system

Abstract

We provide the system. [Solution] A means for users to report problems through their devices, A means for receiving a problem report and determining whether or not it is a known issue, If it is a known issue, a means of responding with a solution, In the case of an unknown phenomenon, the analysis is entrusted to a generative artificial intelligence, and a means of generating new knowledge is provided. A means of adding the generated knowledge to the knowledge base, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The corresponding part of の is described below.

[0005] Conventionally, in server maintenance, quick responses can be made for known events. However, when an unknown event occurs, it is necessary to rely on an external maintenance vendor, which has the problem of taking time and cost for response. Due to this problem, there has been a problem that the system downtime increases and the business efficiency decreases. In addition, since there is a lack of a mechanism to learn new knowledge from past maintenance responses and automatically feedback it to the system, the same response has to be made again when the same problem recurs. The object of this invention is to solve these problems.

Means for Solving the Problems

[0006] The system according to the present invention includes the following means: means for a user to report a problem via a terminal; means for receiving the problem report and determining whether it is a known event; means for responding with a method of action if it is a known event; means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown event; and means for adding the generated knowledge to a knowledge base. It further includes means for the generative artificial intelligence to analyze the problem and generate a solution, and means for responding to the user with the generated solution. Furthermore, it includes means for automatically adding and updating the solution generated by the generative artificial intelligence to the knowledge base, and means for handling future problems based on the updated knowledge base. These means improve the speed of response to unknown events, improve operational efficiency, and promote the accumulation and reuse of knowledge.

[0007] A "user" is a person or organization that uses the system to report a problem.

[0008] A "terminal" is a device used by users to access the system and report problems, and includes personal computers and smartphones.

[0009] "Problem reporting" refers to the act of a user entering and submitting details of a problem that has occurred to the system.

[0010] A "server" refers to a computer system that receives and processes problem reports from users.

[0011] "Known issues" refer to problems that the system has experienced in the past for which countermeasures have already been identified.

[0012] An "unknown event" refers to a problem that the system has never experienced before, or for which the solution is unknown.

[0013] "Generative artificial intelligence" refers to an AI system that uses machine learning techniques to analyze unknown phenomena and automatically generate new knowledge and countermeasures.

[0014] "Knowledge" refers to the solutions and related information that a system possesses to address a problem.

[0015] A "knowledge base" refers to a database that stores and saves known events and new knowledge generated by generative artificial intelligence.

[0016] "Accumulation" refers to the act of adding and saving new knowledge or known events to a knowledge base.

[0017] "Feedback" refers to the act of incorporating new knowledge into existing data and system functions, and using that knowledge to solve problems in the future.

[0018] The above are definitions of important terms included in the patent claims. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0021] First, the terms used in the following description will be described.

[0022] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] This invention is a system for improving efficiency in server maintenance, enabling rapid response to unknown events and knowledge accumulation. Specific embodiments of this system are described below.

[0041] Basic configuration

[0042] This system includes a server that receives reports from users via their terminals, and a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge.

[0043] User reports

[0044] Users report problems to the system using their devices. Specifically, users report problems by entering details of the problem (e.g., error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then pressing the submit button.

[0045] Reception and determination by the server

[0046] The server receives a problem report sent from a terminal and first determines whether it is a known issue. If it is a known issue, the server searches its existing knowledge base for a solution and responds to the user with a suggested solution.

[0047] Handling known events

[0048] If the issue is known, the server will provide a solution based on its knowledge base. For example, if "Error Code 500" is reported, the server will respond to the user with a solution such as "Restart the server."

[0049] Handling unknown events

[0050] If the issue is unknown, the server delegates the problem analysis to a generative artificial intelligence (AI). The AI ​​analyzes the received problem report and generates new knowledge and solutions. The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[0051] Updating and reusing the knowledge base

[0052] New knowledge generated by generative artificial intelligence is stored in a knowledge base. The knowledge base is updated, enabling quick solutions to be provided if similar problems occur again. This allows for rapid response when the same problem recurs, reducing the time and cost of system maintenance.

[0053] Specific example

[0054] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives this problem. The server determines whether this problem already exists in the knowledge base. If it is not a known issue, it delegates the analysis to a generative artificial intelligence system, which generates a new solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user through the server and added to the knowledge base.

[0055] This invention automates the process from problem reporting to solution provision, and the knowledge base is continuously strengthened, thereby improving the overall maintainability of the system. This system enables not only rapid problem resolution but also knowledge accumulation and reuse, resulting in long-term operational efficiency.

[0056] The above describes embodiments for carrying out the present invention.

[0057] The following describes the processing flow.

[0058] Step 1:

[0059] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This sends the problem report to the server.

[0060] Step 2:

[0061] The server receives a problem report. The received problem report is stored in an internal database, and then processing begins to determine whether or not it is a known issue.

[0062] Step 3:

[0063] The server compares the problem report against the known issues list. The known issues list contains information about past problems and their solutions. If the problem report is found in the known issues list, the server searches for the corresponding solution.

[0064] Step 4:

[0065] If the server determines that the issue is a known problem, it will respond to the user with a suggested solution. For example, if "Error Code 500" is reported, the server will respond to the user with the solution "Restart the server." The solution will be displayed on the terminal screen.

[0066] Step 5:

[0067] If the server determines that the reported problem does not exist in the list of known events, it delegates the analysis of the problem to the generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[0068] Step 6:

[0069] The generative artificial intelligence receives a problem report and begins analysis. The generative AI uses machine learning algorithms to analyze the problem and generate new knowledge and solutions. For example, it might generate a solution such as "check the configuration file and configure it appropriately."

[0070] Step 7:

[0071] The generative artificial intelligence generates knowledge and sends it back to the server. The server receives the generated knowledge and responds to the user. The user can then view the solution on their device screen.

[0072] Step 8:

[0073] The server adds the generated knowledge to the knowledge base. The knowledge base is managed as a database, and the addition of new knowledge allows for faster problem resolution in the future.

[0074] The above is the specific processing flow of the program.

[0075] (Example 1)

[0076] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0077] In conventional systems, it was difficult to respond quickly and appropriately to user-reported problems, often resulting in long resolution times. Furthermore, when similar problems recurred, past solutions were not efficiently reused, leading to decreased maintenance efficiency. Additionally, when analysis and solution generation for unknown events were performed manually, knowledge base updates were delayed, reducing the overall operational efficiency of the system.

[0078] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0079] In this invention, the server includes means for a user to report a problem via a terminal, means for receiving the problem report and determining whether it is a known event, means for responding with a method of action if it is a known event, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown event, means for generating new knowledge and solutions from the received problem report using the generative artificial intelligence and responding to the user, and means for adding the generated knowledge to the knowledge base. This enables a quick and appropriate response to problems reported by users, promotes continuous updating and reuse of the knowledge base, and improves the efficiency of maintenance work for the entire system.

[0080] A "user" is the operator of a terminal that uses the system to report a problem.

[0081] A "terminal" refers to a device, such as a PC or smartphone, used to report problems to the system.

[0082] A "server" is a central management device that receives problem reports, determines whether or not they are known events, and delegates the analysis to a generative artificial intelligence.

[0083] A "problem" refers to a system malfunction reported by a user, such as a system error message, abnormal behavior, or failure.

[0084] A "report" is detailed information about a problem that a user sends to the system via their device.

[0085] "Known events" are problems that have occurred in the past and are registered in the knowledge base.

[0086] An "unknown phenomenon" refers to a new problem that does not exist in the knowledge base.

[0087] "Judgment" is the process of checking whether a received problem report is a known issue or not.

[0088] A "response" is the act of a server notifying a user of how to respond or a solution.

[0089] "Generative artificial intelligence" refers to an AI model that analyzes received problem reports to generate new knowledge and solutions.

[0090] "Analysis" is the process of thoroughly examining the contents of a problem report to find the cause and solution.

[0091] "Knowledge" refers to the knowledge and data generated by generative artificial intelligence for problem-solving.

[0092] A "knowledge base" is a database system that stores existing and newly generated knowledge.

[0093] A "prompt statement" is an input statement used when requesting a generative artificial intelligence to analyze a problem.

[0094] This invention provides a system that improves the efficiency of server maintenance and enables rapid response to unknown events and the accumulation of knowledge. The system includes a server that receives reports from users via a terminal, and a generative AI model that analyzes unknown events and generates new knowledge.

[0095] Basic configuration

[0096] This system includes a dedicated application or web interface for users to report problems via their terminals, a server that receives these reports and determines whether they are known issues, and a generative AI model. The hardware used includes PCs and smartphones as terminals, and the server utilizes virtual machines or physical servers in the cloud. The software includes web servers such as Apache® and Nginx, database management systems such as MySQL® and PostgreSQL, and generative AI models such as OpenAI® GPT-3®.

[0097] User reports

[0098] Users report problems to the system using their devices. Specifically, users report problems by entering details of the problem (e.g., error message, system behavior, date and time of occurrence, etc.) through a dedicated application on their device or a web interface, and then pressing the submit button. For example, a user might report that "the application crashes when I try to save a file."

[0099] Reception and determination by the server

[0100] The server receives problem reports sent from terminals. The server first determines whether the problem is a known issue by cross-referencing it with the knowledge base. The knowledge base stores past problems and their solutions.

[0101] Handling known events

[0102] If the issue is known, the server searches its knowledge base for a solution and responds to the user. For example, if "Error Code 500" is reported, the server will respond with a solution such as "Restart the server." The database management system used in this case is MySQL or PostgreSQL.

[0103] Handling unknown events

[0104] If an unknown phenomenon occurs, the server delegates the problem analysis to a generative AI model. This generative AI model, built using OpenAI GPT-3 and other technologies, analyzes the received problem report and generates new knowledge and solutions. The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[0105] Updating and reusing the knowledge base

[0106] New knowledge generated by the generative AI model is stored in a knowledge base. The knowledge base is updated, enabling rapid response to similar problems in the future. This reduces the time and cost associated with system maintenance.

[0107] Specific example

[0108] For example, if a user reports a problem where "the application crashes when trying to save a file," the server receives the issue and determines if it already exists in the knowledge base. If it's not a known issue, it delegates the analysis to a generative AI model, which generates a new solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user via the server and added to the knowledge base.

[0109] Example of a prompt

[0110] Examples of specific prompt messages:

[0111] "User-reported issue: The application crashes when attempting to save a file. Error message: 'Error 404: File not found', Date and time of occurrence: October 1, 2023, System behavior: The application immediately terminates. Please provide a solution."

[0112] This invention automates the process from problem reporting to solution provision, and the knowledge base is continuously strengthened, thereby improving the overall maintainability of the system. This system enables not only rapid problem resolution but also knowledge accumulation and reuse, resulting in long-term operational efficiency.

[0113] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0114] Step 1:

[0115] The user accesses the system from their terminal using a dedicated application or web interface. The input at this stage consists of details of the problem the user is reporting (e.g., error message, system behavior, date and time of occurrence). The output is the transmission of the entered problem details to the server. Specifically, the user fills out a form and clicks a submit button.

[0116] Step 2:

[0117] The server receives problem reports sent from terminals. Specifically, it receives problem reports as HTTP requests via a web server (e.g., Apache, Nginx) and stores their contents in a database. The input is the details of the problem report received from the user, and the output is the problem report information stored in the database.

[0118] Step 3:

[0119] The server determines whether the received problem report is a known issue or not. Specifically, this involves searching the knowledge base in the database (e.g., MySQL, PostgreSQL) to see if it matches any past issues. The input is the problem report information stored in the database, and the output is the determination result of whether the problem is known or unknown. Based on this determination result, the next action is decided.

[0120] Step 4:

[0121] If the server determines that the problem is a known issue, it searches its knowledge base for a solution and responds to the user. The input is the solution information retrieved from the knowledge base, and the output is the solution returned to the user. Specifically, the server executes an SQL query to search for a solution and sends it to the user as an HTTP response.

[0122] Step 5:

[0123] If the server determines that a problem is an unknown phenomenon, it delegates the analysis of the problem to a generative AI model (e.g., OpenAI GPT-3). The input is detailed information about the unknown problem report, and the output is the solution and knowledge generated by the generative AI model. Specifically, the server sends prompt messages to the generative AI model and obtains the analysis results.

[0124] Step 6:

[0125] The generative AI model analyzes the received problem report and generates new knowledge and solutions. The input is the detailed information of the problem report as a prompt, and the output is the analyzed knowledge and solutions. Specifically, the generative AI model analyzes the prompt, performs inference, and generates a new solution.

[0126] Step 7:

[0127] The server returns the generated solution to the user. The input is the solution obtained from the generating AI model, and the output is the response message to the user. Specifically, the server sends the solution to the user as an HTTP response.

[0128] Step 8:

[0129] The server automatically adds the knowledge generated by the AI ​​model to the knowledge base. The input is the newly generated knowledge, and the output is the updated knowledge base. Specifically, the server executes an SQL query to add the new knowledge to the database.

[0130] The above explains the system's program flow, broken down into specific processing steps.

[0131] (Application Example 1)

[0132] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0133] In logistics centers, it is crucial to resolve equipment and system errors quickly and effectively. However, existing systems often resulted in delays in responding to errors, frequently halting operations. Furthermore, the inability to quickly find appropriate countermeasures for unknown errors prolonged response times. This led to decreased operational efficiency at logistics centers, increased costs, and delays in delivery.

[0134] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0135] In this invention, the server includes means for users to report problems via a terminal, means for receiving problem reports and determining whether they are known events, means for responding with a method of action if they are known events, means for delegating analysis to a generative artificial intelligence and generating new knowledge if they are unknown events, means for adding the generated knowledge to a knowledge base, and means for workers to report problems using smart devices when equipment or system errors occur in a logistics center. This makes it possible to provide rapid countermeasures when errors occur, generate new knowledge for unknown errors to expedite responses, and improve the operational efficiency of the logistics center.

[0136] "Users" refers to individuals or workers who report problems when equipment or system errors occur at a logistics center.

[0137] "Terminal" refers to a smart device or computer used by a user to report a problem.

[0138] "Problem reporting" refers to the act of a user sending details of an error or malfunction via their device, as well as the content of that report.

[0139] "Known events" refer to problems or errors that already exist in the knowledge base and for which countermeasures have been established in the past.

[0140] An "unknown phenomenon" refers to a problem or error that does not exist in the knowledge base and requires new analysis and countermeasures.

[0141] "Generative artificial intelligence" refers to an artificial intelligence system that analyzes unknown phenomena and generates new knowledge and solutions.

[0142] A "knowledge base" refers to a database that stores known events and their corresponding countermeasures.

[0143] "Smart devices" refer to electronic devices such as smartphones and tablets that workers use to report problems.

[0144] "Analysis" refers to the process by which a generative artificial intelligence receives a problem report, examines the cause and solution of the event, and generates new knowledge.

[0145] A "logistics center" refers to a facility that manages and distributes goods and supplies.

[0146] This invention provides a system for quickly and effectively resolving errors in equipment and systems at a logistics center. The system includes user terminals, a server, generative artificial intelligence, and a knowledge base.

[0147] Basic configuration

[0148] User problem reports

[0149] Users report errors and problems using their devices. These reports are made using smart devices such as smartphones and tablets, and details of the error (text) and corresponding images are sent through a dedicated application.

[0150] Reception and determination by the server

[0151] The server receives problem reports submitted by users. First, it determines whether the received problem is a known issue. If it is a known issue, it searches the knowledge base for a solution and responds to the user. For example, if a stoppage of an electric conveyor is reported, the knowledge base will contain information recommending "restarting."

[0152] Responding to Unknown Events

[0153] If an unknown phenomenon occurs, the server delegates the analysis to a generative artificial intelligence (such as the GPT-4® model). The generative AI analyzes the received problem report and generates new knowledge and solutions. This generated knowledge is provided to users through the server and is also automatically added to the knowledge base.

[0154] Updating and reusing the knowledge base

[0155] New knowledge generated by generative artificial intelligence is stored in a knowledge base. This knowledge base is continuously updated, enabling rapid responses to future problems.

[0156] Specific example

[0157] For example, suppose a worker at a logistics center discovers a conveyor belt has stopped and reports the problem using a smart device, stating, "The conveyor belt has stopped. Error code 12345." This problem report is received by a server, which first determines whether it is a known issue. If it is an unknown issue, a generative artificial intelligence generates a new solution, such as "Readjust the belt." This solution is then sent back to the worker via the server and simultaneously added to the knowledge base.

[0158] Hardware and software to be used

[0159] Hardware: Smart devices (smartphones, tablets), servers

[0160] Software: Dedicated problem reporting application, generative artificial intelligence (GPT-4, etc.), knowledge base management system

[0161] Data processing and data calculation

[0162] 1. Data entry: Users enter details of the problem and images, and send them to the server.

[0163] 2. Data reception and determination: The server receives the problem report and determines whether it is known or unknown.

[0164] 3. Use of Generative Artificial Intelligence: In the case of unknown events, generative artificial intelligence analyzes the problem and generates new knowledge.

[0165] 4. Knowledge Base Update: Generated knowledge is automatically added to the knowledge base.

[0166] Example of a prompt

[0167] A possible prompt message when a worker reports a conveyor belt stoppage might be: "The conveyor belt has stopped. Error code 12345. Please tell me the cause and solution." This prompt is sent to a generative artificial intelligence system to serve as a reference for generating new knowledge.

[0168] The above describes specific embodiments for carrying out the present invention. This invention is expected to enable rapid problem solving in logistics centers and improve operational efficiency.

[0169] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0170] Step 1:

[0171] Users report problems using smart devices.

[0172] Input: Error details (text) and image

[0173] Output: Problem report data sent from the terminal

[0174] Specific operation: The user launches a dedicated application, enters details of the problem such as "The conveyor belt has stopped. Error code 12345," and adds images as needed. Then, by pressing the submit button, this data is sent to the server.

[0175] Step 2:

[0176] The server receives a problem report.

[0177] Input: Problem report data sent by the user from their device.

[0178] Output: Received problem report data is stored on the server.

[0179] Specific operation: The server stores the received data in a parseable format. For example, text data is stored as a string in the database, and image data is stored in the file system.

[0180] Step 3:

[0181] The server determines whether the problem report it receives is a known issue.

[0182] Input: Received problem report data

[0183] Output: Determination result of whether it is a known or unknown event.

[0184] Specific operation: The server compares the content of the problem report with the knowledge base and checks if it contains known error codes or keywords. If there is a match, it is determined to be a known issue.

[0185] Step 4:

[0186] If the issue is known, the server will search its knowledge base for a solution and respond to the user.

[0187] Input: Problem report data identified as a known issue

[0188] Output: Reply message including the suggested course of action

[0189] Specific actions: Search the knowledge base for relevant solutions (e.g., "Restart the conveyor belt") and send that information to the user as a text message.

[0190] Step 5:

[0191] If the phenomenon is unknown, the server delegates the analysis to a generative artificial intelligence.

[0192] Input: Problem report data identified as an unknown event

[0193] Output: Data sent to the generative artificial intelligence for problem analysis.

[0194] Specific operation: The server sends the details of the problem report to the generative artificial intelligence. It generates a prompt message (e.g., "The conveyor belt has stopped. Error code 12345. Please tell me the cause and solution.") and sends it to the generative artificial intelligence model.

[0195] Step 6:

[0196] Generative artificial intelligence generates new knowledge and solutions.

[0197] Input: Prompt sent to a generative AI

[0198] Output: Generated knowledge and solutions

[0199] Specific operation: The generative artificial intelligence analyzes the prompt text and generates a cause analysis and solution (e.g., "Readjust the belt") in text format.

[0200] Step 7:

[0201] The server returns the generated knowledge to the user and adds it to the knowledge base.

[0202] Input: Knowledge and solutions generated by generative artificial intelligence.

[0203] Output: Solution messages sent to users and updated knowledge base

[0204] Specific operation: The server returns the generated knowledge to the user and saves it as new knowledge in the knowledge base. The user receives a message that includes specific instructions on how to proceed (e.g., "Readjust the belt").

[0205] Step 8:

[0206] We will address future issues based on the updated knowledge base.

[0207] Input: Updated Knowledge Base

[0208] Output: Prompt response to future problem reports

[0209] Specific action: By updating the knowledge base, the server can quickly provide solutions if similar problems recur. For example, the next time the same error code is reported, the solution "re-adjust the belt" will be immediately suggested.

[0210] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0211] This invention is a system for improving efficiency in server maintenance, enabling rapid response to unknown events and knowledge accumulation. Furthermore, by combining it with an emotion engine that recognizes user emotions, it provides more appropriate responses.

[0212] Basic configuration

[0213] This system includes a server that receives reports from users via their terminals, a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge, and an emotion engine that recognizes the user's emotions.

[0214] User reports

[0215] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This sends the problem report to the server.

[0216] Reception and determination by the server

[0217] The server receives a problem report sent from a terminal and first determines whether it is a known issue or not. If it is a known issue, the server searches its existing knowledge base for a solution and responds to the user with a suggested solution.

[0218] Handling known events

[0219] If the issue is known, the server will provide a solution based on its knowledge base. For example, if "Error Code 500" is reported, the server will respond to the user with the solution "Restart the server." The solution will be displayed on the terminal screen.

[0220] Handling unknown events

[0221] If the phenomenon is unknown, the server delegates the analysis of the problem to a generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[0222] Generative artificial intelligence analyzes received problem reports and generates new knowledge and solutions. For example, it might generate solutions such as "Check the configuration file and configure it appropriately." The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[0223] User emotion recognition

[0224] When the server receives a problem report, it uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's text input and voice data to determine whether the user is feeling anxiety, anger, stress, etc.

[0225] Responding according to emotions

[0226] After the emotion engine recognizes the user's emotions, the server selects an appropriate response. For example, if the user is experiencing high levels of stress, the server will respond quickly, providing detailed instructions on the steps necessary to resolve the problem. It may also respond with a gentle, encouraging message.

[0227] Updating and reusing the knowledge base

[0228] New knowledge generated by generative artificial intelligence is stored in the knowledge base. Furthermore, user emotion data recognized by the emotion engine is also stored in the knowledge base, making it possible to provide countermeasures that take past emotion data into account when reporting future problems.

[0229] This allows the system to respond quickly and appropriately the next time a similar problem occurs. Furthermore, if the same problem recurs, a rapid response based on the knowledge base is possible, reducing the time and cost of system maintenance. The emotion recognition function improves the user experience and increases user satisfaction.

[0230] Specific example

[0231] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives this problem. The server determines if this problem already exists in the knowledge base. If it is not a known issue, it delegates the analysis to a generative artificial intelligence system, which generates a solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user through the server and added to the knowledge base. Furthermore, an emotion engine recognizes the user's emotions and generates a message to alleviate the user's stress.

[0232] This invention automates the process from problem reporting to solution provision, continuously strengthening the knowledge base and improving the overall maintainability of the system. Incorporating emotion recognition enhances the user experience, enabling the delivery of more satisfying services. This system not only facilitates rapid problem resolution but also enables knowledge accumulation and reuse, resulting in long-term operational efficiency.

[0233] The above describes embodiments for carrying out the present invention.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time of occurrence, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This action sends the problem report to the server.

[0237] Step 2:

[0238] The server receives a problem report. The received problem report is stored in the internal database.

[0239] Step 3:

[0240] The server uses an emotion engine to analyze the user's emotions from the problem report. The emotion engine uses text analysis and speech analysis to determine the user's emotional state (e.g., anxiety, anger, stress).

[0241] Step 4:

[0242] The server compares the problem report against a list of known events to determine whether or not it is a known event. This determination is made by comparing the data in the knowledge base with the content of the problem report.

[0243] Step 5:

[0244] If the server determines that the reported problem is a known issue, it searches its knowledge base for a solution and provides it to the user. For example, if "Error Code 500" is reported, a solution such as "Restart the server" will be displayed on the terminal.

[0245] Step 6:

[0246] If the server determines that the reported problem is an unknown phenomenon, it delegates the analysis of the problem to a generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[0247] Step 7:

[0248] Generative artificial intelligence receives a problem report and begins analysis. The AI ​​uses its machine learning models and datasets to analyze the problem and generate new knowledge and solutions. For example, it might generate specific solutions such as "check the configuration file and configure it appropriately."

[0249] Step 8:

[0250] The generative artificial intelligence generates knowledge, which is then sent back to the server. The server then provides that knowledge to the user. The user can then view the newly generated solution on their device screen.

[0251] Step 9:

[0252] The server adds the generated knowledge to the knowledge base. The knowledge base is managed as a database and used for addressing future issues. In addition, user sentiment data analyzed by the sentiment engine is also stored in the knowledge base.

[0253] Step 10:

[0254] In the event of a similar problem occurring in the future, the server will provide prompt solutions based on its knowledge base. It can also provide solutions that take past emotional data into account; for example, if a user is experiencing high levels of stress, it will prioritize encouraging messages and prompt responses.

[0255] The above describes the specific processing flow of the system based on the present invention.

[0256] (Example 2)

[0257] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0258] In recent years, with the increasing complexity of information systems, the number of users reporting problems has been rising. While known issues can be addressed quickly, responding appropriately to unknown issues is difficult. Furthermore, users' emotional states influence the speed of problem resolution and their satisfaction, but conventional systems cannot analyze emotions or respond flexibly based on them. Therefore, there is a need for a system that can quickly address unknown problems while simultaneously providing appropriate responses that respond to users' emotions.

[0259] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to report a problem through an information processing device, means for receiving the problem report and determining whether it is a known phenomenon, means for responding with a method of dealing with the known phenomenon if it is a known phenomenon, means for delegating analysis to generative artificial intelligence and generating new knowledge if it is an unknown phenomenon, means for adding the generated knowledge to a knowledge database, means for recognizing the user's emotions using an emotion analysis engine, and means for adjusting the method of dealing with the problem based on the recognized emotions. This enables a quick and appropriate response to unknown problems, and also enables a flexible response that responds to the user's emotions.

[0260] 1. An "information processing device" is a device such as a computer or smartphone that users use to input, process, and output data.

[0261] 2. "Problem reporting" refers to the act of a user sending information to the system to inform it of the details of a malfunction or problem that has occurred.

[0262] 3. A "known phenomenon" is a problem that has already been recorded in the knowledge base and for which countermeasures have been clearly determined.

[0263] 4. An "unknown phenomenon" is a problem that has not been recorded in the past and for which countermeasures have not been established.

[0264] 5. "Generative artificial intelligence" is artificial intelligence that has the ability to analyze input data and generate new knowledge and solutions.

[0265] 6. "New knowledge" refers to solutions and information for unknown phenomena that are analyzed and generated by generative artificial intelligence.

[0266] 7. A "knowledge database" is a database used to accumulate and manage solutions to known phenomena and new knowledge.

[0267] 8. An "emotion analysis engine" is a system that analyzes user input data and identifies the user's emotional state.

[0268] 9. "Solution" refers to the solutions or procedures that the system provides in response to a problem report.

[0269] 10. "Adjusting coping strategies based on recognized emotions" means changing the content and manner of coping strategies according to the user's emotional state as recognized by the emotion analysis engine.

[0270] This invention relates to a problem reporting system using an information processing device, which responds quickly and appropriately to problem reports from users. Furthermore, by combining it with an emotion analysis engine, it achieves flexible responses that respond to the user's emotions. The following describes in detail specific embodiments for carrying out this invention.

[0271] Basic configuration

[0272] This system includes a server that receives user reports via an information processing device, a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge, and an emotion analysis engine that recognizes user emotions. The detailed functions of each element are described below.

[0273] User reports

[0274] Users report problems using information processing devices (e.g., personal computers, smartphones) via a dedicated application or web interface. Users enter detailed information such as error messages, the date and time the problem occurred, and system behavior, and then press the submit button to report the problem.

[0275] Reception and determination by the server

[0276] The server receives problem reports submitted by users. The server consults its knowledge database to determine whether the reported problem is a known issue. If it is a known issue, the server searches the knowledge database for a solution and responds to the user with the appropriate action. For example, if "error code 500" is reported, the server will respond to the user with the solution "restart the system."

[0277] Processing known phenomena

[0278] In the case of known phenomena, the server provides solutions to problems based on the knowledge database. The solutions are displayed on the screen of the user's information processing device. For example, when "error code 500" is reported, the server presents "restart the server" as a solution.

[0279] Processing of unknown phenomena

[0280] In the case of unknown phenomena, the server entrusts the analysis of the problem to a generative artificial intelligence (e.g., GPT-4). The server sends the content of the problem report to the generative artificial intelligence. The generative artificial intelligence analyzes the received problem report and generates new knowledge and solutions. For example, it generates solutions such as "check the configuration file and make appropriate settings". The generated knowledge is replied to the user through the server and added to the knowledge database.

[0281] Recognition of the user's emotion by the emotion analysis engine

[0282] When receiving a problem report, the server analyzes the user's emotion using an emotion analysis engine (e.g., IBM Watson (registered trademark)). The emotion analysis engine analyzes the user's input data and determines whether the user is feeling anxious, angry, stressed, etc.

[0283] Response according to emotion

[0284] After the emotion analysis engine recognizes the user's emotion, the server adjusts the response method based on the recognized emotion. For example, when the user is feeling strong stress, the server responds quickly and explains in detail the procedures necessary to solve the problem. Also, it returns an encouraging message to soothe the user's mood.

[0285] Update and reuse of the knowledge database

[0286] The new knowledge generated by generative artificial intelligence is accumulated in the knowledge database. Furthermore, the user's emotion data recognized by the emotion analysis engine is also stored in the knowledge database. This enables quick and appropriate responses when similar problems occur in the future. Also, it is possible to provide countermeasures considering past emotion data when reporting problems in the future. As a result, the system not only enables quick problem-solving but also allows for the accumulation and reuse of knowledge, realizing the long-term operational efficiency improvement.

[0287] Specific example

[0288] For example, when a user reports a problem such as "The application crashes when trying to save a file", the server receives this problem and determines whether it already exists in the knowledge database. If it is not a known phenomenon, it entrusts the analysis to the generative artificial intelligence to generate a solution such as "Check the configuration file and make appropriate settings". This generated solution is returned to the user through the server and added to the knowledge database. Furthermore, the emotion analysis engine recognizes the user's emotion and generates a message to relieve the user's stress.

[0289] Example of prompt sentence

[0290] "Please generate an appropriate solution for the problem of 'The application crashes when trying to save a file'. Since the user is feeling strong stress, please also add a reassuring message."

[0291] According to the present invention, the process from problem reporting to solution provision is automated, and the knowledge database is continuously strengthened, improving the maintainability of the entire system. By incorporating the emotion recognition function, the user experience is improved, enabling the provision of a more satisfactory service. This system not only enables quick problem-solving but also allows for the accumulation and reuse of knowledge, realizing the long-term operational efficiency improvement.

[0292] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0293] Step 1: User reports a problem.

[0294] Input: The user uses an information processing device (e.g., personal computer, smartphone) to access a dedicated application or web interface and enter details of the problem (e.g., error message, date and time of occurrence, system behavior, etc.).

[0295] Specific operation: The user enters the necessary information into the problem report form and presses the "Submit" button to report the problem.

[0296] Output: The problem report is sent to the server.

[0297] Step 2: Server receives report and determines known / unknown information.

[0298] Input: The server receives problem reports submitted by users.

[0299] Specific operation: The server analyzes the received problem report and accesses the knowledge database to determine whether or not it is a known phenomenon.

[0300] Output: If the issue is known, retrieve a solution from the knowledge database; if it is an unknown issue, proceed to the next step.

[0301] Step 3: Server response to known issues

[0302] Input: The server retrieves solutions for known issues from the knowledge database.

[0303] Specific operation: The server sends the solution to the user's information processing device and displays it on the screen.

[0304] Output: The user is provided with specific countermeasures (e.g., "Restart the system" for error code 500).

[0305] Step 4: Commissioning the Server to Analyze Unknown Phenomena

[0306] Input: The server determines that it is not a known phenomenon and commissions the generation AI model (e.g., GPT-4) for analysis.

[0307] Specific Operation: The server sends the details of the problem report to the generation AI model.

[0308] Output: The details of the problem report are sent to the generation AI model.

[0309] Step 5: Generation of New Knowledge by the Generation AI Model

[0310] Input: The generation AI model receives the problem report sent by the server.

[0311] Specific Operation: The generation AI model analyzes the problem content and generates new knowledge or solutions (e.g., "Check the configuration file and make appropriate settings").

[0312] Output: The generated solution is sent back to the server.

[0313] Step 6: Response with New Knowledge and Stress Management

[0314] Input: The server receives the solution sent back by the generation AI model.

[0315] Specific Operation: The server replies to the user with the solution and simultaneously analyzes the user's sentiment using a sentiment analysis engine (e.g., IBM Watson). If stress is recognized, it generates a detailed procedure description and an encouraging message.

[0316] Output: Specific solutions and sentiment-based messages are provided to the user. <00​​​​

[0318] Input: The server receives new knowledge generated by the generation AI model and data from the emotion analysis engine.

[0319] Specific operation: The server adds new knowledge to the knowledge database and stores sentiment data along with it.

[0320] Output: The knowledge database will be updated, and problem handling and emotional support will be enhanced for future issues.

[0321] The above describes the processing steps of the program for this system.

[0322] (Application Example 2)

[0323] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0324] Existing problem-solving systems were time-consuming to respond to unfamiliar situations, making it difficult to provide appropriate solutions quickly. Furthermore, they failed to consider user emotions, hindering improvements in the user experience. As a result, there was a lack of means to alleviate user stress and dissatisfaction.

[0325] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0326] In this invention, the server includes means for a user to report a problem via a terminal, means for receiving the problem report and determining whether it is a known event, means for responding with a method of action if it is a known event, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown event, means for adding the generated knowledge to a knowledge base, means for sentiment analysis to recognize the user's emotions, and means for providing countermeasures according to the recognized emotions. This enables rapid response to unknown events and effective accumulation of knowledge, and furthermore, by taking user emotions into consideration, it is possible to improve the user experience and reduce dissatisfaction.

[0327] A "user" refers to a person who uses the system or device to report a problem and receive a solution.

[0328] A "device" refers to a device used by a user to report a problem, and includes smartphones, personal computers, and other similar devices.

[0329] "Problem reporting" refers to the act of a user informing the system of any malfunctions or errors that have occurred, as well as the content of that information.

[0330] A "server" refers to a computer system that receives problem reports, analyzes them, and generates solutions.

[0331] "Known events" refer to events where similar problems have occurred in the past, and for which solutions have already been accumulated in the knowledge base.

[0332] An "unknown event" refers to an event that has never occurred before, or for which no solution exists in the knowledge base.

[0333] "Generative artificial intelligence" refers to artificial intelligence technology used to generate new solutions and knowledge in response to unknown phenomena.

[0334] "Knowledge" refers to information, data, and solutions that are useful for solving problems.

[0335] A "knowledge base" refers to a database where accumulated knowledge is stored and can be searched and referenced.

[0336] "Emotional analysis means" refers to technologies and devices used to analyze and recognize the emotions of users.

[0337] "Countermeasures" refer to the specific means or methods provided to solve a problem.

[0338] The system for implementing this invention consists of the following elements. First, a terminal is required for users to report problems. The terminal includes smartphones and personal computers, and has a dedicated application installed. Using this application, users can input details of the problem and send them to the server.

[0339] Upon receiving this problem report, the server first determines whether the reported issue is a known problem. If it is a known issue, the server searches its knowledge base for a solution and responds to the user.

[0340] If an unknown phenomenon occurs, the server delegates the analysis of the problem to a generative artificial intelligence (AI). The generative AI analyzes the received problem report and generates new knowledge and solutions. This new knowledge is returned to the user through the server and is also automatically added to the knowledge base.

[0341] Furthermore, the server recognizes the user's emotions using emotion analysis tools. These tools utilize an emotion analysis model based on the Hugging Face transformers library. This allows the server to analyze the user's emotions, such as stress and frustration, and provide appropriate responses based on the recognized emotions. For example, if the user is experiencing high levels of stress, the server will respond quickly, providing detailed instructions on the steps necessary to resolve the problem. It will also respond with a gentle, encouraging message.

[0342] Hardware and software to be used

[0343] Hardware:

[0344] Server: Cloud servers such as AWS (registered trademark) and Google Cloud (registered trademark)

[0345] Devices: Smartphones and PCs (iOS, Android®, Windows, Mac, etc.)

[0346] software:

[0347] Flask: A web framework written in Python.

[0348] transformers:Hugging Face is a library for emotion analysis models.

[0349] Specific example

[0350] A user reports a problem, such as "the vehicle's autonomous driving function has stopped working." Using the application on their device, they enter details of the problem (e.g., "fault_code_001") and a message describing their concern (e.g., "The autonomous driving function suddenly stopped working. I'm very worried."). The problem report is sent to the server, which receives the problem.

[0351] The server determines from the problem report whether it is a known issue. If it is a known issue, it searches the knowledge base for an appropriate solution and responds. However, in this case, it is determined to be an unknown issue, so generative artificial intelligence analyzes the problem and generates a new solution (for example, "check the configuration file and make the appropriate settings").

[0352] Furthermore, sentiment analysis tools are used to analyze the user's messages and recognize if the user is experiencing stress or worry. In response, encouraging messages such as, "Don't worry, we'll let you know the solution soon," are also sent back.

[0353] Example of a prompt

[0354] The following are specific examples of prompt statements.

[0355] Problem: fault_code_001

[0356] Message: The autonomous driving function suddenly stopped working. I am very worried.

[0357] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0358] Step 1:

[0359] Users report problems using their devices.

[0360] The user opens a dedicated application on their device, enters details of the problem (error message, date and time of occurrence, circumstances, etc.), and submits a report.

[0361] Input: Problem details (text data)

[0362] Output: Problem report data sent to the server

[0363] Step 2:

[0364] The server receives a problem report.

[0365] The server analyzes the problem report data sent from the terminal and retrieves the details of the problem.

[0366] Input: Problem report data

[0367] Output: Analyzed problem content

[0368] Step 3:

[0369] The server determines whether the problem is known.

[0370] The server accesses the knowledge base to check whether the reported issue is a known issue. If it is a known issue, it retrieves the appropriate solution from the knowledge base.

[0371] Input: Analyzed problem description, knowledge base

[0372] Output: Countermeasures (only for known issues)

[0373] Step 4:

[0374] The server will respond with a solution (if it's a known issue).

[0375] The server returns a solution retrieved from the knowledge base to the user. This solution is displayed on the terminal screen.

[0376] Input: Countermeasures

[0377] Output: Reply to the user

[0378] Step 5:

[0379] The server delegates the problem to a generative artificial intelligence (in the case of an unknown event).

[0380] If the issue is not known, the server delegates the analysis of the problem to a generative artificial intelligence.

[0381] Input: Analyzed problem content

[0382] Output: Problem data for generative artificial intelligence

[0383] Step 6:

[0384] Generative artificial intelligence analyzes the problem and generates new knowledge.

[0385] Generative artificial intelligence analyzes problem reports and generates new solutions.

[0386] Input: Problem data

[0387] Output: New knowledge (solution)

[0388] Step 7:

[0389] The server adds the generated knowledge to the knowledge base.

[0390] The newly generated knowledge is automatically added to the knowledge base.

[0391] Input: New knowledge

[0392] Output: Updated Knowledge Base

[0393] Step 8:

[0394] The server recognizes the user's emotions using emotion analysis tools.

[0395] The server inputs the user's text message into an emotion analysis model and analyzes their emotional state.

[0396] Input: User's text message

[0397] Output: Emotional state data

[0398] Step 9:

[0399] The server provides countermeasures based on the emotions it recognizes.

[0400] Based on the sentiment analysis results, the system sends users appropriate responses or encouraging messages.

[0401] Input: Emotional state data, new solution

[0402] Output: Emotionally sensitive responses and messages

[0403] Step 10:

[0404] The server returns the response result to the user.

[0405] Ultimately, the server responds to the user with the generated solution and a message tailored to their emotions, displaying it on their device.

[0406] Input: Emotionally sensitive responses and solutions

[0407] Output: Information returned to the terminal

[0408] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0409] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0410] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0411] [Second Embodiment]

[0412] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0413] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0414] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0415] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0416] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0417] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0418] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0419] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0420] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0421] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0422] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0423] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0424] This invention is a system for improving efficiency in server maintenance, enabling rapid response to unknown events and knowledge accumulation. Specific embodiments of this system are described below.

[0425] Basic configuration

[0426] This system includes a server that receives reports from users via their terminals, and a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge.

[0427] User reports

[0428] Users report problems to the system using their devices. Specifically, users report problems by entering details of the problem (e.g., error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then pressing the submit button.

[0429] Reception and determination by the server

[0430] The server receives a problem report sent from a terminal and first determines whether it is a known issue. If it is a known issue, the server searches its existing knowledge base for a solution and responds to the user with a suggested solution.

[0431] Handling known events

[0432] If the issue is known, the server will provide a solution based on its knowledge base. For example, if "Error Code 500" is reported, the server will respond to the user with a solution such as "Restart the server."

[0433] Handling unknown events

[0434] If the issue is unknown, the server delegates the problem analysis to a generative artificial intelligence (AI). The AI ​​analyzes the received problem report and generates new knowledge and solutions. The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[0435] Updating and reusing the knowledge base

[0436] New knowledge generated by generative artificial intelligence is stored in a knowledge base. The knowledge base is updated, enabling quick solutions to be provided if similar problems occur again. This allows for rapid response when the same problem recurs, reducing the time and cost of system maintenance.

[0437] Specific example

[0438] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives this problem. The server determines whether this problem already exists in the knowledge base. If it is not a known issue, it delegates the analysis to a generative artificial intelligence system, which generates a new solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user through the server and added to the knowledge base.

[0439] This invention automates the process from problem reporting to solution provision, and the knowledge base is continuously strengthened, thereby improving the overall maintainability of the system. This system enables not only rapid problem resolution but also knowledge accumulation and reuse, resulting in long-term operational efficiency.

[0440] The above describes embodiments for carrying out the present invention.

[0441] The following describes the processing flow.

[0442] Step 1:

[0443] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This sends the problem report to the server.

[0444] Step 2:

[0445] The server receives a problem report. The received problem report is stored in an internal database, and then processing begins to determine whether or not it is a known issue.

[0446] Step 3:

[0447] The server compares the problem report against the known issues list. The known issues list contains information about past problems and their solutions. If the problem report is found in the known issues list, the server searches for the corresponding solution.

[0448] Step 4:

[0449] If the server determines that the issue is known, it will respond to the user with a suggested solution. For example, if "Error Code 500" is reported, the server will respond to the user with the solution "Restart the server." The solution will be displayed on the terminal screen.

[0450] Step 5:

[0451] If the server determines that the reported problem does not exist in the list of known events, it delegates the analysis of the problem to the generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[0452] Step 6:

[0453] The generative artificial intelligence receives a problem report and begins analysis. The generative AI uses machine learning algorithms to analyze the problem and generate new knowledge and solutions. For example, it might generate a solution such as "check the configuration file and configure it appropriately."

[0454] Step 7:

[0455] The generative artificial intelligence generates knowledge and sends it back to the server. The server receives the generated knowledge and responds to the user. The user can then view the solution on their device screen.

[0456] Step 8:

[0457] The server adds the generated knowledge to the knowledge base. The knowledge base is managed as a database, and the addition of new knowledge allows for faster problem resolution in the future.

[0458] The above is the specific processing flow of the program.

[0459] (Example 1)

[0460] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0461] In conventional systems, it was difficult to respond quickly and appropriately to user-reported problems, often resulting in long resolution times. Furthermore, when similar problems recurred, past solutions were not efficiently reused, leading to decreased maintenance efficiency. Additionally, when analysis and solution generation for unknown events were performed manually, knowledge base updates were delayed, reducing the overall operational efficiency of the system.

[0462] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0463] In this invention, the server includes means for a user to report a problem via a terminal, means for receiving the problem report and determining whether it is a known event, means for responding with a method of action if it is a known event, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown event, means for generating new knowledge and solutions from the received problem report using the generative artificial intelligence and responding to the user, and means for adding the generated knowledge to the knowledge base. This enables a quick and appropriate response to problems reported by users, promotes continuous updating and reuse of the knowledge base, and improves the efficiency of maintenance work for the entire system.

[0464] A "user" is the operator of a terminal that uses the system to report a problem.

[0465] A "terminal" refers to a device, such as a PC or smartphone, used to report problems to the system.

[0466] A "server" is a central management device that receives problem reports, determines whether or not they are known events, and delegates the analysis to a generative artificial intelligence.

[0467] A "problem" refers to a system malfunction reported by a user, such as a system error message, abnormal behavior, or failure.

[0468] A "report" is detailed information about a problem that a user sends to the system via their device.

[0469] "Known events" are problems that have occurred in the past and are registered in the knowledge base.

[0470] An "unknown phenomenon" refers to a new problem that does not exist in the knowledge base.

[0471] "Judgment" is the process of checking whether a received problem report is a known issue or not.

[0472] A "response" is the act of a server notifying a user of how to respond or a solution.

[0473] "Generative artificial intelligence" refers to an AI model that analyzes received problem reports to generate new knowledge and solutions.

[0474] "Analysis" is the process of thoroughly examining the contents of a problem report to find the cause and solution.

[0475] "Knowledge" refers to the knowledge and data generated by generative artificial intelligence for problem-solving.

[0476] A "knowledge base" is a database system that stores existing and newly generated knowledge.

[0477] A "prompt statement" is an input statement used when requesting a generative artificial intelligence to analyze a problem.

[0478] This invention provides a system that improves the efficiency of server maintenance and enables rapid response to unknown events and the accumulation of knowledge. The system includes a server that receives reports from users via a terminal, and a generative AI model that analyzes unknown events and generates new knowledge.

[0479] Basic configuration

[0480] This system includes a dedicated application or web interface for users to report problems via their devices, a server that receives these reports and determines whether they are known issues, and a generative AI model. The hardware used includes PCs and smartphones as devices, while the server utilizes virtual machines or physical servers in the cloud. The software includes web servers such as Apache and Nginx, database management systems such as MySQL and PostgreSQL, and generative AI models such as OpenAI GPT-3.

[0481] User reports

[0482] Users report problems to the system using their devices. Specifically, users report problems by entering details of the problem (e.g., error message, system behavior, date and time of occurrence, etc.) through a dedicated application on their device or a web interface, and then pressing the submit button. For example, a user might report that "the application crashes when I try to save a file."

[0483] Reception and determination by the server

[0484] The server receives problem reports sent from terminals. The server first determines whether the problem is a known issue by cross-referencing it with the knowledge base. The knowledge base stores past problems and their solutions.

[0485] Handling known events

[0486] If the issue is known, the server searches its knowledge base for a solution and responds to the user. For example, if "Error Code 500" is reported, the server will respond with a solution such as "Restart the server." The database management system used in this case is MySQL or PostgreSQL.

[0487] Handling unknown events

[0488] If an unknown phenomenon occurs, the server delegates the problem analysis to a generative AI model. This generative AI model, built using OpenAI GPT-3 and other technologies, analyzes the received problem report and generates new knowledge and solutions. The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[0489] Updating and reusing the knowledge base

[0490] New knowledge generated by the generative AI model is stored in a knowledge base. The knowledge base is updated, enabling rapid response to similar problems in the future. This reduces the time and cost associated with system maintenance.

[0491] Specific example

[0492] For example, if a user reports a problem where "the application crashes when trying to save a file," the server receives the issue and determines if it already exists in the knowledge base. If it's not a known issue, it delegates the analysis to a generative AI model, which generates a new solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user via the server and added to the knowledge base.

[0493] Example of a prompt

[0494] Examples of specific prompt messages:

[0495] "User-reported issue: The application crashes when attempting to save a file. Error message: 'Error 404: File not found', Date and time of occurrence: October 1, 2023, System behavior: The application immediately terminates. Please provide a solution."

[0496] This invention automates the process from problem reporting to solution provision, and the knowledge base is continuously strengthened, thereby improving the overall maintainability of the system. This system enables not only rapid problem resolution but also knowledge accumulation and reuse, resulting in long-term operational efficiency.

[0497] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0498] Step 1:

[0499] The user accesses the system from their terminal using a dedicated application or web interface. The input at this stage consists of details of the problem the user is reporting (e.g., error message, system behavior, date and time of occurrence). The output is the transmission of the entered problem details to the server. Specifically, the user fills out a form and clicks a submit button.

[0500] Step 2:

[0501] The server receives problem reports sent from terminals. Specifically, it receives problem reports as HTTP requests via a web server (e.g., Apache, Nginx) and stores their contents in a database. The input is the details of the problem report received from the user, and the output is the problem report information stored in the database.

[0502] Step 3:

[0503] The server determines whether the received problem report is a known issue or not. Specifically, this involves searching the knowledge base in the database (e.g., MySQL, PostgreSQL) to see if it matches any past issues. The input is the problem report information stored in the database, and the output is the determination result of whether the problem is known or unknown. Based on this determination result, the next action is decided.

[0504] Step 4:

[0505] If the server determines that the problem is a known issue, it searches its knowledge base for a solution and responds to the user. The input is the solution information retrieved from the knowledge base, and the output is the solution returned to the user. Specifically, the server executes an SQL query to search for a solution and sends it to the user as an HTTP response.

[0506] Step 5:

[0507] If the server determines that a problem is an unknown phenomenon, it delegates the analysis of the problem to a generative AI model (e.g., OpenAI GPT-3). The input is detailed information about the unknown problem report, and the output is the solution and knowledge generated by the generative AI model. Specifically, the server sends prompt messages to the generative AI model and obtains the analysis results.

[0508] Step 6:

[0509] The generative AI model analyzes the received problem report and generates new knowledge and solutions. The input is the detailed information of the problem report as a prompt, and the output is the analyzed knowledge and solutions. Specifically, the generative AI model analyzes the prompt, performs inference, and generates a new solution.

[0510] Step 7:

[0511] The server returns the generated solution to the user. The input is the solution obtained from the generating AI model, and the output is the response message to the user. Specifically, the server sends the solution to the user as an HTTP response.

[0512] Step 8:

[0513] The server automatically adds the knowledge generated by the AI ​​model to the knowledge base. The input is the newly generated knowledge, and the output is the updated knowledge base. Specifically, the server executes an SQL query to add the new knowledge to the database.

[0514] The above explains the system's program flow, broken down into specific processing steps.

[0515] (Application Example 1)

[0516] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0517] In logistics centers, it is crucial to resolve equipment and system errors quickly and effectively. However, existing systems often resulted in delays in responding to errors, frequently halting operations. Furthermore, the inability to quickly find appropriate countermeasures for unknown errors prolonged response times. This led to decreased operational efficiency at logistics centers, increased costs, and delays in delivery.

[0518] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0519] In this invention, the server includes means for users to report problems via a terminal, means for receiving problem reports and determining whether they are known events, means for responding with a method of action if they are known events, means for delegating analysis to a generative artificial intelligence and generating new knowledge if they are unknown events, means for adding the generated knowledge to a knowledge base, and means for workers to report problems using smart devices when equipment or system errors occur in a logistics center. This makes it possible to provide rapid countermeasures when errors occur, generate new knowledge for unknown errors to expedite responses, and improve the operational efficiency of the logistics center.

[0520] "Users" refers to individuals or workers who report problems when equipment or system errors occur at a logistics center.

[0521] "Terminal" refers to a smart device or computer used by a user to report a problem.

[0522] "Problem reporting" refers to the act of a user sending details of an error or malfunction via their device, as well as the content of that report.

[0523] "Known events" refer to problems or errors that already exist in the knowledge base and for which countermeasures have been established in the past.

[0524] An "unknown phenomenon" refers to a problem or error that does not exist in the knowledge base and requires new analysis and countermeasures.

[0525] "Generative artificial intelligence" refers to an artificial intelligence system that analyzes unknown phenomena and generates new knowledge and solutions.

[0526] A "knowledge base" refers to a database that stores known events and their corresponding countermeasures.

[0527] "Smart devices" refer to electronic devices such as smartphones and tablets that workers use to report problems.

[0528] "Analysis" refers to the process by which a generative artificial intelligence receives a problem report, examines the cause and solution of the event, and generates new knowledge.

[0529] A "logistics center" refers to a facility that manages and distributes goods and supplies.

[0530] This invention provides a system for quickly and effectively resolving errors in equipment and systems at a logistics center. The system includes user terminals, a server, generative artificial intelligence, and a knowledge base.

[0531] Basic configuration

[0532] User problem reports

[0533] Users report errors and problems using their devices. These reports are made using smart devices such as smartphones and tablets, and details of the error (text) and corresponding images are sent through a dedicated application.

[0534] Reception and determination by the server

[0535] The server receives problem reports submitted by users. First, it determines whether the received problem is a known issue or not. If it is a known issue, it searches the knowledge base for a solution and responds to the user. For example, if a stoppage of an electric conveyor is reported, the knowledge base will contain information recommending "restarting".

[0536] Responding to Unknown Events

[0537] If an unknown event occurs, the server delegates the analysis to a generative artificial intelligence (such as a GPT-4 model). The generative AI analyzes the received problem report and generates new knowledge and solutions. This generated knowledge is provided to users through the server and is also automatically added to the knowledge base.

[0538] Updating and reusing the knowledge base

[0539] New knowledge generated by generative artificial intelligence is stored in a knowledge base. This knowledge base is continuously updated, enabling rapid responses to future problems.

[0540] Specific example

[0541] For example, suppose a worker at a logistics center discovers a conveyor belt has stopped and reports the problem using a smart device, stating, "The conveyor belt has stopped. Error code 12345." This problem report is received by a server, which first determines whether it is a known issue. If it is an unknown issue, a generative artificial intelligence generates a new solution, such as "Readjust the belt." This solution is then sent back to the worker via the server and simultaneously added to the knowledge base.

[0542] Hardware and software to be used

[0543] Hardware: Smart devices (smartphones, tablets), servers

[0544] Software: Dedicated problem reporting application, generative artificial intelligence (GPT-4, etc.), knowledge base management system

[0545] Data processing and data calculation

[0546] 1. Data entry: Users enter details of the problem and images, and send them to the server.

[0547] 2. Data reception and determination: The server receives the problem report and determines whether it is known or unknown.

[0548] 3. Use of Generative Artificial Intelligence: In the case of unknown events, generative artificial intelligence analyzes the problem and generates new knowledge.

[0549] 4. Knowledge Base Update: Generated knowledge is automatically added to the knowledge base.

[0550] Example of a prompt

[0551] A possible prompt message when a worker reports a conveyor belt stoppage might be: "The conveyor belt has stopped. Error code 12345. Please tell me the cause and solution." This prompt is sent to a generative artificial intelligence system to serve as a reference for generating new knowledge.

[0552] The above describes specific embodiments for carrying out the present invention. This invention is expected to enable rapid problem solving in logistics centers and improve operational efficiency.

[0553] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0554] Step 1:

[0555] Users report problems using smart devices.

[0556] Input: Error details (text) and image

[0557] Output: Problem report data sent from the terminal

[0558] Specific operation: The user launches a dedicated application, enters details of the problem such as "The conveyor belt has stopped. Error code 12345," and adds images as needed. Then, by pressing the submit button, this data is sent to the server.

[0559] Step 2:

[0560] The server receives a problem report.

[0561] Input: Problem report data sent by the user from their device.

[0562] Output: Received problem report data is stored on the server.

[0563] Specific operation: The server stores the received data in a parseable format. For example, text data is stored as a string in the database, and image data is stored in the file system.

[0564] Step 3:

[0565] The server determines whether the problem report it receives is a known issue.

[0566] Input: Received problem report data

[0567] Output: Determination result of whether it is a known or unknown event.

[0568] Specific operation: The server compares the content of the problem report with the knowledge base and checks if it contains known error codes or keywords. If there is a match, it is determined to be a known issue.

[0569] Step 4:

[0570] If the issue is known, the server will search its knowledge base for a solution and respond to the user.

[0571] Input: Problem report data identified as a known issue

[0572] Output: Reply message including the suggested course of action

[0573] Specific actions: Search the knowledge base for relevant solutions (e.g., "Restart the conveyor belt") and send that information to the user as a text message.

[0574] Step 5:

[0575] If the phenomenon is unknown, the server delegates the analysis to a generative artificial intelligence.

[0576] Input: Problem report data identified as an unknown event

[0577] Output: Data sent to the generative artificial intelligence for problem analysis.

[0578] Specific operation: The server sends the details of the problem report to the generative artificial intelligence. It generates a prompt message (e.g., "The conveyor belt has stopped. Error code 12345. Please tell me the cause and solution.") and sends it to the generative artificial intelligence model.

[0579] Step 6:

[0580] Generative artificial intelligence generates new knowledge and solutions.

[0581] Input: Prompt sent to a generative AI

[0582] Output: Generated knowledge and solutions

[0583] Specific operation: The generative artificial intelligence analyzes the prompt text and generates a cause analysis and solution (e.g., "Readjust the belt") in text format.

[0584] Step 7:

[0585] The server returns the generated knowledge to the user and adds it to the knowledge base.

[0586] Input: Knowledge and solutions generated by generative artificial intelligence.

[0587] Output: Solution messages sent to users and updated knowledge base

[0588] Specific operation: The server returns the generated knowledge to the user and saves it as new knowledge in the knowledge base. The user receives a message that includes specific instructions on how to proceed (e.g., "Readjust the belt").

[0589] Step 8:

[0590] We will address future issues based on the updated knowledge base.

[0591] Input: Updated Knowledge Base

[0592] Output: Prompt response to future problem reports

[0593] Specific action: By updating the knowledge base, the server can quickly provide solutions when similar problems recur. For example, the next time the same error code is reported, the solution "re-adjust the belt" will be immediately suggested.

[0594] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0595] This invention is a system for improving efficiency in server maintenance, enabling rapid response to unknown events and knowledge accumulation. Furthermore, by combining it with an emotion engine that recognizes user emotions, it provides more appropriate responses.

[0596] Basic configuration

[0597] This system includes a server that receives reports from users via their terminals, a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge, and an emotion engine that recognizes the user's emotions.

[0598] User reports

[0599] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This sends the problem report to the server.

[0600] Reception and determination by the server

[0601] The server receives a problem report sent from a terminal and first determines whether it is a known issue. If it is a known issue, the server searches its existing knowledge base for a solution and responds to the user with a suggested solution.

[0602] Handling known events

[0603] If the issue is known, the server will provide a solution based on its knowledge base. For example, if "Error Code 500" is reported, the server will respond to the user with the solution "Restart the server." The solution will be displayed on the terminal screen.

[0604] Handling unknown events

[0605] If the phenomenon is unknown, the server delegates the analysis of the problem to a generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[0606] Generative artificial intelligence analyzes received problem reports and generates new knowledge and solutions. For example, it might generate solutions such as "Check the configuration file and configure it appropriately." The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[0607] User emotion recognition

[0608] When the server receives a problem report, it uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's text input and voice data to determine whether the user is feeling anxiety, anger, stress, etc.

[0609] Responding according to emotions

[0610] After the emotion engine recognizes the user's emotions, the server selects an appropriate response. For example, if the user is experiencing high levels of stress, the server will respond quickly, providing detailed instructions on the steps necessary to resolve the problem. It may also respond with a gentle, encouraging message.

[0611] Updating and reusing the knowledge base

[0612] New knowledge generated by generative artificial intelligence is stored in the knowledge base. Furthermore, user emotion data recognized by the emotion engine is also stored in the knowledge base, making it possible to provide countermeasures that take past emotion data into account when future problems are reported.

[0613] This allows the system to respond quickly and appropriately the next time a similar problem occurs. Furthermore, if the same problem recurs, a rapid response based on the knowledge base is possible, reducing the time and cost of system maintenance. The emotion recognition function improves the user experience and increases user satisfaction.

[0614] Specific example

[0615] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives this problem. The server determines if this problem already exists in the knowledge base. If it is not a known issue, it delegates the analysis to a generative artificial intelligence system, which generates a solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user through the server and added to the knowledge base. Furthermore, an emotion engine recognizes the user's emotions and generates a message to alleviate the user's stress.

[0616] This invention automates the process from problem reporting to solution provision, continuously strengthening the knowledge base and improving the overall maintainability of the system. Incorporating emotion recognition enhances the user experience, enabling the delivery of more satisfying services. This system not only facilitates rapid problem resolution but also enables knowledge accumulation and reuse, resulting in long-term operational efficiency.

[0617] The above describes embodiments for carrying out the present invention.

[0618] The following describes the processing flow.

[0619] Step 1:

[0620] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time of occurrence, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This action sends the problem report to the server.

[0621] Step 2:

[0622] The server receives a problem report. The received problem report is stored in the internal database.

[0623] Step 3:

[0624] The server uses an emotion engine to analyze the user's emotions from the problem report. The emotion engine uses text analysis and speech analysis to determine the user's emotional state (e.g., anxiety, anger, stress).

[0625] Step 4:

[0626] The server compares the problem report against a list of known events to determine whether or not it is a known event. This determination is made by comparing the data in the knowledge base with the content of the problem report.

[0627] Step 5:

[0628] If the server determines that the reported problem is a known issue, it searches its knowledge base for a solution and provides it to the user. For example, if "Error Code 500" is reported, a solution such as "Restart the server" will be displayed on the terminal.

[0629] Step 6:

[0630] If the server determines that the reported problem is an unknown phenomenon, it delegates the analysis of the problem to a generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[0631] Step 7:

[0632] Generative artificial intelligence receives a problem report and begins analysis. The AI ​​uses its machine learning models and datasets to analyze the problem and generate new knowledge and solutions. For example, it might generate specific solutions such as "check the configuration file and configure it appropriately."

[0633] Step 8:

[0634] The generative artificial intelligence generates knowledge, which is then sent back to the server. The server then provides that knowledge to the user. The user can then view the newly generated solution on their device screen.

[0635] Step 9:

[0636] The server adds the generated knowledge to the knowledge base. The knowledge base is managed as a database and used for addressing future issues. In addition, user sentiment data analyzed by the sentiment engine is also stored in the knowledge base.

[0637] Step 10:

[0638] In the event of a similar problem occurring in the future, the server will promptly provide solutions based on its knowledge base. It can also provide solutions that take past emotional data into account; for example, if a user is experiencing high levels of stress, it will prioritize encouraging messages and a quick response.

[0639] The above describes the specific processing flow of the system based on the present invention.

[0640] (Example 2)

[0641] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0642] In recent years, with the increasing complexity of information systems, the number of users reporting problems has been rising. While known issues can be addressed quickly, responding appropriately to unknown issues is difficult. Furthermore, users' emotional states influence the speed of problem resolution and their satisfaction, but conventional systems cannot analyze emotions or respond flexibly based on them. Therefore, there is a need for a system that can quickly address unknown problems while simultaneously providing appropriate responses that respond to users' emotions.

[0643] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to report a problem through an information processing device, means for receiving the problem report and determining whether it is a known phenomenon, means for responding with a solution if it is a known phenomenon, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown phenomenon, means for adding the generated knowledge to a knowledge database, means for recognizing the user's emotions using an emotion analysis engine, and means for adjusting the solution based on the recognized emotions. This enables a quick and appropriate response even to unknown problems, and also enables a flexible response that responds to the user's emotions.

[0644] 1. An "information processing device" is a device such as a computer or smartphone that users use to input, process, and output data.

[0645] 2. "Problem reporting" refers to the act of a user sending information to the system to inform it of the details of a malfunction or problem that has occurred.

[0646] 3. A "known phenomenon" is a problem that has already been recorded in the knowledge base and for which countermeasures have been clearly determined.

[0647] 4. An "unknown phenomenon" is a problem that has not been recorded in the past and for which countermeasures have not been established.

[0648] 5. "Generative artificial intelligence" is artificial intelligence that has the ability to analyze input data and generate new knowledge and solutions.

[0649] 6. "New knowledge" refers to solutions and information for unknown phenomena that are analyzed and generated by generative artificial intelligence.

[0650] 7. A "knowledge database" is a database used to accumulate and manage solutions to known phenomena and new knowledge.

[0651] 8. An "emotion analysis engine" is a system that analyzes user input data and identifies the user's emotional state.

[0652] 9. "Solution" refers to the solutions or procedures that the system provides in response to a problem report.

[0653] 10. "Adjusting coping strategies based on recognized emotions" means changing the content and manner of coping strategies according to the user's emotional state as recognized by the emotion analysis engine.

[0654] This invention relates to a problem reporting system using an information processing device, which responds quickly and appropriately to problem reports from users. Furthermore, by combining it with an emotion analysis engine, it achieves flexible responses that respond to the user's emotions. The following describes in detail specific embodiments for carrying out this invention.

[0655] Basic configuration

[0656] This system includes a server that receives user reports via an information processing device, a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge, and an emotion analysis engine that recognizes user emotions. The detailed functions of each element are described below.

[0657] User reports

[0658] Users report problems using information processing devices (e.g., personal computers, smartphones) via a dedicated application or web interface. Users enter detailed information such as error messages, the date and time the problem occurred, and system behavior, and then press the submit button to report the problem.

[0659] Reception and determination by the server

[0660] The server receives problem reports submitted by users. The server consults its knowledge database to determine whether the reported problem is a known issue. If it is a known issue, the server searches the knowledge database for a solution and responds to the user with the appropriate action. For example, if "error code 500" is reported, the server will respond to the user with the solution "restart the system."

[0661] Processing known phenomena

[0662] In the case of a known issue, the server provides a solution based on its knowledge database. The solution is displayed on the user's information processing device screen. For example, if "Error Code 500" is reported, the server will suggest "Restart the server" as the solution.

[0663] Processing unknown phenomena

[0664] If the phenomenon is unknown, the server delegates the analysis of the problem to a generative artificial intelligence (e.g., GPT-4). The server sends the content of the problem report to the generative AI. The generative AI analyzes the received problem report and generates new knowledge and solutions. For example, it might generate a solution such as "Check the configuration file and configure it appropriately." The generated knowledge is returned to the user through the server and added to the knowledge database.

[0665] User emotion recognition by emotion analysis engine

[0666] When the server receives a problem report, it uses an emotion analysis engine (e.g., IBM Watson) to analyze the user's emotions. The emotion analysis engine analyzes the user's input data to determine whether the user is feeling anxiety, anger, stress, etc.

[0667] Responding according to emotions

[0668] After the emotion analysis engine recognizes the user's emotions, the server adjusts its response based on the recognized emotions. For example, if the user is experiencing high levels of stress, the server will respond quickly and provide detailed instructions on the steps necessary to resolve the problem. It will also respond with encouraging messages to help alleviate the user's feelings.

[0669] Updating and reusing the knowledge database

[0670] New knowledge generated by generative artificial intelligence is stored in a knowledge database. Furthermore, user emotion data recognized by the emotion analysis engine is also stored in the knowledge database. This enables quick and appropriate responses when similar problems occur in the future. It also allows for the provision of countermeasures that take past emotion data into account when reporting problems in the future. As a result, the system not only enables rapid problem solving but also facilitates the accumulation and reuse of knowledge, leading to long-term operational efficiency.

[0671] Specific example

[0672] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives the problem and determines if it already exists in the knowledge database. If it's not a known issue, it delegates the analysis to generative artificial intelligence, which generates a solution such as "check the configuration file and configure it appropriately." This generated solution is then returned to the user via the server and added to the knowledge database. Furthermore, an emotion analysis engine recognizes the user's emotions and generates a message to alleviate their stress.

[0673] Example of a prompt

[0674] "Please generate an appropriate solution for the issue where 'the application crashes when trying to save a file.' Since this is causing significant stress to the user, please also include a reassuring message."

[0675] This invention automates the process from problem reporting to solution provision, and the knowledge database is continuously strengthened, improving the overall maintainability of the system. By incorporating emotion recognition functionality, the user experience is enhanced, enabling the provision of more satisfying services. This system not only enables rapid problem resolution but also facilitates the accumulation and reuse of knowledge, resulting in long-term operational efficiency.

[0676] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0677] Step 1: User reports a problem.

[0678] Input: The user uses an information processing device (e.g., personal computer, smartphone) to access a dedicated application or web interface and enter details of the problem (e.g., error message, date and time of occurrence, system behavior, etc.).

[0679] Specific operation: The user enters the necessary information into the problem report form and presses the "Submit" button to report the problem.

[0680] Output: The problem report is sent to the server.

[0681] Step 2: Server receives report and determines known / unknown information.

[0682] Input: The server receives problem reports submitted by users.

[0683] Specific operation: The server analyzes the received problem report and accesses the knowledge database to determine whether or not it is a known phenomenon.

[0684] Output: If the issue is known, retrieve a solution from the knowledge database; if it is an unknown issue, proceed to the next step.

[0685] Step 3: Server response to known issues

[0686] Input: The server retrieves solutions for known issues from the knowledge database.

[0687] Specific operation: The server sends the solution to the user's information processing device and displays it on the screen.

[0688] Output: The user is provided with specific countermeasures (e.g., "Restart the system" for error code 500).

[0689] Step 4: Delegation of analysis of unknown phenomena to the server

[0690] Input: The server determines that this is not a known phenomenon and delegates the analysis to a generative AI model (e.g., GPT-4).

[0691] Specific operation: The server sends the details of the problem report to the generating AI model.

[0692] Output: Details of the problem report are sent to the generating AI model.

[0693] Step 5: Generating new knowledge using a generative AI model

[0694] Input: The generated AI model receives problem reports sent from the server.

[0695] Specific operation: The generative AI model analyzes the problem and generates new knowledge and solutions (e.g., "Check the configuration file and configure it appropriately").

[0696] Output: The generated solution is sent back to the server.

[0697] Step 6: Responding with new knowledge and managing stress

[0698] Input: The server receives the solution returned from the generated AI model.

[0699] Specific operation: The server responds to the user with a solution and simultaneously analyzes the user's emotions using an emotion analysis engine (e.g., IBM Watson). If stress is detected, it generates detailed instructions and an encouraging message.

[0700] Output: The user is provided with concrete solutions and emotionally resonant messages.

[0701] Step 7: Update the knowledge database by the server.

[0702] Input: The server receives new knowledge generated by the generation AI model and data from the emotion analysis engine.

[0703] Specific operation: The server adds new knowledge to the knowledge database and stores sentiment data along with it.

[0704] Output: The knowledge database will be updated, and problem handling and emotional support will be enhanced for future issues.

[0705] The above describes the processing steps of the program for this system.

[0706] (Application Example 2)

[0707] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0708] Existing problem-solving systems were time-consuming to respond to unfamiliar situations, making it difficult to provide appropriate solutions quickly. Furthermore, they failed to consider user emotions, hindering improvements in the user experience. As a result, there was a lack of means to alleviate user stress and dissatisfaction.

[0709] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0710] In this invention, the server includes means for a user to report a problem via a terminal, means for receiving the problem report and determining whether it is a known event, means for responding with a method of action if it is a known event, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown event, means for adding the generated knowledge to a knowledge base, means for sentiment analysis to recognize the user's emotions, and means for providing countermeasures according to the recognized emotions. This enables rapid response to unknown events and effective accumulation of knowledge, and furthermore, by taking user emotions into consideration, it is possible to improve the user experience and reduce dissatisfaction.

[0711] A "user" refers to a person who uses the system or device to report a problem and receive a solution.

[0712] A "device" refers to a device used by a user to report a problem, and includes smartphones, personal computers, and other similar devices.

[0713] "Problem reporting" refers to the act of a user informing the system of any malfunctions or errors that have occurred, as well as the content of that information.

[0714] A "server" refers to a computer system that receives problem reports, analyzes them, and generates solutions.

[0715] "Known events" refer to events where similar problems have occurred in the past, and for which solutions have already been accumulated in the knowledge base.

[0716] An "unknown event" refers to an event that has never occurred before, or for which no solution exists in the knowledge base.

[0717] "Generative artificial intelligence" refers to artificial intelligence technology used to generate new solutions and knowledge in response to unknown phenomena.

[0718] "Knowledge" refers to information, data, and solutions that are useful for solving problems.

[0719] A "knowledge base" refers to a database where accumulated knowledge is stored and can be searched and referenced.

[0720] "Emotional analysis means" refers to technologies and devices used to analyze and recognize the emotions of users.

[0721] "Countermeasures" refer to the specific means or methods provided to solve a problem.

[0722] The system for implementing this invention consists of the following elements. First, a terminal is required for users to report problems. The terminal includes smartphones and personal computers, and has a dedicated application installed. Using this application, users can input details of the problem and send them to the server.

[0723] Upon receiving this problem report, the server first determines whether the reported issue is a known problem. If it is a known issue, the server searches its knowledge base for a solution and responds to the user.

[0724] If an unknown phenomenon occurs, the server delegates the analysis of the problem to a generative artificial intelligence (AI). The generative AI analyzes the received problem report and generates new knowledge and solutions. This new knowledge is returned to the user through the server and is also automatically added to the knowledge base.

[0725] Furthermore, the server recognizes the user's emotions using emotion analysis tools. These tools utilize an emotion analysis model based on the Hugging Face transformers library. This allows the server to analyze the user's emotions, such as stress and frustration, and provide appropriate responses based on the recognized emotions. For example, if the user is experiencing high levels of stress, the server will respond quickly, providing detailed instructions on the steps necessary to resolve the problem. It will also respond with a gentle, encouraging message.

[0726] Hardware and software to be used

[0727] Hardware:

[0728] Server: Cloud servers such as AWS and Google Cloud

[0729] Devices: Smartphones and computers (iOS, Android, Windows, Mac, etc.)

[0730] software:

[0731] Flask: A web framework written in Python.

[0732] transformers:Hugging Face is a library for emotion analysis models.

[0733] Specific example

[0734] A user reports a problem, such as "the vehicle's autonomous driving function has stopped working." Using the application on their device, they enter details of the problem (e.g., "fault_code_001") and a message describing their concern (e.g., "The autonomous driving function suddenly stopped working. I'm very worried."). The problem report is sent to the server, which receives the problem.

[0735] The server determines from the problem report whether it is a known issue. If it is a known issue, it searches the knowledge base for an appropriate solution and responds. However, in this case, it is determined to be an unknown issue, so generative artificial intelligence analyzes the problem and generates a new solution (for example, "check the configuration file and make the appropriate settings").

[0736] Furthermore, sentiment analysis tools are used to analyze the user's messages and recognize if the user is experiencing stress or worry. In response, encouraging messages such as, "Don't worry, we'll let you know the solution soon," are also sent back.

[0737] Example of a prompt

[0738] The following are specific examples of prompt statements.

[0739] Problem: fault_code_001

[0740] Message: The autonomous driving function suddenly stopped working. I am very worried.

[0741] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0742] Step 1:

[0743] Users report problems using their devices.

[0744] The user opens a dedicated application on their device, enters details of the problem (error message, date and time of occurrence, circumstances, etc.), and submits a report.

[0745] Input: Problem details (text data)

[0746] Output: Problem report data sent to the server

[0747] Step 2:

[0748] The server receives a problem report.

[0749] The server analyzes the problem report data sent from the terminal and retrieves the details of the problem.

[0750] Input: Problem report data

[0751] Output: Analyzed problem content

[0752] Step 3:

[0753] The server determines whether the problem is known.

[0754] The server accesses the knowledge base to check whether the reported issue is a known issue. If it is a known issue, it retrieves the appropriate solution from the knowledge base.

[0755] Input: Analyzed problem description, knowledge base

[0756] Output: Countermeasures (only for known issues)

[0757] Step 4:

[0758] The server will respond with a solution (if it's a known issue).

[0759] The server returns a solution retrieved from the knowledge base to the user. This solution is displayed on the terminal screen.

[0760] Input: Countermeasures

[0761] Output: Reply to the user

[0762] Step 5:

[0763] The server delegates the problem to a generative artificial intelligence (in the case of an unknown event).

[0764] If the issue is not known, the server delegates the analysis of the problem to a generative artificial intelligence.

[0765] Input: Analyzed problem content

[0766] Output: Problem data for generative artificial intelligence

[0767] Step 6:

[0768] Generative artificial intelligence analyzes the problem and generates new knowledge.

[0769] Generative artificial intelligence analyzes problem reports and generates new solutions.

[0770] Input: Problem data

[0771] Output: New knowledge (solution)

[0772] Step 7:

[0773] The server adds the generated knowledge to the knowledge base.

[0774] The newly generated knowledge is automatically added to the knowledge base.

[0775] Input: New knowledge

[0776] Output: Updated Knowledge Base

[0777] Step 8:

[0778] The server recognizes the user's emotions using emotion analysis tools.

[0779] The server inputs the user's text message into an emotion analysis model and analyzes their emotional state.

[0780] Input: User's text message

[0781] Output: Emotional state data

[0782] Step 9:

[0783] The server provides countermeasures based on the emotions it recognizes.

[0784] Based on the sentiment analysis results, the system sends users appropriate responses or encouraging messages.

[0785] Input: Emotional state data, new solution

[0786] Output: Emotionally sensitive responses and messages

[0787] Step 10:

[0788] The server returns the response result to the user.

[0789] Ultimately, the server responds to the user with the generated solution and a message tailored to their emotions, displaying it on their device.

[0790] Input: Emotionally sensitive responses and solutions

[0791] Output: Information returned to the terminal

[0792] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0793] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0794] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0795] [Third Embodiment]

[0796] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0797] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0798] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0799] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0800] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0801] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0802] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0803] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0804] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0805] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0806] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0807] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0808] This invention is a system for improving efficiency in server maintenance, enabling rapid response to unknown events and knowledge accumulation. Specific embodiments of this system are described below.

[0809] Basic configuration

[0810] This system includes a server that receives reports from users via their terminals, and a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge.

[0811] User reports

[0812] Users report problems to the system using their devices. Specifically, users report problems by entering details of the problem (e.g., error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then pressing the submit button.

[0813] Reception and determination by the server

[0814] The server receives a problem report sent from a terminal and first determines whether it is a known issue. If it is a known issue, the server searches its existing knowledge base for a solution and responds to the user with a suggested solution.

[0815] Handling known events

[0816] If the issue is known, the server will provide a solution based on its knowledge base. For example, if "Error Code 500" is reported, the server will respond to the user with a solution such as "Restart the server."

[0817] Handling unknown events

[0818] If the issue is unknown, the server delegates the problem analysis to a generative artificial intelligence (AI). The AI ​​analyzes the received problem report and generates new knowledge and solutions. The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[0819] Updating and reusing the knowledge base

[0820] New knowledge generated by generative artificial intelligence is stored in a knowledge base. The knowledge base is updated, enabling quick solutions to be provided if similar problems occur again. This allows for rapid response when the same problem recurs, reducing the time and cost of system maintenance.

[0821] Specific example

[0822] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives this problem. The server determines whether this problem already exists in the knowledge base. If it is not a known issue, it delegates the analysis to a generative artificial intelligence system, which generates a new solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user through the server and added to the knowledge base.

[0823] This invention automates the process from problem reporting to solution provision, and the knowledge base is continuously strengthened, thereby improving the overall maintainability of the system. This system enables not only rapid problem resolution but also knowledge accumulation and reuse, resulting in long-term operational efficiency.

[0824] The above describes embodiments for carrying out the present invention.

[0825] The following describes the processing flow.

[0826] Step 1:

[0827] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This sends the problem report to the server.

[0828] Step 2:

[0829] The server receives a problem report. The received problem report is stored in an internal database, and then processing begins to determine whether or not it is a known issue.

[0830] Step 3:

[0831] The server compares the problem report against the known issues list. The known issues list contains information about past problems and their solutions. If the problem report is found in the known issues list, the server searches for the corresponding solution.

[0832] Step 4:

[0833] If the server determines that the issue is known, it will respond to the user with a suggested solution. For example, if "Error Code 500" is reported, the server will respond to the user with the solution "Restart the server." The solution will be displayed on the terminal screen.

[0834] Step 5:

[0835] If the server determines that the reported problem does not exist in the list of known events, it delegates the analysis of the problem to the generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[0836] Step 6:

[0837] The generative artificial intelligence receives a problem report and begins analysis. The generative AI uses machine learning algorithms to analyze the problem and generate new knowledge and solutions. For example, it might generate a solution such as "check the configuration file and configure it appropriately."

[0838] Step 7:

[0839] The generative artificial intelligence generates knowledge and sends it back to the server. The server receives the generated knowledge and responds to the user. The user can then view the solution on their device screen.

[0840] Step 8:

[0841] The server adds the generated knowledge to the knowledge base. The knowledge base is managed as a database, and the addition of new knowledge allows for faster problem resolution in the future.

[0842] The above is the specific processing flow of the program.

[0843] (Example 1)

[0844] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0845] In conventional systems, it was difficult to respond quickly and appropriately to user-reported problems, often resulting in long resolution times. Furthermore, when similar problems recurred, past solutions were not efficiently reused, leading to decreased maintenance efficiency. Additionally, when analysis and solution generation for unknown events were performed manually, knowledge base updates were delayed, reducing the overall operational efficiency of the system.

[0846] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0847] In this invention, the server includes means for a user to report a problem via a terminal, means for receiving the problem report and determining whether it is a known event, means for responding with a method of action if it is a known event, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown event, means for generating new knowledge and solutions from the received problem report using the generative artificial intelligence and responding to the user, and means for adding the generated knowledge to the knowledge base. This enables a quick and appropriate response to problems reported by users, promotes continuous updating and reuse of the knowledge base, and improves the efficiency of maintenance work for the entire system.

[0848] A "user" is the operator of a terminal that uses the system to report a problem.

[0849] A "terminal" refers to a device, such as a PC or smartphone, used to report problems to the system.

[0850] A "server" is a central management device that receives problem reports, determines whether or not they are known events, and delegates the analysis to a generative artificial intelligence.

[0851] A "problem" refers to a system malfunction reported by a user, such as a system error message, abnormal behavior, or failure.

[0852] A "report" is detailed information about a problem that a user sends to the system via their device.

[0853] "Known events" are problems that have occurred in the past and are registered in the knowledge base.

[0854] An "unknown phenomenon" refers to a new problem that does not exist in the knowledge base.

[0855] "Judgment" is the process of checking whether a received problem report is a known issue or not.

[0856] A "response" is the act of a server notifying a user of how to respond or a solution.

[0857] "Generative artificial intelligence" refers to an AI model that analyzes received problem reports to generate new knowledge and solutions.

[0858] "Analysis" is the process of thoroughly examining the contents of a problem report to find the cause and solution.

[0859] "Knowledge" refers to the knowledge and data generated by generative artificial intelligence for problem-solving.

[0860] A "knowledge base" is a database system that stores existing and newly generated knowledge.

[0861] A "prompt statement" is an input statement used when requesting a generative artificial intelligence to analyze a problem.

[0862] This invention provides a system that improves the efficiency of server maintenance and enables rapid response to unknown events and the accumulation of knowledge. The system includes a server that receives reports from users via a terminal, and a generative AI model that analyzes unknown events and generates new knowledge.

[0863] Basic configuration

[0864] This system includes a dedicated application or web interface for users to report problems via their devices, a server that receives these reports and determines whether they are known issues, and a generative AI model. The hardware used includes PCs and smartphones as devices, while the server utilizes virtual machines or physical servers in the cloud. The software includes web servers such as Apache and Nginx, database management systems such as MySQL and PostgreSQL, and generative AI models such as OpenAI GPT-3.

[0865] User reports

[0866] Users report problems to the system using their devices. Specifically, users report problems by entering details of the problem (e.g., error message, system behavior, date and time of occurrence, etc.) through a dedicated application on their device or a web interface, and then pressing the submit button. For example, a user might report that "the application crashes when I try to save a file."

[0867] Reception and determination by the server

[0868] The server receives problem reports sent from terminals. The server first determines whether the problem is a known issue by cross-referencing it with the knowledge base. The knowledge base stores past problems and their solutions.

[0869] Handling known events

[0870] If the issue is known, the server searches its knowledge base for a solution and responds to the user. For example, if "Error Code 500" is reported, the server will respond with a solution such as "Restart the server." The database management system used in this case is MySQL or PostgreSQL.

[0871] Handling unknown events

[0872] If an unknown phenomenon occurs, the server delegates the problem analysis to a generative AI model. This generative AI model, built using OpenAI GPT-3 and other technologies, analyzes the received problem report and generates new knowledge and solutions. The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[0873] Updating and reusing the knowledge base

[0874] New knowledge generated by the generative AI model is stored in a knowledge base. The knowledge base is updated, enabling rapid response to similar problems in the future. This reduces the time and cost associated with system maintenance.

[0875] Specific example

[0876] For example, if a user reports a problem where "the application crashes when trying to save a file," the server receives the issue and determines if it already exists in the knowledge base. If it's not a known issue, it delegates the analysis to a generative AI model, which generates a new solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user via the server and added to the knowledge base.

[0877] Example of a prompt

[0878] Examples of specific prompt messages:

[0879] "User-reported issue: The application crashes when attempting to save a file. Error message: 'Error 404: File not found', Date and time of occurrence: October 1, 2023, System behavior: The application immediately terminates. Please provide a solution."

[0880] This invention automates the process from problem reporting to solution provision, and the knowledge base is continuously strengthened, thereby improving the overall maintainability of the system. This system enables not only rapid problem resolution but also knowledge accumulation and reuse, resulting in long-term operational efficiency.

[0881] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0882] Step 1:

[0883] The user accesses the system from their terminal using a dedicated application or web interface. The input at this stage consists of details of the problem the user is reporting (e.g., error message, system behavior, date and time of occurrence). The output is the transmission of the entered problem details to the server. Specifically, the user fills out a form and clicks a submit button.

[0884] Step 2:

[0885] The server receives problem reports sent from terminals. Specifically, it receives problem reports as HTTP requests via a web server (e.g., Apache, Nginx) and stores their contents in a database. The input is the details of the problem report received from the user, and the output is the problem report information stored in the database.

[0886] Step 3:

[0887] The server determines whether the received problem report is a known issue or not. Specifically, this involves searching the knowledge base in the database (e.g., MySQL, PostgreSQL) to see if it matches any past issues. The input is the problem report information stored in the database, and the output is the determination result of whether the problem is known or unknown. Based on this determination result, the next action is decided.

[0888] Step 4:

[0889] If the server determines that the problem is a known issue, it searches its knowledge base for a solution and responds to the user. The input is the solution information retrieved from the knowledge base, and the output is the solution returned to the user. Specifically, the server executes an SQL query to search for a solution and sends it to the user as an HTTP response.

[0890] Step 5:

[0891] If the server determines that a problem is an unknown phenomenon, it delegates the analysis of the problem to a generative AI model (e.g., OpenAI GPT-3). The input is detailed information about the unknown problem report, and the output is the solution and knowledge generated by the generative AI model. Specifically, the server sends prompt messages to the generative AI model and obtains the analysis results.

[0892] Step 6:

[0893] The generative AI model analyzes the received problem report and generates new knowledge and solutions. The input is the detailed information of the problem report as a prompt, and the output is the analyzed knowledge and solutions. Specifically, the generative AI model analyzes the prompt, performs inference, and generates a new solution.

[0894] Step 7:

[0895] The server returns the generated solution to the user. The input is the solution obtained from the generating AI model, and the output is the response message to the user. Specifically, the server sends the solution to the user as an HTTP response.

[0896] Step 8:

[0897] The server automatically adds the knowledge generated by the AI ​​model to the knowledge base. The input is the newly generated knowledge, and the output is the updated knowledge base. Specifically, the server executes an SQL query to add the new knowledge to the database.

[0898] The above explains the system's program flow, broken down into specific processing steps.

[0899] (Application Example 1)

[0900] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0901] In logistics centers, it is crucial to resolve equipment and system errors quickly and effectively. However, existing systems often resulted in delays in responding to errors, frequently halting operations. Furthermore, the inability to quickly find appropriate countermeasures for unknown errors prolonged response times. This led to decreased operational efficiency at logistics centers, increased costs, and delays in delivery.

[0902] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0903] In this invention, the server includes means for users to report problems via a terminal, means for receiving problem reports and determining whether they are known events, means for responding with a method of action if they are known events, means for delegating analysis to a generative artificial intelligence and generating new knowledge if they are unknown events, means for adding the generated knowledge to a knowledge base, and means for workers to report problems using smart devices when equipment or system errors occur in a logistics center. This makes it possible to provide rapid countermeasures when errors occur, generate new knowledge for unknown errors to expedite responses, and improve the operational efficiency of the logistics center.

[0904] "Users" refers to individuals or workers who report problems when equipment or system errors occur at a logistics center.

[0905] "Terminal" refers to a smart device or computer used by a user to report a problem.

[0906] "Problem reporting" refers to the act of a user sending details of an error or malfunction via their device, as well as the content of that report.

[0907] "Known events" refer to problems or errors that already exist in the knowledge base and for which countermeasures have been established in the past.

[0908] An "unknown phenomenon" refers to a problem or error that does not exist in the knowledge base and requires new analysis and countermeasures.

[0909] "Generative artificial intelligence" refers to an artificial intelligence system that analyzes unknown phenomena and generates new knowledge and solutions.

[0910] A "knowledge base" refers to a database that stores known events and their corresponding countermeasures.

[0911] "Smart devices" refer to electronic devices such as smartphones and tablets that workers use to report problems.

[0912] "Analysis" refers to the process by which a generative artificial intelligence receives a problem report, examines the cause and solution of the event, and generates new knowledge.

[0913] A "logistics center" refers to a facility that manages and distributes goods and supplies.

[0914] This invention provides a system for quickly and effectively resolving errors in equipment and systems at a logistics center. The system includes user terminals, a server, generative artificial intelligence, and a knowledge base.

[0915] Basic configuration

[0916] User problem reports

[0917] Users report errors and problems using their devices. These reports are made using smart devices such as smartphones and tablets, and details of the error (text) and corresponding images are sent through a dedicated application.

[0918] Reception and determination by the server

[0919] The server receives problem reports submitted by users. First, it determines whether the received problem is a known issue or not. If it is a known issue, it searches the knowledge base for a solution and responds to the user. For example, if a stoppage of an electric conveyor is reported, the knowledge base will contain information recommending "restarting".

[0920] Responding to Unknown Events

[0921] If an unknown event occurs, the server delegates the analysis to a generative artificial intelligence (such as a GPT-4 model). The generative AI analyzes the received problem report and generates new knowledge and solutions. This generated knowledge is provided to users through the server and is also automatically added to the knowledge base.

[0922] Updating and reusing the knowledge base

[0923] New knowledge generated by generative artificial intelligence is stored in a knowledge base. This knowledge base is continuously updated, enabling rapid responses to future problems.

[0924] Specific example

[0925] For example, suppose a worker at a logistics center discovers a conveyor belt has stopped and reports the problem using a smart device, stating, "The conveyor belt has stopped. Error code 12345." This problem report is received by a server, which first determines whether it is a known issue. If it is an unknown issue, a generative artificial intelligence generates a new solution, such as "Readjust the belt." This solution is then sent back to the worker via the server and simultaneously added to the knowledge base.

[0926] Hardware and software to be used

[0927] Hardware: Smart devices (smartphones, tablets), servers

[0928] Software: Dedicated problem reporting application, generative artificial intelligence (GPT-4, etc.), knowledge base management system

[0929] Data processing and data calculation

[0930] 1. Data entry: Users enter details of the problem and images, and send them to the server.

[0931] 2. Data reception and determination: The server receives the problem report and determines whether it is known or unknown.

[0932] 3. Use of Generative Artificial Intelligence: In the case of unknown events, generative artificial intelligence analyzes the problem and generates new knowledge.

[0933] 4. Knowledge Base Update: Generated knowledge is automatically added to the knowledge base.

[0934] Example of a prompt

[0935] A possible prompt message when a worker reports a conveyor belt stoppage might be: "The conveyor belt has stopped. Error code 12345. Please tell me the cause and solution." This prompt is sent to a generative artificial intelligence system to serve as a reference for generating new knowledge.

[0936] The above describes specific embodiments for carrying out the present invention. This invention is expected to enable rapid problem solving in logistics centers and improve operational efficiency.

[0937] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0938] Step 1:

[0939] Users report problems using smart devices.

[0940] Input: Error details (text) and image

[0941] Output: Problem report data sent from the terminal

[0942] Specific operation: The user launches a dedicated application, enters details of the problem such as "The conveyor belt has stopped. Error code 12345," and adds images as needed. Then, by pressing the submit button, this data is sent to the server.

[0943] Step 2:

[0944] The server receives a problem report.

[0945] Input: Problem report data sent by the user from their device.

[0946] Output: Received problem report data is stored on the server.

[0947] Specific operation: The server stores the received data in a parseable format. For example, text data is stored as a string in the database, and image data is stored in the file system.

[0948] Step 3:

[0949] The server determines whether the problem report it receives is a known issue.

[0950] Input: Received problem report data

[0951] Output: Determination result of whether it is a known or unknown event.

[0952] Specific operation: The server compares the content of the problem report with the knowledge base and checks if it contains known error codes or keywords. If there is a match, it is determined to be a known issue.

[0953] Step 4:

[0954] If the issue is known, the server will search its knowledge base for a solution and respond to the user.

[0955] Input: Problem report data identified as a known issue

[0956] Output: Reply message including the suggested course of action

[0957] Specific actions: Search the knowledge base for relevant solutions (e.g., "Restart the conveyor belt") and send that information to the user as a text message.

[0958] Step 5:

[0959] If the phenomenon is unknown, the server delegates the analysis to a generative artificial intelligence.

[0960] Input: Problem report data identified as an unknown event

[0961] Output: Data sent to the generative artificial intelligence for problem analysis.

[0962] Specific operation: The server sends the details of the problem report to the generative artificial intelligence. It generates a prompt message (e.g., "The conveyor belt has stopped. Error code 12345. Please tell me the cause and solution.") and sends it to the generative artificial intelligence model.

[0963] Step 6:

[0964] Generative artificial intelligence generates new knowledge and solutions.

[0965] Input: Prompt sent to a generative AI

[0966] Output: Generated knowledge and solutions

[0967] Specific operation: The generative artificial intelligence analyzes the prompt text and generates a cause analysis and solution (e.g., "Readjust the belt") in text format.

[0968] Step 7:

[0969] The server returns the generated knowledge to the user and adds it to the knowledge base.

[0970] Input: Knowledge and solutions generated by generative artificial intelligence.

[0971] Output: Solution messages sent to users and updated knowledge base

[0972] Specific operation: The server returns the generated knowledge to the user and saves it as new knowledge in the knowledge base. The user receives a message that includes specific instructions on how to proceed (e.g., "Readjust the belt").

[0973] Step 8:

[0974] We will address future issues based on the updated knowledge base.

[0975] Input: Updated Knowledge Base

[0976] Output: Prompt response to future problem reports

[0977] Specific action: By updating the knowledge base, the server can quickly provide solutions when similar problems recur. For example, the next time the same error code is reported, the solution "re-adjust the belt" will be immediately suggested.

[0978] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0979] This invention is a system for improving efficiency in server maintenance, enabling rapid response to unknown events and knowledge accumulation. Furthermore, by combining it with an emotion engine that recognizes user emotions, it provides more appropriate responses.

[0980] Basic configuration

[0981] This system includes a server that receives reports from users via their terminals, a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge, and an emotion engine that recognizes the user's emotions.

[0982] User reports

[0983] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This sends the problem report to the server.

[0984] Reception and determination by the server

[0985] The server receives a problem report sent from a terminal and first determines whether it is a known issue. If it is a known issue, the server searches its existing knowledge base for a solution and responds to the user with a suggested solution.

[0986] Handling known events

[0987] If the issue is known, the server will provide a solution based on its knowledge base. For example, if "Error Code 500" is reported, the server will respond to the user with the solution "Restart the server." The solution will be displayed on the terminal screen.

[0988] Handling unknown events

[0989] If the phenomenon is unknown, the server delegates the analysis of the problem to a generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[0990] Generative artificial intelligence analyzes received problem reports and generates new knowledge and solutions. For example, it might generate solutions such as "Check the configuration file and configure it appropriately." The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[0991] User emotion recognition

[0992] When the server receives a problem report, it uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's text input and voice data to determine whether the user is feeling anxiety, anger, stress, etc.

[0993] Responding according to emotions

[0994] After the emotion engine recognizes the user's emotions, the server selects an appropriate response. For example, if the user is experiencing high levels of stress, the server will respond quickly, providing detailed instructions on the steps necessary to resolve the problem. It may also respond with a gentle, encouraging message.

[0995] Updating and reusing the knowledge base

[0996] New knowledge generated by generative artificial intelligence is stored in the knowledge base. Furthermore, user emotion data recognized by the emotion engine is also stored in the knowledge base, making it possible to provide countermeasures that take past emotion data into account when future problems are reported.

[0997] This allows the system to respond quickly and appropriately the next time a similar problem occurs. Furthermore, if the same problem recurs, a rapid response based on the knowledge base is possible, reducing the time and cost of system maintenance. The emotion recognition function improves the user experience and increases user satisfaction.

[0998] Specific example

[0999] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives this problem. The server determines if this problem already exists in the knowledge base. If it is not a known issue, it delegates the analysis to a generative artificial intelligence system, which generates a solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user through the server and added to the knowledge base. Furthermore, an emotion engine recognizes the user's emotions and generates a message to alleviate the user's stress.

[1000] This invention automates the process from problem reporting to solution provision, continuously strengthening the knowledge base and improving the overall maintainability of the system. Incorporating emotion recognition enhances the user experience, enabling the delivery of more satisfying services. This system not only facilitates rapid problem resolution but also enables knowledge accumulation and reuse, resulting in long-term operational efficiency.

[1001] The above describes embodiments for carrying out the present invention.

[1002] The following describes the processing flow.

[1003] Step 1:

[1004] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time of occurrence, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This action sends the problem report to the server.

[1005] Step 2:

[1006] The server receives a problem report. The received problem report is stored in the internal database.

[1007] Step 3:

[1008] The server uses an emotion engine to analyze the user's emotions from the problem report. The emotion engine uses text analysis and speech analysis to determine the user's emotional state (e.g., anxiety, anger, stress).

[1009] Step 4:

[1010] The server compares the problem report against a list of known events to determine whether or not it is a known event. This determination is made by comparing the data in the knowledge base with the content of the problem report.

[1011] Step 5:

[1012] If the server determines that the reported problem is a known issue, it searches its knowledge base for a solution and provides it to the user. For example, if "Error Code 500" is reported, a solution such as "Restart the server" will be displayed on the terminal.

[1013] Step 6:

[1014] If the server determines that the reported problem is an unknown phenomenon, it delegates the analysis of the problem to a generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[1015] Step 7:

[1016] Generative artificial intelligence receives a problem report and begins analysis. The AI ​​uses its machine learning models and datasets to analyze the problem and generate new knowledge and solutions. For example, it might generate specific solutions such as "check the configuration file and configure it appropriately."

[1017] Step 8:

[1018] The generative artificial intelligence generates knowledge, which is then sent back to the server. The server then provides that knowledge to the user. The user can then view the newly generated solution on their device screen.

[1019] Step 9:

[1020] The server adds the generated knowledge to the knowledge base. The knowledge base is managed as a database and used for addressing future issues. In addition, user sentiment data analyzed by the sentiment engine is also stored in the knowledge base.

[1021] Step 10:

[1022] In the event of a similar problem occurring in the future, the server will promptly provide solutions based on its knowledge base. It can also provide solutions that take past emotional data into account; for example, if a user is experiencing high levels of stress, it will prioritize encouraging messages and a quick response.

[1023] The above describes the specific processing flow of the system based on the present invention.

[1024] (Example 2)

[1025] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1026] In recent years, with the increasing complexity of information systems, the number of users reporting problems has been rising. While known issues can be addressed quickly, responding appropriately to unknown issues is difficult. Furthermore, users' emotional states influence the speed of problem resolution and their satisfaction, but conventional systems cannot analyze emotions or respond flexibly based on them. Therefore, there is a need for a system that can quickly address unknown problems while simultaneously providing appropriate responses that respond to users' emotions.

[1027] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to report a problem through an information processing device, means for receiving the problem report and determining whether it is a known phenomenon, means for responding with a solution if it is a known phenomenon, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown phenomenon, means for adding the generated knowledge to a knowledge database, means for recognizing the user's emotions using an emotion analysis engine, and means for adjusting the solution based on the recognized emotions. This enables a quick and appropriate response even to unknown problems, and also enables a flexible response that responds to the user's emotions.

[1028] 1. An "information processing device" is a device such as a computer or smartphone that users use to input, process, and output data.

[1029] 2. "Problem reporting" refers to the act of a user sending information to the system to inform it of the details of a malfunction or problem that has occurred.

[1030] 3. A "known phenomenon" is a problem that has already been recorded in the knowledge base and for which countermeasures have been clearly determined.

[1031] 4. An "unknown phenomenon" is a problem that has not been recorded in the past and for which countermeasures have not been established.

[1032] 5. "Generative artificial intelligence" is artificial intelligence that has the ability to analyze input data and generate new knowledge and solutions.

[1033] 6. "New knowledge" refers to solutions and information for unknown phenomena that are analyzed and generated by generative artificial intelligence.

[1034] 7. A "knowledge database" is a database used to accumulate and manage solutions to known phenomena and new knowledge.

[1035] 8. An "emotion analysis engine" is a system that analyzes user input data and identifies the user's emotional state.

[1036] 9. "Solution" refers to the solutions or procedures that the system provides in response to a problem report.

[1037] 10. "Adjusting coping strategies based on recognized emotions" means changing the content and manner of coping strategies according to the user's emotional state as recognized by the emotion analysis engine.

[1038] This invention relates to a problem reporting system using an information processing device, which responds quickly and appropriately to problem reports from users. Furthermore, by combining it with an emotion analysis engine, it achieves flexible responses that respond to the user's emotions. The following describes in detail specific embodiments for carrying out this invention.

[1039] Basic configuration

[1040] This system includes a server that receives user reports via an information processing device, a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge, and an emotion analysis engine that recognizes user emotions. The detailed functions of each element are described below.

[1041] User reports

[1042] Users report problems using information processing devices (e.g., personal computers, smartphones) via a dedicated application or web interface. Users enter detailed information such as error messages, the date and time the problem occurred, and system behavior, and then press the submit button to report the problem.

[1043] Reception and determination by the server

[1044] The server receives problem reports submitted by users. The server consults its knowledge database to determine whether the reported problem is a known issue. If it is a known issue, the server searches the knowledge database for a solution and responds to the user with the appropriate action. For example, if "error code 500" is reported, the server will respond to the user with the solution "restart the system."

[1045] Processing known phenomena

[1046] In the case of a known issue, the server provides a solution based on its knowledge database. The solution is displayed on the user's information processing device screen. For example, if "Error Code 500" is reported, the server will suggest "Restart the server" as the solution.

[1047] Processing unknown phenomena

[1048] If the phenomenon is unknown, the server delegates the analysis of the problem to a generative artificial intelligence (e.g., GPT-4). The server sends the content of the problem report to the generative AI. The generative AI analyzes the received problem report and generates new knowledge and solutions. For example, it might generate a solution such as "Check the configuration file and configure it appropriately." The generated knowledge is returned to the user through the server and added to the knowledge database.

[1049] User emotion recognition by emotion analysis engine

[1050] When the server receives a problem report, it uses an emotion analysis engine (e.g., IBM Watson) to analyze the user's emotions. The emotion analysis engine analyzes the user's input data to determine whether the user is feeling anxiety, anger, stress, etc.

[1051] Responding according to emotions

[1052] After the emotion analysis engine recognizes the user's emotions, the server adjusts its response based on the recognized emotions. For example, if the user is experiencing high levels of stress, the server will respond quickly and provide detailed instructions on the steps necessary to resolve the problem. It will also respond with encouraging messages to help alleviate the user's feelings.

[1053] Updating and reusing the knowledge database

[1054] New knowledge generated by generative artificial intelligence is stored in a knowledge database. Furthermore, user emotion data recognized by the emotion analysis engine is also stored in the knowledge database. This enables quick and appropriate responses when similar problems occur in the future. It also allows for the provision of countermeasures that take past emotion data into account when reporting problems in the future. As a result, the system not only enables rapid problem solving but also facilitates the accumulation and reuse of knowledge, leading to long-term operational efficiency.

[1055] Specific example

[1056] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives the problem and determines if it already exists in the knowledge database. If it's not a known issue, it delegates the analysis to generative artificial intelligence, which generates a solution such as "check the configuration file and configure it appropriately." This generated solution is then returned to the user via the server and added to the knowledge database. Furthermore, an emotion analysis engine recognizes the user's emotions and generates a message to alleviate their stress.

[1057] Example of a prompt

[1058] "Please generate an appropriate solution for the issue where 'the application crashes when trying to save a file.' Since this is causing significant stress to the user, please also include a reassuring message."

[1059] This invention automates the process from problem reporting to solution provision, and the knowledge database is continuously strengthened, improving the overall maintainability of the system. By incorporating emotion recognition functionality, the user experience is enhanced, enabling the provision of more satisfying services. This system not only enables rapid problem resolution but also facilitates the accumulation and reuse of knowledge, resulting in long-term operational efficiency.

[1060] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1061] Step 1: User reports a problem.

[1062] Input: The user uses an information processing device (e.g., personal computer, smartphone) to access a dedicated application or web interface and enter details of the problem (e.g., error message, date and time of occurrence, system behavior, etc.).

[1063] Specific operation: The user enters the necessary information into the problem report form and presses the "Submit" button to report the problem.

[1064] Output: The problem report is sent to the server.

[1065] Step 2: Server receives report and determines known / unknown information.

[1066] Input: The server receives problem reports submitted by users.

[1067] Specific operation: The server analyzes the received problem report and accesses the knowledge database to determine whether or not it is a known phenomenon.

[1068] Output: If the issue is known, retrieve a solution from the knowledge database; if it is an unknown issue, proceed to the next step.

[1069] Step 3: Server response to known issues

[1070] Input: The server retrieves solutions for known issues from the knowledge database.

[1071] Specific operation: The server sends the solution to the user's information processing device and displays it on the screen.

[1072] Output: The user is provided with specific countermeasures (e.g., "Restart the system" for error code 500).

[1073] Step 4: Delegation of analysis of unknown phenomena to the server

[1074] Input: The server determines that this is not a known phenomenon and delegates the analysis to a generative AI model (e.g., GPT-4).

[1075] Specific operation: The server sends the details of the problem report to the generating AI model.

[1076] Output: Details of the problem report are sent to the generating AI model.

[1077] Step 5: Generating new knowledge using a generative AI model

[1078] Input: The generated AI model receives problem reports sent from the server.

[1079] Specific operation: The generative AI model analyzes the problem and generates new knowledge and solutions (e.g., "Check the configuration file and configure it appropriately").

[1080] Output: The generated solution is sent back to the server.

[1081] Step 6: Responding with new knowledge and managing stress

[1082] Input: The server receives the solution returned from the generated AI model.

[1083] Specific operation: The server responds to the user with a solution and simultaneously analyzes the user's emotions using an emotion analysis engine (e.g., IBM Watson). If stress is detected, it generates detailed instructions and an encouraging message.

[1084] Output: The user is provided with concrete solutions and emotionally resonant messages.

[1085] Step 7: Update the knowledge database by the server.

[1086] Input: The server receives new knowledge generated by the generation AI model and data from the emotion analysis engine.

[1087] Specific operation: The server adds new knowledge to the knowledge database and stores sentiment data along with it.

[1088] Output: The knowledge database will be updated, and problem handling and emotional support will be enhanced for future issues.

[1089] The above describes the processing steps of the program for this system.

[1090] (Application Example 2)

[1091] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1092] Existing problem-solving systems were time-consuming to respond to unfamiliar situations, making it difficult to provide appropriate solutions quickly. Furthermore, they failed to consider user emotions, hindering improvements in the user experience. As a result, there was a lack of means to alleviate user stress and dissatisfaction.

[1093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1094] In this invention, the server includes means for a user to report a problem via a terminal, means for receiving the problem report and determining whether it is a known event, means for responding with a method of action if it is a known event, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown event, means for adding the generated knowledge to a knowledge base, means for sentiment analysis to recognize the user's emotions, and means for providing countermeasures according to the recognized emotions. This enables rapid response to unknown events and effective accumulation of knowledge, and furthermore, by taking user emotions into consideration, it is possible to improve the user experience and reduce dissatisfaction.

[1095] A "user" refers to a person who uses the system or device to report a problem and receive a solution.

[1096] A "device" refers to a device used by a user to report a problem, and includes smartphones, personal computers, and other similar devices.

[1097] "Problem reporting" refers to the act of a user informing the system of any malfunctions or errors that have occurred, as well as the content of that information.

[1098] A "server" refers to a computer system that receives problem reports, analyzes them, and generates solutions.

[1099] "Known events" refer to events where similar problems have occurred in the past, and for which solutions have already been accumulated in the knowledge base.

[1100] An "unknown event" refers to an event that has never occurred before, or for which no solution exists in the knowledge base.

[1101] "Generative artificial intelligence" refers to artificial intelligence technology used to generate new solutions and knowledge in response to unknown phenomena.

[1102] "Knowledge" refers to information, data, and solutions that are useful for solving problems.

[1103] A "knowledge base" refers to a database where accumulated knowledge is stored and can be searched and referenced.

[1104] "Emotional analysis means" refers to technologies and devices used to analyze and recognize the emotions of users.

[1105] "Countermeasures" refer to the specific means or methods provided to solve a problem.

[1106] The system for implementing this invention consists of the following elements. First, a terminal is required for users to report problems. The terminal includes smartphones and personal computers, and has a dedicated application installed. Using this application, users can input details of the problem and send them to the server.

[1107] Upon receiving this problem report, the server first determines whether the reported issue is a known problem. If it is a known issue, the server searches its knowledge base for a solution and responds to the user.

[1108] If an unknown phenomenon occurs, the server delegates the analysis of the problem to a generative artificial intelligence (AI). The generative AI analyzes the received problem report and generates new knowledge and solutions. This new knowledge is returned to the user through the server and is also automatically added to the knowledge base.

[1109] Furthermore, the server recognizes the user's emotions using emotion analysis tools. These tools utilize an emotion analysis model based on the Hugging Face transformers library. This allows the server to analyze the user's emotions, such as stress and frustration, and provide appropriate responses based on the recognized emotions. For example, if the user is experiencing high levels of stress, the server will respond quickly, providing detailed instructions on the steps necessary to resolve the problem. It will also respond with a gentle, encouraging message.

[1110] Hardware and software to be used

[1111] Hardware:

[1112] Server: Cloud servers such as AWS and Google Cloud

[1113] Devices: Smartphones and computers (iOS, Android, Windows, Mac, etc.)

[1114] software:

[1115] Flask: A web framework written in Python.

[1116] transformers:Hugging Face is a library for emotion analysis models.

[1117] Specific example

[1118] A user reports a problem, such as "the vehicle's autonomous driving function has stopped working." Using the application on their device, they enter details of the problem (e.g., "fault_code_001") and a message describing their concern (e.g., "The autonomous driving function suddenly stopped working. I'm very worried."). The problem report is sent to the server, which receives the problem.

[1119] The server determines from the problem report whether it is a known issue. If it is a known issue, it searches the knowledge base for an appropriate solution and responds. However, in this case, it is determined to be an unknown issue, so generative artificial intelligence analyzes the problem and generates a new solution (for example, "check the configuration file and make the appropriate settings").

[1120] Furthermore, sentiment analysis tools are used to analyze the user's messages and recognize if the user is experiencing stress or worry. In response, encouraging messages such as, "Don't worry, we'll let you know the solution soon," are also sent back.

[1121] Example of a prompt

[1122] The following are specific examples of prompt statements.

[1123] Problem: fault_code_001

[1124] Message: The autonomous driving function suddenly stopped working. I am very worried.

[1125] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1126] Step 1:

[1127] Users report problems using their devices.

[1128] The user opens a dedicated application on their device, enters details of the problem (error message, date and time of occurrence, circumstances, etc.), and submits a report.

[1129] Input: Problem details (text data)

[1130] Output: Problem report data sent to the server

[1131] Step 2:

[1132] The server receives a problem report.

[1133] The server analyzes the problem report data sent from the terminal and retrieves the details of the problem.

[1134] Input: Problem report data

[1135] Output: Analyzed problem content

[1136] Step 3:

[1137] The server determines whether the problem is known.

[1138] The server accesses the knowledge base to check whether the reported issue is a known issue. If it is a known issue, it retrieves the appropriate solution from the knowledge base.

[1139] Input: Analyzed problem description, knowledge base

[1140] Output: Countermeasures (only for known issues)

[1141] Step 4:

[1142] The server will respond with a solution (if it's a known issue).

[1143] The server returns a solution retrieved from the knowledge base to the user. This solution is displayed on the terminal screen.

[1144] Input: Countermeasures

[1145] Output: Reply to the user

[1146] Step 5:

[1147] The server delegates the problem to a generative artificial intelligence (in the case of an unknown event).

[1148] If the issue is not known, the server delegates the analysis of the problem to a generative artificial intelligence.

[1149] Input: Analyzed problem content

[1150] Output: Problem data for generative artificial intelligence

[1151] Step 6:

[1152] Generative artificial intelligence analyzes the problem and generates new knowledge.

[1153] Generative artificial intelligence analyzes problem reports and generates new solutions.

[1154] Input: Problem data

[1155] Output: New knowledge (solution)

[1156] Step 7:

[1157] The server adds the generated knowledge to the knowledge base.

[1158] The newly generated knowledge is automatically added to the knowledge base.

[1159] Input: New knowledge

[1160] Output: Updated Knowledge Base

[1161] Step 8:

[1162] The server recognizes the user's emotions using emotion analysis tools.

[1163] The server inputs the user's text message into an emotion analysis model and analyzes their emotional state.

[1164] Input: User's text message

[1165] Output: Emotional state data

[1166] Step 9:

[1167] The server provides countermeasures based on the emotions it recognizes.

[1168] Based on the sentiment analysis results, the system sends users appropriate responses or encouraging messages.

[1169] Input: Emotional state data, new solution

[1170] Output: Emotionally sensitive responses and messages

[1171] Step 10:

[1172] The server returns the response result to the user.

[1173] Ultimately, the server responds to the user with the generated solution and a message tailored to their emotions, displaying it on their device.

[1174] Input: Emotionally sensitive responses and solutions

[1175] Output: Information returned to the terminal

[1176] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1177] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1178] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1179] [Fourth Embodiment]

[1180] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1181] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1182] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1183] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1184] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1185] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1186] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1187] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1188] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1189] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1190] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1191] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1192] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1193] This invention is a system for improving efficiency in server maintenance, enabling rapid response to unknown events and knowledge accumulation. Specific embodiments of this system are described below.

[1194] Basic configuration

[1195] This system includes a server that receives reports from users via their terminals, and a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge.

[1196] User reports

[1197] Users report problems to the system using their devices. Specifically, users report problems by entering details of the problem (e.g., error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then pressing the submit button.

[1198] Reception and determination by the server

[1199] The server receives a problem report sent from a terminal and first determines whether it is a known issue. If it is a known issue, the server searches its existing knowledge base for a solution and responds to the user with a suggested solution.

[1200] Handling known events

[1201] If the issue is known, the server will provide a solution based on its knowledge base. For example, if "Error Code 500" is reported, the server will respond to the user with a solution such as "Restart the server."

[1202] Handling unknown events

[1203] If the issue is unknown, the server delegates the problem analysis to a generative artificial intelligence (AI). The AI ​​analyzes the received problem report and generates new knowledge and solutions. The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[1204] Updating and reusing the knowledge base

[1205] New knowledge generated by generative artificial intelligence is stored in a knowledge base. The knowledge base is updated, enabling quick solutions to be provided if similar problems occur again. This allows for rapid response when the same problem recurs, reducing the time and cost of system maintenance.

[1206] Specific example

[1207] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives this problem. The server determines whether this problem already exists in the knowledge base. If it is not a known issue, it delegates the analysis to a generative artificial intelligence system, which generates a new solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user through the server and added to the knowledge base.

[1208] This invention automates the process from problem reporting to solution provision, and the knowledge base is continuously strengthened, thereby improving the overall maintainability of the system. This system enables not only rapid problem resolution but also knowledge accumulation and reuse, resulting in long-term operational efficiency.

[1209] The above describes embodiments for carrying out the present invention.

[1210] The following describes the processing flow.

[1211] Step 1:

[1212] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This sends the problem report to the server.

[1213] Step 2:

[1214] The server receives a problem report. The received problem report is stored in an internal database, and then processing begins to determine whether or not it is a known issue.

[1215] Step 3:

[1216] The server compares the problem report against the known issues list. The known issues list contains information about past problems and their solutions. If the problem report is found in the known issues list, the server searches for the corresponding solution.

[1217] Step 4:

[1218] If the server determines that the issue is known, it will respond to the user with a suggested solution. For example, if "Error Code 500" is reported, the server will respond to the user with the solution "Restart the server." The solution will be displayed on the terminal screen.

[1219] Step 5:

[1220] If the server determines that the reported problem does not exist in the list of known events, it delegates the analysis of the problem to the generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[1221] Step 6:

[1222] The generative artificial intelligence receives a problem report and begins analysis. The generative AI uses machine learning algorithms to analyze the problem and generate new knowledge and solutions. For example, it might generate a solution such as "check the configuration file and configure it appropriately."

[1223] Step 7:

[1224] The generative artificial intelligence generates knowledge and sends it back to the server. The server receives the generated knowledge and responds to the user. The user can then view the solution on their device screen.

[1225] Step 8:

[1226] The server adds the generated knowledge to the knowledge base. The knowledge base is managed as a database, and the addition of new knowledge allows for faster problem resolution in the future.

[1227] The above is the specific processing flow of the program.

[1228] (Example 1)

[1229] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1230] In conventional systems, it was difficult to respond quickly and appropriately to user-reported problems, often resulting in long resolution times. Furthermore, when similar problems recurred, past solutions were not efficiently reused, leading to decreased maintenance efficiency. Additionally, when analysis and solution generation for unknown events were performed manually, knowledge base updates were delayed, reducing the overall operational efficiency of the system.

[1231] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1232] In this invention, the server includes means for a user to report a problem via a terminal, means for receiving the problem report and determining whether it is a known event, means for responding with a method of action if it is a known event, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown event, means for generating new knowledge and solutions from the received problem report using the generative artificial intelligence and responding to the user, and means for adding the generated knowledge to the knowledge base. This enables a quick and appropriate response to problems reported by users, promotes continuous updating and reuse of the knowledge base, and improves the efficiency of maintenance work for the entire system.

[1233] A "user" is the operator of a terminal that uses the system to report a problem.

[1234] A "terminal" refers to a device, such as a PC or smartphone, used to report problems to the system.

[1235] A "server" is a central management device that receives problem reports, determines whether or not they are known events, and delegates the analysis to a generative artificial intelligence.

[1236] A "problem" refers to a system malfunction reported by a user, such as a system error message, abnormal behavior, or failure.

[1237] A "report" is detailed information about a problem that a user sends to the system via their device.

[1238] "Known events" are problems that have occurred in the past and are registered in the knowledge base.

[1239] An "unknown phenomenon" refers to a new problem that does not exist in the knowledge base.

[1240] "Judgment" is the process of checking whether a received problem report is a known issue or not.

[1241] A "response" is the act of a server notifying a user of how to respond or a solution.

[1242] "Generative artificial intelligence" refers to an AI model that analyzes received problem reports to generate new knowledge and solutions.

[1243] "Analysis" is the process of thoroughly examining the contents of a problem report to find the cause and solution.

[1244] "Knowledge" refers to the knowledge and data generated by generative artificial intelligence for problem-solving.

[1245] A "knowledge base" is a database system that stores existing and newly generated knowledge.

[1246] A "prompt statement" is an input statement used when requesting a generative artificial intelligence to analyze a problem.

[1247] This invention provides a system that improves the efficiency of server maintenance and enables rapid response to unknown events and the accumulation of knowledge. The system includes a server that receives reports from users via a terminal, and a generative AI model that analyzes unknown events and generates new knowledge.

[1248] Basic configuration

[1249] This system includes a dedicated application or web interface for users to report problems via their devices, a server that receives these reports and determines whether they are known issues, and a generative AI model. The hardware used includes PCs and smartphones as devices, while the server utilizes virtual machines or physical servers in the cloud. The software includes web servers such as Apache and Nginx, database management systems such as MySQL and PostgreSQL, and generative AI models such as OpenAI GPT-3.

[1250] User reports

[1251] Users report problems to the system using their devices. Specifically, users report problems by entering details of the problem (e.g., error message, system behavior, date and time of occurrence, etc.) through a dedicated application on their device or a web interface, and then pressing the submit button. For example, a user might report that "the application crashes when I try to save a file."

[1252] Reception and determination by the server

[1253] The server receives problem reports sent from terminals. The server first determines whether the problem is a known issue by cross-referencing it with the knowledge base. The knowledge base stores past problems and their solutions.

[1254] Handling known events

[1255] If the issue is known, the server searches its knowledge base for a solution and responds to the user. For example, if "Error Code 500" is reported, the server will respond with a solution such as "Restart the server." The database management system used in this case is MySQL or PostgreSQL.

[1256] Handling unknown events

[1257] If an unknown phenomenon occurs, the server delegates the problem analysis to a generative AI model. This generative AI model, built using OpenAI GPT-3 and other technologies, analyzes the received problem report and generates new knowledge and solutions. The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[1258] Updating and reusing the knowledge base

[1259] New knowledge generated by the generative AI model is stored in a knowledge base. The knowledge base is updated, enabling rapid response to similar problems in the future. This reduces the time and cost associated with system maintenance.

[1260] Specific example

[1261] For example, if a user reports a problem where "the application crashes when trying to save a file," the server receives the issue and determines if it already exists in the knowledge base. If it's not a known issue, it delegates the analysis to a generative AI model, which generates a new solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user via the server and added to the knowledge base.

[1262] Example of a prompt

[1263] Examples of specific prompt messages:

[1264] "User-reported issue: The application crashes when attempting to save a file. Error message: 'Error 404: File not found', Date and time of occurrence: October 1, 2023, System behavior: The application immediately terminates. Please provide a solution."

[1265] This invention automates the process from problem reporting to solution provision, and the knowledge base is continuously strengthened, thereby improving the overall maintainability of the system. This system enables not only rapid problem resolution but also knowledge accumulation and reuse, resulting in long-term operational efficiency.

[1266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1267] Step 1:

[1268] The user accesses the system from their terminal using a dedicated application or web interface. The input at this stage consists of details of the problem the user is reporting (e.g., error message, system behavior, date and time of occurrence). The output is the transmission of the entered problem details to the server. Specifically, the user fills out a form and clicks a submit button.

[1269] Step 2:

[1270] The server receives problem reports sent from terminals. Specifically, it receives problem reports as HTTP requests via a web server (e.g., Apache, Nginx) and stores their contents in a database. The input is the details of the problem report received from the user, and the output is the problem report information stored in the database.

[1271] Step 3:

[1272] The server determines whether the received problem report is a known issue or not. Specifically, this involves searching the knowledge base in the database (e.g., MySQL, PostgreSQL) to see if it matches any past issues. The input is the problem report information stored in the database, and the output is the determination result of whether the problem is known or unknown. Based on this determination result, the next action is decided.

[1273] Step 4:

[1274] If the server determines that the problem is a known issue, it searches its knowledge base for a solution and responds to the user. The input is the solution information retrieved from the knowledge base, and the output is the solution returned to the user. Specifically, the server executes an SQL query to search for a solution and sends it to the user as an HTTP response.

[1275] Step 5:

[1276] If the server determines that a problem is an unknown phenomenon, it delegates the analysis of the problem to a generative AI model (e.g., OpenAI GPT-3). The input is detailed information about the unknown problem report, and the output is the solution and knowledge generated by the generative AI model. Specifically, the server sends prompt messages to the generative AI model and obtains the analysis results.

[1277] Step 6:

[1278] The generative AI model analyzes the received problem report and generates new knowledge and solutions. The input is the detailed information of the problem report as a prompt, and the output is the analyzed knowledge and solutions. Specifically, the generative AI model analyzes the prompt, performs inference, and generates a new solution.

[1279] Step 7:

[1280] The server returns the generated solution to the user. The input is the solution obtained from the generating AI model, and the output is the response message to the user. Specifically, the server sends the solution to the user as an HTTP response.

[1281] Step 8:

[1282] The server automatically adds the knowledge generated by the AI ​​model to the knowledge base. The input is the newly generated knowledge, and the output is the updated knowledge base. Specifically, the server executes an SQL query to add the new knowledge to the database.

[1283] The above explains the system's program flow, broken down into specific processing steps.

[1284] (Application Example 1)

[1285] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1286] In logistics centers, it is crucial to resolve equipment and system errors quickly and effectively. However, existing systems often resulted in delays in responding to errors, frequently halting operations. Furthermore, the inability to quickly find appropriate countermeasures for unknown errors prolonged response times. This led to decreased operational efficiency at logistics centers, increased costs, and delays in delivery.

[1287] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1288] In this invention, the server includes means for users to report problems via a terminal, means for receiving problem reports and determining whether they are known events, means for responding with a method of action if they are known events, means for delegating analysis to a generative artificial intelligence and generating new knowledge if they are unknown events, means for adding the generated knowledge to a knowledge base, and means for workers to report problems using smart devices when equipment or system errors occur in a logistics center. This makes it possible to provide rapid countermeasures when errors occur, generate new knowledge for unknown errors to expedite responses, and improve the operational efficiency of the logistics center.

[1289] "Users" refers to individuals or workers who report problems when equipment or system errors occur at a logistics center.

[1290] "Terminal" refers to a smart device or computer used by a user to report a problem.

[1291] "Problem reporting" refers to the act of a user sending details of an error or malfunction via their device, as well as the content of that report.

[1292] "Known events" refer to problems or errors that already exist in the knowledge base and for which countermeasures have been established in the past.

[1293] An "unknown phenomenon" refers to a problem or error that does not exist in the knowledge base and requires new analysis and countermeasures.

[1294] "Generative artificial intelligence" refers to an artificial intelligence system that analyzes unknown phenomena and generates new knowledge and solutions.

[1295] A "knowledge base" refers to a database that stores known events and their corresponding countermeasures.

[1296] "Smart devices" refer to electronic devices such as smartphones and tablets that workers use to report problems.

[1297] "Analysis" refers to the process by which a generative artificial intelligence receives a problem report, examines the cause and solution of the event, and generates new knowledge.

[1298] A "logistics center" refers to a facility that manages and distributes goods and supplies.

[1299] This invention provides a system for quickly and effectively resolving errors in equipment and systems at a logistics center. The system includes user terminals, a server, generative artificial intelligence, and a knowledge base.

[1300] Basic configuration

[1301] User problem reports

[1302] Users report errors and problems using their devices. These reports are made using smart devices such as smartphones and tablets, and details of the error (text) and corresponding images are sent through a dedicated application.

[1303] Reception and determination by the server

[1304] The server receives problem reports submitted by users. First, it determines whether the received problem is a known issue or not. If it is a known issue, it searches the knowledge base for a solution and responds to the user. For example, if a stoppage of an electric conveyor is reported, the knowledge base will contain information recommending "restarting".

[1305] Responding to Unknown Events

[1306] If an unknown event occurs, the server delegates the analysis to a generative artificial intelligence (such as a GPT-4 model). The generative AI analyzes the received problem report and generates new knowledge and solutions. This generated knowledge is provided to users through the server and is also automatically added to the knowledge base.

[1307] Updating and reusing the knowledge base

[1308] New knowledge generated by generative artificial intelligence is stored in a knowledge base. This knowledge base is continuously updated, enabling rapid responses to future problems.

[1309] Specific example

[1310] For example, suppose a worker at a logistics center discovers a conveyor belt has stopped and reports the problem using a smart device, stating, "The conveyor belt has stopped. Error code 12345." This problem report is received by a server, which first determines whether it is a known issue. If it is an unknown issue, a generative artificial intelligence generates a new solution, such as "Readjust the belt." This solution is then sent back to the worker via the server and simultaneously added to the knowledge base.

[1311] Hardware and software to be used

[1312] Hardware: Smart devices (smartphones, tablets), servers

[1313] Software: Dedicated problem reporting application, generative artificial intelligence (GPT-4, etc.), knowledge base management system

[1314] Data processing and data calculation

[1315] 1. Data entry: Users enter details of the problem and images, and send them to the server.

[1316] 2. Data reception and determination: The server receives the problem report and determines whether it is known or unknown.

[1317] 3. Use of Generative Artificial Intelligence: In the case of unknown events, generative artificial intelligence analyzes the problem and generates new knowledge.

[1318] 4. Knowledge Base Update: Generated knowledge is automatically added to the knowledge base.

[1319] Example of a prompt

[1320] A possible prompt message when a worker reports a conveyor belt stoppage might be: "The conveyor belt has stopped. Error code 12345. Please tell me the cause and solution." This prompt is sent to a generative artificial intelligence system to serve as a reference for generating new knowledge.

[1321] The above describes specific embodiments for carrying out the present invention. This invention is expected to enable rapid problem solving in logistics centers and improve operational efficiency.

[1322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1323] Step 1:

[1324] Users report problems using smart devices.

[1325] Input: Error details (text) and image

[1326] Output: Problem report data sent from the terminal

[1327] Specific operation: The user launches a dedicated application, enters details of the problem such as "The conveyor belt has stopped. Error code 12345," and adds images as needed. Then, by pressing the submit button, this data is sent to the server.

[1328] Step 2:

[1329] The server receives a problem report.

[1330] Input: Problem report data sent by the user from their device.

[1331] Output: Received problem report data is stored on the server.

[1332] Specific operation: The server stores the received data in a parseable format. For example, text data is stored as a string in the database, and image data is stored in the file system.

[1333] Step 3:

[1334] The server determines whether the problem report it receives is a known issue.

[1335] Input: Received problem report data

[1336] Output: Determination result of whether it is a known or unknown event.

[1337] Specific operation: The server compares the content of the problem report with the knowledge base and checks if it contains known error codes or keywords. If there is a match, it is determined to be a known issue.

[1338] Step 4:

[1339] If the issue is known, the server will search its knowledge base for a solution and respond to the user.

[1340] Input: Problem report data identified as a known issue

[1341] Output: Reply message including the suggested course of action

[1342] Specific actions: Search the knowledge base for relevant solutions (e.g., "Restart the conveyor belt") and send that information to the user as a text message.

[1343] Step 5:

[1344] If the phenomenon is unknown, the server delegates the analysis to a generative artificial intelligence.

[1345] Input: Problem report data identified as an unknown event

[1346] Output: Data sent to the generative artificial intelligence for problem analysis.

[1347] Specific operation: The server sends the details of the problem report to the generative artificial intelligence. It generates a prompt message (e.g., "The conveyor belt has stopped. Error code 12345. Please tell me the cause and solution.") and sends it to the generative artificial intelligence model.

[1348] Step 6:

[1349] Generative artificial intelligence generates new knowledge and solutions.

[1350] Input: Prompt sent to a generative AI

[1351] Output: Generated knowledge and solutions

[1352] Specific operation: The generative artificial intelligence analyzes the prompt text and generates a cause analysis and solution (e.g., "Readjust the belt") in text format.

[1353] Step 7:

[1354] The server returns the generated knowledge to the user and adds it to the knowledge base.

[1355] Input: Knowledge and solutions generated by generative artificial intelligence.

[1356] Output: Solution messages sent to users and updated knowledge base

[1357] Specific operation: The server returns the generated knowledge to the user and saves it as new knowledge in the knowledge base. The user receives a message that includes specific instructions on how to proceed (e.g., "Readjust the belt").

[1358] Step 8:

[1359] We will address future issues based on the updated knowledge base.

[1360] Input: Updated Knowledge Base

[1361] Output: Prompt response to future problem reports

[1362] Specific action: By updating the knowledge base, the server can quickly provide solutions when similar problems recur. For example, the next time the same error code is reported, the solution "re-adjust the belt" will be immediately suggested.

[1363] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1364] This invention is a system for improving efficiency in server maintenance, enabling rapid response to unknown events and knowledge accumulation. Furthermore, by combining it with an emotion engine that recognizes user emotions, it provides more appropriate responses.

[1365] Basic configuration

[1366] This system includes a server that receives reports from users via their terminals, a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge, and an emotion engine that recognizes the user's emotions.

[1367] User reports

[1368] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time it occurred, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This sends the problem report to the server.

[1369] Reception and determination by the server

[1370] The server receives a problem report sent from a terminal and first determines whether it is a known issue. If it is a known issue, the server searches its existing knowledge base for a solution and responds to the user with a suggested solution.

[1371] Handling known events

[1372] If the issue is known, the server will provide a solution based on its knowledge base. For example, if "Error Code 500" is reported, the server will respond to the user with the solution "Restart the server." The solution will be displayed on the terminal screen.

[1373] Handling unknown events

[1374] If the phenomenon is unknown, the server delegates the analysis of the problem to a generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[1375] Generative artificial intelligence analyzes received problem reports and generates new knowledge and solutions. For example, it might generate solutions such as "Check the configuration file and configure it appropriately." The generated knowledge is returned to the user via the server and automatically added to the knowledge base.

[1376] User emotion recognition

[1377] When the server receives a problem report, it uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's text input and voice data to determine whether the user is feeling anxiety, anger, stress, etc.

[1378] Responding according to emotions

[1379] After the emotion engine recognizes the user's emotions, the server selects an appropriate response. For example, if the user is experiencing high levels of stress, the server will respond quickly, providing detailed instructions on the steps necessary to resolve the problem. It may also respond with a gentle, encouraging message.

[1380] Updating and reusing the knowledge base

[1381] New knowledge generated by generative artificial intelligence is stored in the knowledge base. Furthermore, user emotion data recognized by the emotion engine is also stored in the knowledge base, making it possible to provide countermeasures that take past emotion data into account when future problems are reported.

[1382] This allows the system to respond quickly and appropriately the next time a similar problem occurs. Furthermore, if the same problem recurs, a rapid response based on the knowledge base is possible, reducing the time and cost of system maintenance. The emotion recognition function improves the user experience and increases user satisfaction.

[1383] Specific example

[1384] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives this problem. The server determines if this problem already exists in the knowledge base. If it is not a known issue, it delegates the analysis to a generative artificial intelligence system, which generates a solution such as "check the configuration file and configure it appropriately." This generated solution is returned to the user through the server and added to the knowledge base. Furthermore, an emotion engine recognizes the user's emotions and generates a message to alleviate the user's stress.

[1385] This invention automates the process from problem reporting to solution provision, continuously strengthening the knowledge base and improving the overall maintainability of the system. Incorporating emotion recognition enhances the user experience, enabling the delivery of more satisfying services. This system not only facilitates rapid problem resolution but also enables knowledge accumulation and reuse, resulting in long-term operational efficiency.

[1386] The above describes embodiments for carrying out the present invention.

[1387] The following describes the processing flow.

[1388] Step 1:

[1389] Users report problems to the system using their devices. Specifically, users enter details of the problem (error message, system behavior, date and time of occurrence, etc.) through a dedicated application on their device or a web interface, and then press the submit button. This action sends the problem report to the server.

[1390] Step 2:

[1391] The server receives a problem report. The received problem report is stored in the internal database.

[1392] Step 3:

[1393] The server uses an emotion engine to analyze the user's emotions from the problem report. The emotion engine uses text analysis and speech analysis to determine the user's emotional state (e.g., anxiety, anger, stress).

[1394] Step 4:

[1395] The server compares the problem report against a list of known events to determine whether or not it is a known event. This determination is made by comparing the data in the knowledge base with the content of the problem report.

[1396] Step 5:

[1397] If the server determines that the reported problem is a known issue, it searches its knowledge base for a solution and provides it to the user. For example, if "Error Code 500" is reported, a solution such as "Restart the server" will be displayed on the terminal.

[1398] Step 6:

[1399] If the server determines that the reported problem is an unknown phenomenon, it delegates the analysis of the problem to a generative artificial intelligence. The contents of the problem report are sent to the generative artificial intelligence.

[1400] Step 7:

[1401] Generative artificial intelligence receives a problem report and begins analysis. The AI ​​uses its machine learning models and datasets to analyze the problem and generate new knowledge and solutions. For example, it might generate specific solutions such as "check the configuration file and configure it appropriately."

[1402] Step 8:

[1403] The generative artificial intelligence generates knowledge, which is then sent back to the server. The server then provides that knowledge to the user. The user can then view the newly generated solution on their device screen.

[1404] Step 9:

[1405] The server adds the generated knowledge to the knowledge base. The knowledge base is managed as a database and used for addressing future issues. In addition, user sentiment data analyzed by the sentiment engine is also stored in the knowledge base.

[1406] Step 10:

[1407] In the event of a similar problem occurring in the future, the server will promptly provide solutions based on its knowledge base. It can also provide solutions that take past emotional data into account; for example, if a user is experiencing high levels of stress, it will prioritize encouraging messages and a quick response.

[1408] The above describes the specific processing flow of the system based on the present invention.

[1409] (Example 2)

[1410] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1411] In recent years, with the increasing complexity of information systems, the number of users reporting problems has been rising. While known issues can be addressed quickly, responding appropriately to unknown issues is difficult. Furthermore, users' emotional states influence the speed of problem resolution and their satisfaction, but conventional systems cannot analyze emotions or respond flexibly based on them. Therefore, there is a need for a system that can quickly address unknown problems while simultaneously providing appropriate responses that respond to users' emotions.

[1412] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to report a problem through an information processing device, means for receiving the problem report and determining whether it is a known phenomenon, means for responding with a solution if it is a known phenomenon, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown phenomenon, means for adding the generated knowledge to a knowledge database, means for recognizing the user's emotions using an emotion analysis engine, and means for adjusting the solution based on the recognized emotions. This enables a quick and appropriate response even to unknown problems, and also enables a flexible response that responds to the user's emotions.

[1413] 1. An "information processing device" is a device such as a computer or smartphone that users use to input, process, and output data.

[1414] 2. "Problem reporting" refers to the act of a user sending information to the system to inform it of the details of a malfunction or problem that has occurred.

[1415] 3. A "known phenomenon" is a problem that has already been recorded in the knowledge base and for which countermeasures have been clearly determined.

[1416] 4. An "unknown phenomenon" is a problem that has not been recorded in the past and for which countermeasures have not been established.

[1417] 5. "Generative artificial intelligence" is artificial intelligence that has the ability to analyze input data and generate new knowledge and solutions.

[1418] 6. "New knowledge" refers to solutions and information for unknown phenomena that are analyzed and generated by generative artificial intelligence.

[1419] 7. A "knowledge database" is a database used to accumulate and manage solutions to known phenomena and new knowledge.

[1420] 8. An "emotion analysis engine" is a system that analyzes user input data and identifies the user's emotional state.

[1421] 9. "Solution" refers to the solutions or procedures that the system provides in response to a problem report.

[1422] 10. "Adjusting coping strategies based on recognized emotions" means changing the content and manner of coping strategies according to the user's emotional state as recognized by the emotion analysis engine.

[1423] This invention relates to a problem reporting system using an information processing device, which responds quickly and appropriately to problem reports from users. Furthermore, by combining it with an emotion analysis engine, it achieves flexible responses that respond to the user's emotions. The following describes in detail specific embodiments for carrying out this invention.

[1424] Basic configuration

[1425] This system includes a server that receives user reports via an information processing device, a generative artificial intelligence that analyzes unknown phenomena and generates new knowledge, and an emotion analysis engine that recognizes user emotions. The detailed functions of each element are described below.

[1426] User reports

[1427] Users report problems using information processing devices (e.g., personal computers, smartphones) via a dedicated application or web interface. Users enter detailed information such as error messages, the date and time the problem occurred, and system behavior, and then press the submit button to report the problem.

[1428] Reception and determination by the server

[1429] The server receives problem reports submitted by users. The server consults its knowledge database to determine whether the reported problem is a known issue. If it is a known issue, the server searches the knowledge database for a solution and responds to the user with the appropriate action. For example, if "error code 500" is reported, the server will respond to the user with the solution "restart the system."

[1430] Processing known phenomena

[1431] In the case of a known issue, the server provides a solution based on its knowledge database. The solution is displayed on the user's information processing device screen. For example, if "Error Code 500" is reported, the server will suggest "Restart the server" as the solution.

[1432] Processing unknown phenomena

[1433] If the phenomenon is unknown, the server delegates the analysis of the problem to a generative artificial intelligence (e.g., GPT-4). The server sends the content of the problem report to the generative AI. The generative AI analyzes the received problem report and generates new knowledge and solutions. For example, it might generate a solution such as "Check the configuration file and configure it appropriately." The generated knowledge is returned to the user through the server and added to the knowledge database.

[1434] User emotion recognition by emotion analysis engine

[1435] When the server receives a problem report, it uses an emotion analysis engine (e.g., IBM Watson) to analyze the user's emotions. The emotion analysis engine analyzes the user's input data to determine whether the user is feeling anxiety, anger, stress, etc.

[1436] Responding according to emotions

[1437] After the emotion analysis engine recognizes the user's emotions, the server adjusts its response based on the recognized emotions. For example, if the user is experiencing high levels of stress, the server will respond quickly and provide detailed instructions on the steps necessary to resolve the problem. It will also respond with encouraging messages to help alleviate the user's feelings.

[1438] Updating and reusing the knowledge database

[1439] New knowledge generated by generative artificial intelligence is stored in a knowledge database. Furthermore, user emotion data recognized by the emotion analysis engine is also stored in the knowledge database. This enables quick and appropriate responses when similar problems occur in the future. It also allows for the provision of countermeasures that take past emotion data into account when reporting problems in the future. As a result, the system not only enables rapid problem solving but also facilitates the accumulation and reuse of knowledge, leading to long-term operational efficiency.

[1440] Specific example

[1441] For example, if a user reports a problem such as "the application crashes when I try to save a file," the server receives the problem and determines if it already exists in the knowledge database. If it's not a known issue, it delegates the analysis to generative artificial intelligence, which generates a solution such as "check the configuration file and configure it appropriately." This generated solution is then returned to the user via the server and added to the knowledge database. Furthermore, an emotion analysis engine recognizes the user's emotions and generates a message to alleviate their stress.

[1442] Example of a prompt

[1443] "Please generate an appropriate solution for the issue where 'the application crashes when trying to save a file.' Since this is causing significant stress to the user, please also include a reassuring message."

[1444] This invention automates the process from problem reporting to solution provision, and the knowledge database is continuously strengthened, improving the overall maintainability of the system. By incorporating emotion recognition functionality, the user experience is enhanced, enabling the provision of more satisfying services. This system not only enables rapid problem resolution but also facilitates the accumulation and reuse of knowledge, resulting in long-term operational efficiency.

[1445] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1446] Step 1: User reports a problem.

[1447] Input: The user uses an information processing device (e.g., personal computer, smartphone) to access a dedicated application or web interface and enter details of the problem (e.g., error message, date and time of occurrence, system behavior, etc.).

[1448] Specific operation: The user enters the necessary information into the problem report form and presses the "Submit" button to report the problem.

[1449] Output: The problem report is sent to the server.

[1450] Step 2: Server receives report and determines known / unknown information.

[1451] Input: The server receives problem reports submitted by users.

[1452] Specific operation: The server analyzes the received problem report and accesses the knowledge database to determine whether or not it is a known phenomenon.

[1453] Output: If the issue is known, retrieve a solution from the knowledge database; if it is an unknown issue, proceed to the next step.

[1454] Step 3: Server response to known issues

[1455] Input: The server retrieves solutions for known issues from the knowledge database.

[1456] Specific operation: The server sends the solution to the user's information processing device and displays it on the screen.

[1457] Output: The user is provided with specific countermeasures (e.g., "Restart the system" for error code 500).

[1458] Step 4: Delegation of analysis of unknown phenomena to the server

[1459] Input: The server determines that this is not a known phenomenon and delegates the analysis to a generative AI model (e.g., GPT-4).

[1460] Specific operation: The server sends the details of the problem report to the generating AI model.

[1461] Output: Details of the problem report are sent to the generating AI model.

[1462] Step 5: Generating new knowledge using a generative AI model

[1463] Input: The generated AI model receives problem reports sent from the server.

[1464] Specific operation: The generative AI model analyzes the problem and generates new knowledge and solutions (e.g., "Check the configuration file and configure it appropriately").

[1465] Output: The generated solution is sent back to the server.

[1466] Step 6: Responding with new knowledge and managing stress

[1467] Input: The server receives the solution returned from the generated AI model.

[1468] Specific operation: The server responds to the user with a solution and simultaneously analyzes the user's emotions using an emotion analysis engine (e.g., IBM Watson). If stress is detected, it generates detailed instructions and an encouraging message.

[1469] Output: The user is provided with concrete solutions and emotionally resonant messages.

[1470] Step 7: Update the knowledge database by the server.

[1471] Input: The server receives new knowledge generated by the generation AI model and data from the emotion analysis engine.

[1472] Specific operation: The server adds new knowledge to the knowledge database and stores sentiment data along with it.

[1473] Output: The knowledge database will be updated, and problem handling and emotional support will be enhanced for future issues.

[1474] The above describes the processing steps of the program for this system.

[1475] (Application Example 2)

[1476] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1477] Existing problem-solving systems were time-consuming to respond to unfamiliar situations, making it difficult to provide appropriate solutions quickly. Furthermore, they failed to consider user emotions, hindering improvements in the user experience. As a result, there was a lack of means to alleviate user stress and dissatisfaction.

[1478] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1479] In this invention, the server includes means for a user to report a problem via a terminal, means for receiving the problem report and determining whether it is a known event, means for responding with a method of action if it is a known event, means for delegating analysis to a generative artificial intelligence and generating new knowledge if it is an unknown event, means for adding the generated knowledge to a knowledge base, means for sentiment analysis to recognize the user's emotions, and means for providing countermeasures according to the recognized emotions. This enables rapid response to unknown events and effective accumulation of knowledge, and furthermore, by taking user emotions into consideration, it is possible to improve the user experience and reduce dissatisfaction.

[1480] A "user" refers to a person who uses the system or device to report a problem and receive a solution.

[1481] A "device" refers to a device used by a user to report a problem, and includes smartphones, personal computers, and other similar devices.

[1482] "Problem reporting" refers to the act of a user informing the system of any malfunctions or errors that have occurred, as well as the content of that information.

[1483] A "server" refers to a computer system that receives problem reports, analyzes them, and generates solutions.

[1484] "Known events" refer to events where similar problems have occurred in the past, and for which solutions have already been accumulated in the knowledge base.

[1485] An "unknown event" refers to an event that has never occurred before, or for which no solution exists in the knowledge base.

[1486] "Generative artificial intelligence" refers to artificial intelligence technology used to generate new solutions and knowledge in response to unknown phenomena.

[1487] "Knowledge" refers to information, data, and solutions that are useful for solving problems.

[1488] A "knowledge base" refers to a database where accumulated knowledge is stored and can be searched and referenced.

[1489] "Emotional analysis means" refers to technologies and devices used to analyze and recognize the emotions of users.

[1490] "Countermeasures" refer to the specific means or methods provided to solve a problem.

[1491] The system for implementing this invention consists of the following elements. First, a terminal is required for users to report problems. The terminal includes smartphones and personal computers, and has a dedicated application installed. Using this application, users can input details of the problem and send them to the server.

[1492] Upon receiving this problem report, the server first determines whether the reported issue is a known problem. If it is a known issue, the server searches its knowledge base for a solution and responds to the user.

[1493] If an unknown phenomenon occurs, the server delegates the analysis of the problem to a generative artificial intelligence (AI). The generative AI analyzes the received problem report and generates new knowledge and solutions. This new knowledge is returned to the user through the server and is also automatically added to the knowledge base.

[1494] Furthermore, the server recognizes the user's emotions using emotion analysis tools. These tools utilize an emotion analysis model based on the Hugging Face transformers library. This allows the server to analyze the user's emotions, such as stress and frustration, and provide appropriate responses based on the recognized emotions. For example, if the user is experiencing high levels of stress, the server will respond quickly, providing detailed instructions on the steps necessary to resolve the problem. It will also respond with a gentle, encouraging message.

[1495] Hardware and software to be used

[1496] Hardware:

[1497] Server: Cloud servers such as AWS and Google Cloud

[1498] Devices: Smartphones and computers (iOS, Android, Windows, Mac, etc.)

[1499] software:

[1500] Flask: A web framework written in Python.

[1501] transformers:Hugging Face is a library for emotion analysis models.

[1502] Specific example

[1503] A user reports a problem, such as "the vehicle's autonomous driving function has stopped working." Using the application on their device, they enter details of the problem (e.g., "fault_code_001") and a message describing their concern (e.g., "The autonomous driving function suddenly stopped working. I'm very worried."). The problem report is sent to the server, which receives the problem.

[1504] The server determines from the problem report whether it is a known issue. If it is a known issue, it searches the knowledge base for an appropriate solution and responds. However, in this case, it is determined to be an unknown issue, so generative artificial intelligence analyzes the problem and generates a new solution (for example, "check the configuration file and make the appropriate settings").

[1505] Furthermore, sentiment analysis tools are used to analyze the user's messages and recognize if the user is experiencing stress or worry. In response, encouraging messages such as, "Don't worry, we'll let you know the solution soon," are also sent back.

[1506] Example of a prompt

[1507] The following are specific examples of prompt statements.

[1508] Problem: fault_code_001

[1509] Message: The autonomous driving function suddenly stopped working. I am very worried.

[1510] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1511] Step 1:

[1512] Users report problems using their devices.

[1513] The user opens a dedicated application on their device, enters details of the problem (error message, date and time of occurrence, circumstances, etc.), and submits a report.

[1514] Input: Problem details (text data)

[1515] Output: Problem report data sent to the server

[1516] Step 2:

[1517] The server receives a problem report.

[1518] The server analyzes the problem report data sent from the terminal and retrieves the details of the problem.

[1519] Input: Problem report data

[1520] Output: Analyzed problem content

[1521] Step 3:

[1522] The server determines whether the problem is known.

[1523] The server accesses the knowledge base to check whether the reported issue is a known issue. If it is a known issue, it retrieves the appropriate solution from the knowledge base.

[1524] Input: Analyzed problem description, knowledge base

[1525] Output: Countermeasures (only for known issues)

[1526] Step 4:

[1527] The server will respond with a solution (if it's a known issue).

[1528] The server returns a solution retrieved from the knowledge base to the user. This solution is displayed on the terminal screen.

[1529] Input: Countermeasures

[1530] Output: Reply to the user

[1531] Step 5:

[1532] The server delegates the problem to a generative artificial intelligence (in the case of an unknown event).

[1533] If the issue is not known, the server delegates the analysis of the problem to a generative artificial intelligence.

[1534] Input: Analyzed problem content

[1535] Output: Problem data for generative artificial intelligence

[1536] Step 6:

[1537] Generative artificial intelligence analyzes the problem and generates new knowledge.

[1538] Generative artificial intelligence analyzes problem reports and generates new solutions.

[1539] Input: Problem data

[1540] Output: New knowledge (solution)

[1541] Step 7:

[1542] The server adds the generated knowledge to the knowledge base.

[1543] The newly generated knowledge is automatically added to the knowledge base.

[1544] Input: New knowledge

[1545] Output: Updated Knowledge Base

[1546] Step 8:

[1547] The server recognizes the user's emotions using emotion analysis tools.

[1548] The server inputs the user's text message into an emotion analysis model and analyzes their emotional state.

[1549] Input: User's text message

[1550] Output: Emotional state data

[1551] Step 9:

[1552] The server provides countermeasures based on the emotions it recognizes.

[1553] Based on the sentiment analysis results, the system sends users appropriate responses or encouraging messages.

[1554] Input: Emotional state data, new solution

[1555] Output: Emotionally sensitive responses and messages

[1556] Step 10:

[1557] The server returns the response result to the user.

[1558] Ultimately, the server responds to the user with the generated solution and a message tailored to their emotions, displaying it on their device.

[1559] Input: Emotionally sensitive responses and solutions

[1560] Output: Information returned to the terminal

[1561] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1562] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1563] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1564] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1565] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1566] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1567] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1568] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1569] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1570] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1571] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1572] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1573] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1574] 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.

[1575] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1576] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1577] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1578] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1579] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1580] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1581] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1582] The following is further disclosed regarding the embodiments described above.

[1583] (Claim 1)

[1584] A means for users to report problems through their devices,

[1585] A means for receiving a problem report and determining whether or not it is a known issue,

[1586] If it is a known issue, a means of responding with a solution,

[1587] In the case of an unknown phenomenon, the analysis is entrusted to a generative artificial intelligence, and a means of generating new knowledge is provided.

[1588] A means of adding the generated knowledge to the knowledge base,

[1589] A system that includes this.

[1590] (Claim 2)

[1591] Generative artificial intelligence analyzes problems and generates solutions,

[1592] A means of responding to the user with the generated solution,

[1593] The system according to claim 1, further comprising:

[1594] (Claim 3)

[1595] A means of automatically adding and updating solutions generated by generative artificial intelligence to a knowledge base,

[1596] A means of addressing future issues based on the updated knowledge base,

[1597] The system according to claim 1, further comprising:

[1598] These claims clearly define the technical features of the system and limit the technical scope of the invention.

[1599] "Example 1"

[1600] (Claim 1)

[1601] A means for users to report problems through their devices,

[1602] A means for receiving a problem report and determining whether or not it is a known issue,

[1603] If it is a known issue, a means of responding with a solution,

[1604] In the case of an unknown phenomenon, the analysis is entrusted to a generative artificial intelligence, and a means of generating new knowledge is provided.

[1605] A means of adding the generated knowledge to the knowledge base,

[1606] A means of generating new knowledge and solutions from received problem reports using generative artificial intelligence and responding to the user,

[1607] A system that includes this.

[1608] (Claim 2)

[1609] Generative artificial intelligence analyzes problems and generates solutions,

[1610] A means of responding to the user with the generated solution,

[1611] A means of automatically adding the generated knowledge to the knowledge base,

[1612] To enable a swift response to similar problems in the future, we will utilize an updated knowledge base.

[1613] The system according to claim 1, including the following:

[1614] (Claim 3)

[1615] A method for using prompt sentences generated by a generative artificial intelligence,

[1616] A means of generating solutions based on prompt statements and updating the knowledge base,

[1617] The system according to claim 1, including the following:

[1618] "Application Example 1"

[1619] (Claim 1)

[1620] A means for users to report problems through their devices,

[1621] A means for receiving a problem report and determining whether or not it is a known issue,

[1622] If it is a known issue, a means of responding with a solution,

[1623] In the case of an unknown phenomenon, the analysis is entrusted to a generative artificial intelligence, and a means of generating new knowledge is provided.

[1624] A means of adding the generated knowledge to the knowledge base,

[1625] In a logistics center, a means for workers to report equipment and system errors using smart devices,

[1626] A system that includes this.

[1627] (Claim 2)

[1628] Generative artificial intelligence analyzes problems and generates solutions,

[1629] A means of responding to the user with the generated solution,

[1630] A method for sending error details and images reported from smart devices to a server, and then suggesting countermeasures from a knowledge base,

[1631] The system according to claim 1, further comprising:

[1632] (Claim 3)

[1633] A means of automatically adding and updating solutions generated by generative artificial intelligence to a knowledge base,

[1634] A means of addressing future issues based on the updated knowledge base,

[1635] A means of analyzing and generating knowledge about unknown phenomena using generative artificial intelligence,

[1636] The system according to claim 1, further comprising:

[1637] "Example 2 of combining an emotion engine"

[1638] (Claim 1)

[1639] A means for users to report problems through an information processing device,

[1640] A means of receiving a problem report and determining whether or not it is a known phenomenon,

[1641] If it is a known phenomenon, a means of responding with a solution,

[1642] In the case of an unknown phenomenon, the analysis is entrusted to generative artificial intelligence, providing a means to generate new knowledge.

[1643] A means of adding the generated knowledge to a knowledge database,

[1644] A means of recognizing a user's emotions using an emotion analysis engine,

[1645] A means of adjusting coping strategies based on recognized emotions,

[1646] A system that includes this.

[1647] (Claim 2)

[1648] Generative artificial intelligence analyzes problems and generates solutions,

[1649] A means of responding to the user with the generated solution,

[1650] A means for generating messages to reduce user stress based on the results of emotion analysis,

[1651] The system according to claim 1, further comprising:

[1652] (Claim 3)

[1653] A means of automatically adding and updating solutions generated by generative artificial intelligence to a knowledge database,

[1654] A means of addressing future problems based on an updated knowledge database,

[1655] A means to enhance future emotional responses by utilizing the analysis data from the emotion analysis engine,

[1656] The system according to claim 1, further comprising:

[1657] "Application example 2 when combining with an emotional engine"

[1658] (Claim 1)

[1659] A means for users to report problems through their devices,

[1660] A means for receiving a problem report and determining whether or not it is a known issue,

[1661] If it is a known issue, a means of responding with a solution,

[1662] In the case of an unknown phenomenon, the analysis is entrusted to a generative artificial intelligence, and a means of generating new knowledge is provided.

[1663] A means of adding the generated knowledge to the knowledge base,

[1664] A means of analyzing user emotions,

[1665] A means of providing countermeasures that correspond to recognized emotions,

[1666] A system that includes this.

[1667] (Claim 2)

[1668] Generative artificial intelligence analyzes problems and generates solutions,

[1669] A means of responding to the user with the generated solution,

[1670] A means for monitoring changes in the user's emotions in real time through emotion analysis and adjusting countermeasures based on that,

[1671] The system according to claim 1, further comprising:

[1672] (Claim 3)

[1673] A means of automatically adding and updating solutions generated by generative artificial intelligence to a knowledge base,

[1674] A means of addressing future issues based on the updated knowledge base,

[1675] This method involves saving response strategies in association with user sentiment data, thereby improving future emotional responses.

[1676] The system according to claim 1, further comprising: [Explanation of Symbols]

[1677] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to report problems through their devices, A means for receiving a problem report and determining whether or not it is a known issue, If it is a known issue, a means of responding with a solution, In the case of an unknown phenomenon, the analysis is entrusted to a generative artificial intelligence, and a means of generating new knowledge is provided. A means of adding the generated knowledge to the knowledge base, A system that includes this.

2. Generative artificial intelligence analyzes problems and generates solutions, A means of responding to the user with the generated solution, The system according to claim 1, further comprising:

3. A means of automatically adding and updating solutions generated by generative artificial intelligence to a knowledge base, A means of addressing future issues based on the updated knowledge base, The system according to claim 1, further comprising: These claims clearly define the technical features of the system and limit the technical scope of the invention.

Images