

[1639] An analysis means for analyzing the collected text data using a generation AI model and automatically generating a report on the details of the defect, the extent of its impact, the cause, the date and time of resolution, and measures to prevent recurrence;

[1640] An output means for converting the automatically generated report into a PDF in a predetermined format and outputting it;

[1641] A system including:

[1642] (Claim 2)

[1643] The system of claim 1, wherein the analysis means generates a report template including details of the report content, the scope of the impact of the defect, the cause, the date and time of resolution, and measures to prevent recurrence, and performs a final check using the generated AI model.

[1644] (Claim 3)

[1645] 2. The system according to claim 1, wherein the output means includes a process of arranging the automatically generated report in a predetermined format, saving it as a PDF, and sending it to the user.

[1646] "Example 2: Combining Emotion Engines"

[1647] (Claim 1)

[1648] An information processing means that has learned the service content and business procedures in advance,

[1649] A data collection means for collecting communication exchanges after an accident as text data;

[1650] An analysis means for analyzing the collected text data and automatically generating a report on the details of the defect, the extent of its impact, the cause, the date and time of its resolution, and measures to prevent recurrence;

[1651] an output means for outputting the automatically generated report content;

[1652] an emotion analysis means for analyzing the user's emotional state and adjusting the tone and expression of the report content;

[1653] A system including:

[1654] (Claim 2)

[1655] 2. The system according to claim 1, wherein the analysis means generates a report template including details of the report content, the extent of the impact of the defect, the cause, the date and time of resolution, and measures to prevent recurrence, and performs a final check.

[1656] (Claim 3)

[1657] 2. The system according to claim 1, wherein the output means includes a process for converting the automatically generated report into a predetermined format and transmitting the report to the user.

[1658] "Application example 2 when combining emotion engines"

[1659] (Claim 1)

[1660] An information processing means that has learned the service content and business procedures in advance,

[1661] A data collection method for collecting text data from communications made via communication tools after an accident occurs;

[1662] An analysis means for analyzing the collected text data and automatically generating a report on the details of the defect, the extent of its impact, the cause, the date and time of its resolution, and measures to prevent recurrence;

[1663] A sentiment analysis tool to adjust the tone and expression of the automatically generated report; and

[1664] an output means for outputting the automatically generated report content;

[1665] A system including:

[1666] (Claim 2)

[1667] 2. The system according to claim 1, wherein the analysis means generates a report template including details of the report content, the extent of the impact of the defect, the cause, the date and time of resolution, and measures to prevent recurrence, and performs a final check.

[1668] (Claim 3)

[1669] 2. The system according to claim 1, wherein the output means includes a process for converting the automatically generated report into a predetermined format and transmitting the report to the user. [Explanation of symbols]

[1670] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. An information processing means that has learned the service content and business procedures in advance, A data collection method for collecting text data from communications made via communication tools after an accident occurs; An analysis means for analyzing the collected text data and automatically generating a report on the details of the defect, the extent of its impact, the cause, the date and time of its resolution, and measures to prevent recurrence; an output means for outputting the automatically generated report content; A system including:

2. 2. The system according to claim 1, wherein the analysis means generates a report template including details of the report content, the extent of the impact of the defect, the cause, the date and time of resolution, and measures to prevent recurrence, and includes a process for performing a final check.

3. 2. The system according to claim 1, wherein the output means includes a process for converting the automatically generated report into a predetermined format and transmitting the report to the user.

Images