System

Abstract

A system is provided.SOLUTION: This system includes a means for receiving inquiry contents from a user, a means for summarizing the received inquiry contents, a means for executing a relevant computer command based on the summarized contents and collecting a log, a means for analyzing the collected log and converting it into an easy-to-understand format, and a means for providing the converted contents to an operator.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's IT industry, there is a high level of personnel turnover, and highly skilled operators are not always available. As a result, when responding to inquiries, logging into the system to check its internal operation and identify the cause of the problem requires a lot of effort and time. As a result, there is a problem of overconsumption of highly skilled expert resources. This invention aims to reduce the burden on experts by enabling even less skilled operators to respond quickly and accurately to system problems. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for accepting inquiries from users and automatically summarizing those contents. The received inquiry contents are summarized using a generation AI, and related computer commands are executed based on the summarized contents, and logs are collected. The collected logs are analyzed again by the generation AI and converted into an easy-to-understand format. This allows operators to respond to inquiries quickly and appropriately based on the generated contents. This system is a means for enabling even operators without specialized knowledge to respond to system malfunctions.

[0006] "User" refers to a user of the service who makes an inquiry to the system.

[0007] "Inquiry Content" refers to a specific description of a problem or question that a user sends to the system.

[0008] A "summary" is a short sentence that succinctly states the important points of the inquiry.

[0009] "Means" refers to the methods or techniques used to achieve a particular purpose.

[0010] "Computer command" refers to an instruction to perform a system operation or change a system setting.

[0011] "Log" refers to a record of system actions and events.

[0012] "Generative AI" refers to a system that automatically generates text using artificial intelligence technology.

[0013] "Operator" refers to the person in charge of system management and responding to inquiries.

[0014] "Analysis" refers to the process of examining information or data in detail to understand its content and structure.

[0015] "System" refers to the entire mechanism in which multiple computer programs and hardware work together. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention relates to a system that receives inquiries from users, summarizes the inquiries, and collects and analyzes related logs. Detailed embodiments of this system will be described below.

[0038] First, the user sends a message regarding the system malfunction to the inquiry desk. The user enters the inquiry content using a terminal and clicks the send button to make the inquiry. This content is sent to the server, which receives it and stores it in a database.

[0039] The server then begins the process of summarizing the received inquiry. Using a generation AI, the server automatically summarizes the inquiry based on the necessary information. For example, if a user sends a query such as "My service has stopped. What should I do?", the generation AI converts this into a summary such as "My service has stopped."

[0040] Based on the summary, the server selects the relevant computer command. For example, if the summary is "Service has stopped," the server selects the command sudo systemctl status some_service. This command is executed within the server, and the relevant logs are collected as output.

[0041] The collected logs are then analyzed again using the generation AI. The server inputs the log data into the generation AI, and the server converts the resulting information into an easy-to-understand format. For example, if the log contains the content "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation: "The service has stopped due to lack of memory. Please check your memory usage and restart if necessary."

[0042] Finally, the server provides the generated explanation to the operator, who then responds promptly and appropriately to the user's inquiry based on the explanation. The operator then informs the user of the solution via the terminal, and the user can follow the solution to solve the problem.

[0043] As a concrete example, the flow when a user makes an inquiry saying, "The service has stopped. What should I do?" is shown below. The server receives this inquiry and the generation AI summarizes it as "The service has stopped." The server then selects and executes the sudo systemctl status some_service command, collecting a log stating, "Some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation saying, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. The operator conveys this explanation to the user, who then follows the instructions to take measures and resolve the problem.

[0044] In this way, the present invention enables even less skilled operators to isolate and handle advanced system faults, thereby enabling the efficient use of expert resources.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] The user uses the terminal to enter the inquiry details and clicks the send button.

[0048] Step 2:

[0049] The terminal transmits the input inquiry to the server.

[0050] Step 3:

[0051] The server receives the query and stores it in a database.

[0052] Step 4:

[0053] The server sends the received query to the generation AI, which generates a summary.

[0054] Step 5:

[0055] The server selects the appropriate computer command based on the generated summary.

[0056] Step 6:

[0057] The server executes selected computer commands and collects relevant logs.

[0058] Step 7:

[0059] The server sends the collected logs to a generation AI, which generates an easy-to-understand explanation.

[0060] Step 8:

[0061] The server sends the generated explanation to the operator's terminal for display.

[0062] Step 9:

[0063] The operator will inform the user of the countermeasures via the terminal.

[0064] Step 10:

[0065] The user follows the operator's instructions and performs operations to solve the problem through the terminal.

[0066] Step 11:

[0067] After the user has resolved the problem, he reports the results to the operator, who then records the results on the server.

[0068] Example 1

[0069] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0070] There is a need to respond to user inquiries quickly and effectively and identify the cause of system failures. However, with conventional methods, manually summarizing the content of inquiries and collecting and analyzing logs takes a great deal of time and effort, making it difficult for operators without specialized knowledge to provide advanced responses. Furthermore, in situations where a quick response is required, delays can result in a decrease in user satisfaction.

[0071] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0072] In this invention, the server includes means for accepting inquiries from users, means for automatically summarizing the accepted inquiries using a generative AI model, means for executing related computer resource management commands based on the summarized content and collecting logs, means for analyzing the collected log data using the generative AI model and converting it into an easy-to-understand format, and means for providing the converted content to an operator, thereby enabling even operators without specialized knowledge to respond to user inquiries quickly and accurately.

[0073] "User" refers to an individual or company representative who queries the system.

[0074] "Inquiry content" refers to information entered and sent by a user regarding a system malfunction or question.

[0075] A "generative AI model" refers to an artificial intelligence algorithm that generates and analyzes text based on large amounts of data.

[0076] "Summary" refers to a sentence that briefly summarizes the main information of the inquiry.

[0077] "Computer resource management commands" refer to instructions executed by a server to check or manipulate the state of the system.

[0078] A "log" refers to data that records various events and activities that occur on a computer system.

[0079] "Analysis" refers to the process of examining collected log data in detail to identify the cause of the problem and how to solve it.

[0080] "Operator" refers to the person in charge of operating the system and dealing with users.

[0081] MODE FOR CARRYING OUT THE INVENTION

[0082] The present invention relates to a system that receives inquiries from users, summarizes the inquiries, and collects and analyzes related logs. Detailed embodiments of this system will be described below.

[0083] First, the user uses their own device (PC or smartphone) to enter the inquiry and clicks the send button. For example, if the user enters something like "The service has stopped. What should I do?", the inquiry is sent from the user's device to the server.

[0084] The server stores the query received from the user in a database. The stored data includes not only the query content but also metadata such as date and time and user ID. This storage process is performed using a database management system on the server (e.g., MySQL, PostgreSQL, etc.).

[0085] The server then inputs the saved query content into a generative AI model for summarization. This summarization process uses natural language processing techniques to concisely summarize the key information in the query content. For example, in response to a query such as "The service has stopped. What should I do?", the generative AI model generates the summary "The service has stopped."

[0086] Based on the summary, the server selects the appropriate computer resource management command. This selection process is performed by a rule-based engine or script within the server. For example, for the summary "Service has stopped," the server selects the command sudo systemctl status some_service.

[0087] The server executes the selected commands and collects the resulting logs, which contain important information about the system's state and are stored using an on-server log management system (e.g., ELK stack, Splunk, etc.).

[0088] The collected log data is then input back into the generative AI model for analysis. During this analysis process, the log contents are examined in detail to identify the cause of the problem and how to resolve it. The generative AI model analyzes the log contents and extracts information such as "some_service has stopped due to insufficient memory."

[0089] The server generates an easy-to-understand explanation for the user based on the analysis results of the generative AI model. The generative AI model converts the analysis results into a simple explanation such as "The service has stopped due to insufficient memory. Please check your memory usage and restart if necessary."

[0090] Finally, the server provides the generated explanation to the operator. The operator responds to the user based on the explanation provided. The operator communicates the explanation to the user through their own terminal and provides specific countermeasures. For example, the operator might instruct the user, "The service has stopped due to insufficient memory. Please check the memory usage and restart if necessary."

[0091] As a concrete example, let's consider the case where a user makes an inquiry saying, "The service has stopped. What should I do?" The server receives the inquiry and summarizes it as "The service has stopped" using the generative AI model. The server then selects and executes the sudo systemctl status some_service command, collecting a log stating, "Some_service has stopped due to insufficient memory." The generative AI model converts this log into an explanation saying, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides this to the operator. The operator then conveys this explanation to the user, who then follows the instructions to take measures and resolve the problem.

[0092] Below are some examples of prompts for generative AI models:

[0093] "When a user asks, 'My service is down, what do I do?' Summarize and create a concise answer."

[0094] "Based on the log data 'some_service has stopped due to insufficient memory', please generate an easy-to-understand explanation for the user."

[0095] As described above, the present invention enables even operators without specialized knowledge to respond to user inquiries quickly and accurately.

[0096] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0097] Step 1:

[0098] The user inputs a query into the terminal and sends it.

[0099] The user enters the inquiry into their own terminal and clicks the send button. For example, they enter "The service has stopped. What should I do?" The entered inquiry is sent from the terminal to the server via the network.

[0100] Input: User inquiry (e.g. "My service has stopped. What should I do?").

[0101] Output: The query is sent to the server.

[0102] Step 2:

[0103] The server receives the query and stores it in a database.

[0104] The server receives the inquiry sent by the user and temporarily stores it in memory.Then, it stores the inquiry in a database.At this time, in addition to the inquiry content, it also stores metadata such as the date and time and user ID.

[0105] Input: User's inquiry.

[0106] Output: Query details and metadata stored in a database.

[0107] Step 3:

[0108] The server automatically summarizes the query using a generative AI model.

[0109] The server retrieves the query content from the database and inputs it into the generative AI model. The generative AI model analyzes the query content, extracts key information, and generates a summary. For example, the query "The service has stopped. What should I do?" is summarized as "The service has stopped."

[0110] Input: The query retrieved from the database.

[0111] Output: A summary from the generative AI model (e.g., "The service has stopped").

[0112] Step 4:

[0113] The server selects relevant computer resource management commands based on the abstract content.

[0114] The server selects an appropriate command based on the summary obtained from the generative AI model. For example, for the summary "The service has stopped," the command "sudo systemctl status some_service" is selected. This selection is performed by a rule-based engine or script within the server.

[0115] Input: A summary from a generative AI model.

[0116] Output: The selected computer resource management command (e.g., sudo systemctl status some_service).

[0117] Step 5:

[0118] The server executes the selected command and collects the logs.

[0119] The server runs the selected command and collects logs as its output, for example, run the command sudo systemctl status some_service to get log data about the status of the service.

[0120] Input: Selected computer resource management command.

[0121] Output: The captured log data.

[0122] Step 6:

[0123] The logs collected by the server are analyzed using a generative AI model.

[0124] The server inputs the collected log data into a generative AI model for analysis. The generative AI model then examines the log contents in detail to identify the cause of the problem. For example, it might analyze and extract information such as "some_service has stopped due to insufficient memory."

[0125] Input: Collected log data.

[0126] Output: Analysis results from the generative AI model (e.g., "some_service has stopped due to lack of memory").

[0127] Step 7:

[0128] The server generates an easy-to-understand explanation for the user based on the analysis results of the generated AI model.

[0129] The server generates an explanation in a form that is easy for the user to understand based on the analysis results of the generative AI model. The generative AI model converts the analysis results into an explanation such as "The service has stopped due to insufficient memory. Please check your memory usage and restart if necessary."

[0130] Input: Analysis results of the generative AI model.

[0131] Output: A generated, user-friendly explanation (e.g., "The service has stopped due to low memory. Please check your memory usage and restart if necessary").

[0132] Step 8:

[0133] The server provides the generated explanation to the operator.

[0134] The server provides the generated explanation to an interface accessible to the operator, who then checks the explanation provided by the server on his / her terminal.

[0135] Input: The generated description.

[0136] Output: The description provided to the operator.

[0137] Step 9:

[0138] The operator responds to the user based on the explanation.

[0139] The operator responds to the user based on the explanation provided by the server and instructs the user on specific measures to take, for example, "The service has stopped due to a lack of memory. Please check the memory usage and restart if necessary."

[0140] Input: A description provided by the server.

[0141] Output: Specific measures provided to the user.

[0142] (Application example 1)

[0143] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0144] Modern factories employ a large number of robots, and when one of these robots breaks down, a rapid and appropriate response is required. However, detecting a robot's malfunction and identifying its cause requires a high level of specialized knowledge, making a rapid response often difficult. Furthermore, it takes time and effort for maintenance staff to manually analyze all log data and find the optimal solution. As a result, in many factories, responding to robot malfunctions takes a long time, which can lead to reduced productivity. Furthermore, analyzing complex log data and summarizing inquiries requires a lot of manual work, making efficient operation difficult. A system that can solve these issues is needed.

[0145] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0146] In this invention, the server includes: means for accepting inquiries from users; means for summarizing the received inquiries; means for executing related computer commands based on the summaries and collecting logs; means for analyzing the collected logs and converting them into an easy-to-understand format; means for providing the converted logs to an operator; and means installed on a mobile device that includes an application for processing the inquiries and displaying the log analysis results. This allows maintenance staff to quickly and efficiently identify the cause of robot failures and take appropriate action. Furthermore, the automatic summarization of inquiries and automatic analysis of log data improves work efficiency.

[0147] "User" means a person or entity that queries the System.

[0148] "Inquiry content" refers to detailed information about a question or problem that a user sends to the system.

[0149] "Means for receiving" refers to the method by which the system receives inquiries from users.

[0150] "Means of summarizing" refers to a method for concisely summarizing the content of inquiries received.

[0151] "Relevant computer commands" are system commands that are executed based on the abstracted query.

[0152] A "log" is recorded information such as system operation history and error messages.

[0153] "Means of collection" refers to the method for collecting the necessary log data.

[0154] "Means of analysis" refers to the method of analyzing collected log data to identify problems and solutions.

[0155] "Means for providing" refers to a method for presenting analysis results and other information to an operator.

[0156] An "operator" is a person who manages the system and responds to inquiries from users.

[0157] A "mobile device" is a portable electronic device such as a smartphone or tablet.

[0158] "Installation" is the act of introducing application software onto specific hardware.

[0159] An "application" is a software program designed to provide a particular function or service.

[0160] "Generative AI" is an artificial intelligence technology that automates the analysis of inquiry content and logs.

[0161] The present invention relates to a system for quickly and efficiently dealing with robot failures in a factory. An embodiment of this system will be described in detail below.

[0162] The entire system consists of a server that accepts inquiries from users, a server that summarizes the inquiries using generative AI, a means for executing related computer commands based on the summarized content and collecting logs, a means for analyzing the collected logs and converting them into an easy-to-understand format, a means for providing the converted content to the operator, and an application installed on a mobile device.

[0163] First, a user uses a mobile device to input an inquiry about a robot malfunction or operational problem and send it to the server. For example, a user might send an inquiry such as, "My robot has stopped. What should I do?"

[0164] The server summarizes the received query using a generative AI model. In this case, OpenAI's GPT-3 is used as the AI ​​model. If the query is "My robot has stopped. What should I do?", the summary will be "My robot has stopped." Based on this summary, the system selects an appropriate computer command. For example, it could execute a command to "check the robot's status" and collect related log data.

[0165] Next, the collected log data is analyzed again using generative AI and converted into a format that is easy for users to understand. For example, if the log contains information such as "A motor error has occurred. The temperature is too high," the analysis result will be converted into a simple explanation such as "The robot's motor is experiencing an error. Please check the motor temperature and cool it if necessary." This process also uses OpenAI's GPT-3.

[0166] The converted information is provided to the operator, who then provides feedback on countermeasures to the user via a mobile device, allowing the user to quickly and accurately resolve the robot's problems.

[0167] As a concrete example, the following is an example of a prompt sentence to be input to a generative AI model:

[0168] Summary of your inquiry:

[0169] Please summarize your inquiry in one sentence:

[0170] My robot has stopped working, what should I do?

[0171] Log analysis:

[0172] Please analyze the following logs and clearly explain the problem and solution:

[0173] Robot motor error - Memory error detected - Temperature rise

[0174] This system enables factory maintenance staff, even those without advanced skills, to quickly identify the cause of a robot malfunction and take appropriate action, thereby improving productivity and enabling efficient malfunction response.

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1:

[0177] The user uses a mobile terminal to input an inquiry about a robot malfunction or operational problem and clicks the send button. At this point, the input is the inquiry entered by the user into the terminal, and the output is the inquiry data sent to the server. The server receives this data.

[0178] Step 2:

[0179] The server inputs the received query content into a generative AI model (for example, OpenAI's GPT-3) and summarizes the query content in one sentence. The prompt uses the format "Please summarize the following query content in one sentence:\n\n{query content}\n". The input is the received query data, and data processing is a summary process by the generative AI. The output is the summarized query content.

[0180] Step 3:

[0181] The server selects an appropriate computer command based on the abstract. For example, for the abstract "The robot has stopped," it selects the command sudo systemctl status robot_service to check the robot's status. The input is the abstracted query, and the output is the selected computer command.

[0182] Step 4:

[0183] The server executes the selected computer command and collects log data. Specifically, it collects the output obtained by executing the command (e.g., service status information obtained as a result of sudo systemctl status robot_service) as a log. The input is the selected computer command, the data calculation is the command execution process, and the output is the collected log data.

[0184] Step 5:

[0185] The collected log data is again input into the generative AI model, where it is analyzed and converted into an easy-to-understand format. The prompt sentence is "Analyze the following log and provide a clear explanation of the problem and solution:\n\n{log data}\n". The input is the collected log data, and the output is the analyzed result (e.g., "An error has occurred in the robot's motor. Check the motor temperature and cool it if necessary").

[0186] Step 6:

[0187] The server provides the analysis results to the operator. Based on this information, the operator provides appropriate feedback on countermeasures to the user via their mobile device. The input is the analysis results, and the output is specific countermeasure information provided to the user. The operator communicates this information to the user, who then uses it to solve the robot's problems.

[0188] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0189] This invention combines a system that accepts inquiries from users, summarizes the contents, and collects and analyzes related logs with an emotion engine that recognizes the emotions of the user. Detailed embodiments of this system are described below.

[0190] First, the user inputs the inquiry using the terminal and clicks the send button. The inquiry includes a detailed description of the technical problem or malfunction. The terminal then sends the user's input information to the server.

[0191] The server stores the received inquiry and sends it to the generation AI, which summarizes the inquiry and converts it into a concise format. This process allows the operator to grasp a lot of information in a short amount of time.

[0192] Next, the server uses an emotion engine to recognize the user's emotion from the inquiry. The emotion engine uses natural language processing technology to analyze the emotion from the user's sentence. For example, if the user says "I'm in a lot of trouble," the emotion engine will recognize emotions such as "stress" and "urgent need."

[0193] The emotions recognized by the emotion engine are used to determine the priority of the inquiry. For example, if the inquiry is highly angry or stressed, it will be treated as a high priority. The emotion engine can also advise the operator on the appropriate response method based on the recognized emotion.

[0194] Based on the summary and the perceived emotion, the server selects the relevant computer command. For example, if the summary says "Service has stopped" and the user is showing high stress, the server needs to respond quickly, so it will immediately run the sudo systemctl status some_service command and collect the necessary logs.

[0195] The collected logs are then analyzed using the generation AI and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation such as "The service has stopped due to lack of memory. Check the memory usage and restart it if necessary."

[0196] Finally, the server sends the notification content adjusted according to the generated explanation and the recognized emotion to the operator's terminal. The operator responds to the user's inquiry promptly and appropriately based on the provided explanation and emotion information. The operator then provides the user with specific measures via the terminal, and the user can follow the instructions to resolve the problem.

[0197] As a concrete example, the following shows the flow when a user inquires, "The service has stopped. What should I do?" and expresses the emotion, "I'm very troubled." The server receives this inquiry, and the generation AI summarizes it as "The service has stopped." The emotion engine then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating, "Some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick response, and the user follows the instructions to implement the response and resolves the problem.

[0198] In this way, the present invention recognizes the user's emotions and takes them into consideration when responding to inquiries, thereby reducing the burden on operators and increasing user satisfaction.

[0199] The processing flow will be explained below.

[0200] Step 1:

[0201] The user uses the terminal to enter the inquiry details and clicks the send button.

[0202] Step 2:

[0203] The terminal sends the inquiry to the server.

[0204] Step 3:

[0205] The server receives the query and stores it in a database.

[0206] Step 4:

[0207] The server sends the received query content to the generation AI, which summarizes the query content.

[0208] Step 5:

[0209] The generation AI summarizes the query, and the server receives the summary.

[0210] Step 6:

[0211] The server sends the summarized query content to the emotion engine to analyze the user's emotions.

[0212] Step 7:

[0213] The emotion engine recognizes the user's emotion from the summary content and sends the result to the server.

[0214] Step 8:

[0215] The server selects relevant computer commands based on the recognized emotions and summary content.

[0216] Step 9:

[0217] The server executes selected computer commands and collects logs.

[0218] Step 10:

[0219] The server sends the collected logs to the generation AI, requesting it to analyze the logs and generate easy-to-understand explanations.

[0220] Step 11:

[0221] The generation AI analyzes the logs, generates easy-to-understand explanations, and sends the results to the server.

[0222] Step 12:

[0223] The server sends a notification to the operator's terminal based on the generated description and the recognized emotion.

[0224] Step 13:

[0225] An operator uses the terminal to check the provided explanation and emotional information and inform the user of a response plan.

[0226] Step 14:

[0227] The user uses the terminal and follows the instructions of the operator to carry out operations to solve the problem.

[0228] Step 15:

[0229] The user reports that the problem has been resolved to the operator, and the result is recorded on the server.

[0230] Example 2

[0231] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0232] Conventional inquiry response systems have difficulty quickly and appropriately summarizing user inquiries, recognizing emotions, and determining response priorities. Furthermore, converting collected logs into an easy-to-understand format is time-consuming, increasing the burden on operators. This raises concerns about a decline in user satisfaction.

[0233] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting a user's inquiry, means for summarizing the accepted inquiry using a generative AI model, means for executing related computer commands based on the summarized content and collecting logs, means for analyzing the collected logs using the generative AI model and converting them into an easy-to-understand format, emotion recognition means for recognizing the user's emotion from the inquiry, means for determining the priority of the inquiry based on the recognized emotion, means for providing notification content according to the priority, and means for providing the converted content to the operator. This makes it possible to quickly and appropriately summarize the user's inquiry, recognize the emotion and determine the priority of the response, convert the collected logs into an easy-to-understand format, reduce the burden on the operator, and improve user satisfaction.

[0234] A "user" is a person or entity that uses the system to make an inquiry.

[0235] A "terminal" is an electronic device that a user operates to input and send inquiry details.

[0236] A "server" is a central system that processes and responds to inquiries received.

[0237] An "inquiry" is a message containing a problem or question that a user sends to the system.

[0238] A "generative AI model" is an artificial intelligence that learns from large amounts of data and is used to summarize and analyze user input.

[0239] "Summarization" is the process or result of converting detailed query content into a concise form.

[0240] A "computer command" is an instruction that a server executes to initiate a particular operation or process.

[0241] A "log" is recorded data about the operating status of a system or service and events that have occurred.

[0242] "Emotion recognition means" refers to a technology or system for analyzing and recognizing emotions from the content of a user's inquiry.

[0243] "Priority" is an index for determining the urgency and importance of a response based on the content of the inquiry and the user's feelings.

[0244] An "operator" is a person in charge of managing the system and dealing directly with users.

[0245] "Notification content" is information about the processing result, the user's feelings, and priority that is sent by the server to the operator.

[0246] "Analysis" is the process or result of examining data or logs in detail and extracting useful information.

[0247] "Converting into a format" means reconstructing collected data and logs into a format that is easy for operators to understand.

[0248] A "system" is a collection of hardware and software configured to perform a particular function.

[0249] The present invention provides a system that efficiently summarizes the content of inquiries from users, analyzes related logs, and recognizes the user's emotions to determine the priority of responses. Specific embodiments of this system are described below.

[0250] First, the user uses the terminal to enter the inquiry content and clicks the send button. The inquiry content includes a detailed description of the technical problem or malfunction. For example, the user might enter "The service has stopped. What should I do?" The terminal then sends the user's input information to the server. This transmission is done using an HTTP request or an API call.

[0251] The server stores the received query content in a database and sends the content to a generative AI model. An example of a generative AI model is GPT-3, a widely used artificial intelligence model. This model learns from large amounts of text data and has the ability to automatically summarize the input text. The generative AI model summarizes the query content in a concise format, such as "The service has been stopped."

[0252] Next, the server uses an emotion recognition means to recognize the user's emotion from the inquiry. Natural language processing technologies such as IBM Watson's Tone Analyzer are used as emotion recognition means. For example, if the user says "I'm in a lot of trouble," the emotion recognition means will recognize the emotion as "urgent need."

[0253] The server determines the priority of the query based on the emotion recognition results. For example, if the query indicates high anger or stress, it is treated as a high priority. The server then selects and executes the relevant computer command and collects the necessary logs. For example, if the summary reads "Service has stopped" and the user indicates high stress, the server will need to respond quickly, so it will run the sudo systemctl status some_service command and collect logs.

[0254] The collected logs are then analyzed using the generative AI model and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generative AI model converts this information into a simple explanation such as "The service has stopped due to lack of memory. Please check your memory usage and restart it if necessary."

[0255] Finally, the server sends the notification content, adjusted according to the generated explanation and the recognized emotion, to the operator's terminal. The operator responds promptly and appropriately to the user's inquiry based on the provided explanation and emotion information. The operator then provides the user with specific solutions via the terminal, allowing the user to solve the problem by following the instructions. In this way, the present invention recognizes the user's emotion and takes it into consideration when responding to inquiries, thereby reducing the burden on the operator and increasing user satisfaction.

[0256] As a concrete example, let's look at the flow when a user inquires, "The service has stopped. What should I do?" and expresses the emotion, "I'm very troubled." The server receives this inquiry, and the generative AI summarizes it as "The service has stopped." The emotion recognition means then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating, "Some_service has stopped due to insufficient memory." The generative AI model converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick solution, and the user can follow the instructions to implement the solution and resolve the problem.

[0257] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0258] Step 1:

[0259] The user uses the terminal to enter the inquiry and clicks the send button. The data entered is a specific problem or question. For example, "The service has stopped. What should I do?" is entered and sent. This is the input.

[0260] Step 2:

[0261] The terminal sends the inquiry entered by the user to the server. The specific operation performed at this time is to send data via an HTTP request. The input data is the inquiry entered by the user, and the output data is text data sent to the server.

[0262] Step 3:

[0263] The server stores the received query in a database. The input data is the query received from the terminal, and the output data is the query data stored in the database. Specifically, the server writes data to the database using SQL queries, etc.

[0264] Step 4:

[0265] The server sends the saved query content to the generative AI model. The input data is the query content saved in the database, and the output data is the text data sent to the generative AI model. Specifically, data is sent to the generative AI model using an HTTP request or API call.

[0266] Step 5:

[0267] The generative AI model summarizes the query content. The input data is the query content sent from the server, and the output data is the summarized text. Specifically, the generative AI model analyzes the text, extracts the important parts, and converts them into a concise form. For example, a summary such as "The service has been stopped" is generated.

[0268] Step 6:

[0269] The server uses the emotion recognition means to recognize the user's emotion from the summarized inquiry content. The input data is the summarized inquiry content, and the output data is the recognized emotion information. Specifically, the emotion recognition means analyzes the text using natural language processing (NLP) technology and extracts emotions. For example, an emotion such as "very troubled" is recognized as "urgent."

[0270] Step 7:

[0271] The server determines the priority of the inquiry based on the recognized emotion data. The input data is the recognized emotion information, and the output data is the priority information of the inquiry. Specifically, the server evaluates the emotion data and classifies the priority as high, medium, low, etc. For example, if the emotion data is recognized as "urgent," the inquiry is treated as high priority.

[0272] Step 8:

[0273] The server selects and executes the relevant computer command based on priority. The input data is the query priority information, and the output data is the execution result of the executed command. Specific operations include running a shell command to check the system status. For example, the sudo systemctl status some_service command is executed, and a log stating "some_service has stopped due to insufficient memory" is collected.

[0274] Step 9:

[0275] The collected logs are then analyzed again using the generative AI model and converted into an easy-to-understand format. The input data is the collected logs, and the output data is the analyzed simple explanatory text. Specifically, the generative AI model analyzes the logs and converts them into a format that is easy for users and operators to understand. For example, it generates an explanation such as "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary."

[0276] Step 10:

[0277] The server then sends the notification content, adjusted according to the generated explanation and the recognized emotion, to the operator's terminal. The input data is a simple explanation text and emotion information, and the output data is the notification content provided to the operator. Specifically, the server sends an appropriate notification to the operator's terminal, and the operator responds to the user based on that.

[0278] Step 11:

[0279] The operator will then provide the user with specific countermeasures based on the provided explanation. The input data is the explanation provided by the server, and the output data is feedback to the user. Specifically, the operator will tell the user to "check memory usage and reboot if necessary."

[0280] Step 12:

[0281] The user takes specific actions to solve the problem according to the feedback from the operator. The input data are instructions from the operator, and the output data are the measures taken and their results. Specific actions include the user checking memory usage on the terminal and restarting the service if necessary.

[0282] In this way, the system recognizes the user's emotions and takes them into consideration when responding to inquiries, thereby reducing the burden on operators and increasing user satisfaction.

[0283] (Application example 2)

[0284] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0285] In modern security services, it is extremely important to quickly and accurately handle user-reported issues. However, when user reports are verbose or emotionally charged, a system is needed to efficiently summarize them and respond quickly. Furthermore, responses that do not take user emotions into consideration can lead to significant dissatisfaction and further problems. Therefore, there is a need for systems that can understand user emotions and respond appropriately based on those emotions.

[0286] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for summarizing the accepted inquiry, means for executing related computer commands based on the summarized inquiry and collecting logs, means for analyzing the logs and converting them into an easy-to-understand format, means for recognizing the user's emotion based on the summarized inquiry and the analyzed log, means for determining a priority according to the recognized emotion, and means for providing the converted content and priority information to an operator. This enables a quick and appropriate response that takes the user's emotion into consideration.

[0287] "User" means any person or entity that submits an inquiry using this system.

[0288] "Inquiry" is the details of the problem or question reported by the user.

[0289] A "summarization means" is a technology that has the ability to convert the content of a query into a concise format.

[0290] "Generative AI" is an artificial intelligence technology for automatically summarizing and analyzing inquiry content.

[0291] A "computer command" is an instruction to perform a particular task.

[0292] A "log" is a record of system actions and events.

[0293] "Means of analysis" refers to the technology used to analyze collected logs and convert them into an easy-to-understand format.

[0294] "Means for recognizing emotions" refers to technology that determines the emotions of users based on their inquiries.

[0295] The "means for determining priority" is a function that determines the order of processing priorities based on the recognized emotions.

[0296] An "operator" is a person who operates the system and responds to user inquiries.

[0297] "Transformed content" is information that has been processed through summarization and analysis.

[0298] "Priority information" is information about the priority of processing determined by recognizing emotions.

[0299] This invention combines a system that accepts inquiries from users, summarizes the contents, and collects and analyzes related logs with an emotion engine that recognizes the emotions of the user. Detailed embodiments of this system are described below.

[0300] First, the user inputs the inquiry using the terminal and clicks the send button. The inquiry includes a detailed description of the technical problem or malfunction. The terminal then sends the user's input information to the server.

[0301] The server stores the received inquiry and sends it to the generation AI, which summarizes the inquiry and converts it into a concise format. This process allows the operator to grasp a lot of information in a short amount of time.

[0302] Next, the server uses an emotion engine to recognize the user's emotion from the inquiry. The emotion engine uses natural language processing technology to analyze the emotion from the user's sentence. For example, if the user says "I'm in a lot of trouble," the emotion engine will recognize emotions such as "stress" and "urgent need."

[0303] The emotions recognized by the emotion engine are used to determine the priority of the inquiry. For example, if the inquiry is highly angry or stressed, it will be treated as a high priority. The emotion engine can also advise the operator on the appropriate response method based on the recognized emotion.

[0304] Based on the summary and the perceived emotion, the server selects the relevant computer command. For example, if the summary says "Service has stopped" and the user is showing high stress, the server needs to respond quickly, so it will immediately run the sudo systemctl status some_service command and collect the necessary logs.

[0305] The collected logs are then analyzed using the generation AI and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation such as "The service has stopped due to lack of memory. Check the memory usage and restart it if necessary."

[0306] Finally, the server sends the notification content adjusted according to the generated explanation and the recognized emotion to the operator's terminal. The operator responds to the user's inquiry promptly and appropriately based on the provided explanation and emotion information. The operator then provides the user with specific measures via the terminal, and the user can follow the instructions to resolve the problem.

[0307] As a concrete example, the following shows the flow when a user reports that "my account may have been compromised" and expresses the emotion "very troubled." The server receives this inquiry, and the generation AI summarizes it as "my account is suspected to have been compromised." The emotion engine then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating "some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick response, and the user follows the instructions to implement the response and resolve the problem.

[0308] As a result, the present invention can recognize the user's emotions and respond to inquiries taking these into consideration, thereby reducing the burden on operators and increasing user satisfaction.

[0309] It also uses a generative AI model to summarize the query, an emotion engine to recognize emotions, and then executes the associated computer command. For each step, the following prompts are available:

[0310] Inquiry:

[0311] -------

[0312] I think my account may have been accessed illegally. I've noticed some suspicious activity since this morning. I'm in a lot of trouble.

[0313] summary:

[0314] ------

[0315] 1. Suspected unauthorized access to your account.

[0316] 2. Suspicious activity is observed.

[0317] 3. Users are very confused.

[0318] Emotion recognition:

[0319] --------------

[0320] Very confused (urgent)

[0321] The hardware used includes servers and devices, while the software includes generative AI models, emotion engines, and natural language processing technologies. The application of these technologies enables efficient and emotion-sensitive user support.

[0322] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0323] Step 1:

[0324] The user uses the terminal to input the inquiry content and clicks the send button. The input inquiry content (data) is sent from the terminal to the server. The input is the user's report content, and the output is the inquiry data sent to the server.

[0325] Step 2:

[0326] The server stores the query content received and sends it to the generative AI model, which then summarizes the query content. The input here is the query data received from the user, and the output is the summary data converted into a concise format.

[0327] Step 3:

[0328] The server sends the summarized query content to the emotion engine to recognize the user's emotion. The emotion engine uses natural language processing technology to analyze emotions. The input is the summary data, and the output is emotion data such as "confusion" or "urgency."

[0329] Step 4:

[0330] The server determines the priority of the query based on the recognized emotion data. For example, if the emotion is "urgent" or "angry," the query is set as a high priority. The input is emotion data, and the output is priority information.

[0331] Step 5:

[0332] The server selects and executes relevant computer commands based on the summary content and priority information. For example, run the command sudo systemctl status some_service to collect the required logs. The input is the summary data and priority information, and the output is the collected log data.

[0333] Step 6:

[0334] The server sends the collected log data to the generative AI model, which analyzes the logs and converts them into an easy-to-understand format. For example, it may convert the information into "The service has stopped due to insufficient memory." The input is the log data, and the output is simple explanatory data.

[0335] Step 7:

[0336] The server sends the generated explanation data and priority information to the operator's terminal. The operator responds promptly and appropriately to the user's inquiry based on the provided explanation and emotion information. The input is the explanation data and priority information, and the output is the information notified to the operator.

[0337] Step 8:

[0338] The operator communicates specific countermeasures to the user via the terminal. The user can then follow the instructions to implement the countermeasures and solve the problem. The input is the instructions from the operator, and the output is the countermeasure implemented by the user.

[0339] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0340] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0341] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0342] [Second embodiment]

[0343] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0344] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0345] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0346] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0347] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0348] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0349] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0350] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0351] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0352] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0353] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0354] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0355] The present invention relates to a system that receives inquiries from users, summarizes the inquiries, and collects and analyzes related logs. Detailed embodiments of this system will be described below.

[0356] First, the user sends a message regarding the system malfunction to the inquiry desk. The user enters the inquiry content using a terminal and clicks the send button to make the inquiry. This content is sent to the server, which receives it and stores it in a database.

[0357] The server then begins the process of summarizing the received inquiry. Using a generation AI, the server automatically summarizes the inquiry based on the necessary information. For example, if a user sends a query such as "My service has stopped. What should I do?", the generation AI converts this into a summary such as "My service has stopped."

[0358] Based on the summary, the server selects the relevant computer command. For example, if the summary is "Service has stopped," the server selects the command sudo systemctl status some_service. This command is executed within the server, and the relevant logs are collected as output.

[0359] The collected logs are then analyzed again using the generation AI. The server inputs the log data into the generation AI, and the server converts the resulting information into an easy-to-understand format. For example, if the log contains the content "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation: "The service has stopped due to lack of memory. Please check your memory usage and restart if necessary."

[0360] Finally, the server provides the generated explanation to the operator, who then responds promptly and appropriately to the user's inquiry based on the explanation. The operator then informs the user of the solution via the terminal, and the user can follow the solution to solve the problem.

[0361] As a concrete example, the flow when a user makes an inquiry saying, "The service has stopped. What should I do?" is shown below. The server receives this inquiry and the generation AI summarizes it as "The service has stopped." The server then selects and executes the sudo systemctl status some_service command, collecting a log stating, "Some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation saying, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. The operator conveys this explanation to the user, who then follows the instructions to take measures and resolve the problem.

[0362] In this way, the present invention enables even less skilled operators to isolate and handle advanced system faults, thereby enabling the efficient use of expert resources.

[0363] The processing flow will be explained below.

[0364] Step 1:

[0365] The user uses the terminal to enter the inquiry details and clicks the send button.

[0366] Step 2:

[0367] The terminal transmits the input inquiry to the server.

[0368] Step 3:

[0369] The server receives the query and stores it in a database.

[0370] Step 4:

[0371] The server sends the received query to the generation AI, which generates a summary.

[0372] Step 5:

[0373] The server selects the appropriate computer command based on the generated summary.

[0374] Step 6:

[0375] The server executes selected computer commands and collects relevant logs.

[0376] Step 7:

[0377] The server sends the collected logs to a generation AI, which generates an easy-to-understand explanation.

[0378] Step 8:

[0379] The server sends the generated explanation to the operator's terminal for display.

[0380] Step 9:

[0381] The operator will inform the user of the countermeasures via the terminal.

[0382] Step 10:

[0383] The user follows the operator's instructions and performs operations to solve the problem through the terminal.

[0384] Step 11:

[0385] After the user has resolved the problem, he reports the results to the operator, who then records the results on the server.

[0386] Example 1

[0387] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0388] There is a need to respond to user inquiries quickly and effectively and identify the cause of system failures. However, with conventional methods, manually summarizing the content of inquiries and collecting and analyzing logs takes a great deal of time and effort, making it difficult for operators without specialized knowledge to provide advanced responses. Furthermore, in situations where a quick response is required, delays can result in a decrease in user satisfaction.

[0389] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0390] In this invention, the server includes means for accepting inquiries from users, means for automatically summarizing the accepted inquiries using a generative AI model, means for executing related computer resource management commands based on the summarized content and collecting logs, means for analyzing the collected log data using the generative AI model and converting it into an easy-to-understand format, and means for providing the converted content to an operator, thereby enabling even operators without specialized knowledge to respond to user inquiries quickly and accurately.

[0391] "User" refers to an individual or company representative who queries the system.

[0392] "Inquiry content" refers to information entered and sent by a user regarding a system malfunction or question.

[0393] A "generative AI model" refers to an artificial intelligence algorithm that generates and analyzes text based on large amounts of data.

[0394] "Summary" refers to a sentence that briefly summarizes the main information of the inquiry.

[0395] "Computer resource management commands" refer to instructions executed by a server to check or manipulate the state of the system.

[0396] A "log" refers to data that records various events and activities that occur on a computer system.

[0397] "Analysis" refers to the process of examining collected log data in detail to identify the cause of the problem and how to solve it.

[0398] "Operator" refers to the person in charge of operating the system and dealing with users.

[0399] MODE FOR CARRYING OUT THE INVENTION

[0400] The present invention relates to a system that receives inquiries from users, summarizes the inquiries, and collects and analyzes related logs. Detailed embodiments of this system will be described below.

[0401] First, the user uses their own device (PC or smartphone) to enter the inquiry and clicks the send button. For example, if the user enters something like "The service has stopped. What should I do?", the inquiry is sent from the user's device to the server.

[0402] The server stores the query received from the user in a database. The stored data includes not only the query content but also metadata such as date and time and user ID. This storage process is performed using a database management system on the server (e.g., MySQL, PostgreSQL, etc.).

[0403] The server then inputs the saved query content into a generative AI model for summarization. This summarization process uses natural language processing techniques to concisely summarize the key information in the query content. For example, in response to a query such as "The service has stopped. What should I do?", the generative AI model generates the summary "The service has stopped."

[0404] Based on the summary, the server selects the appropriate computer resource management command. This selection process is performed by a rule-based engine or script within the server. For example, for the summary "Service has stopped," the server selects the command sudo systemctl status some_service.

[0405] The server executes the selected commands and collects the resulting logs, which contain important information about the system's state and are stored using an on-server log management system (e.g., ELK stack, Splunk, etc.).

[0406] The collected log data is then input back into the generative AI model for analysis. During this analysis process, the log contents are examined in detail to identify the cause of the problem and how to resolve it. The generative AI model analyzes the log contents and extracts information such as "some_service has stopped due to insufficient memory."

[0407] The server generates an easy-to-understand explanation for the user based on the analysis results of the generative AI model. The generative AI model converts the analysis results into a simple explanation such as "The service has stopped due to insufficient memory. Please check your memory usage and restart if necessary."

[0408] Finally, the server provides the generated explanation to the operator. The operator responds to the user based on the explanation provided. The operator communicates the explanation to the user through their own terminal and provides specific countermeasures. For example, the operator might instruct the user, "The service has stopped due to insufficient memory. Please check the memory usage and restart if necessary."

[0409] As a concrete example, let's consider the case where a user makes an inquiry saying, "The service has stopped. What should I do?" The server receives the inquiry and summarizes it as "The service has stopped" using the generative AI model. The server then selects and executes the sudo systemctl status some_service command, collecting a log stating, "Some_service has stopped due to insufficient memory." The generative AI model converts this log into an explanation saying, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides this to the operator. The operator then conveys this explanation to the user, who then follows the instructions to take measures and resolve the problem.

[0410] Below are some examples of prompts for generative AI models:

[0411] "When a user asks, 'My service is down, what do I do?' Summarize and create a concise answer."

[0412] "Based on the log data 'some_service has stopped due to insufficient memory', please generate an easy-to-understand explanation for the user."

[0413] As described above, the present invention enables even operators without specialized knowledge to respond to user inquiries quickly and accurately.

[0414] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0415] Step 1:

[0416] The user inputs a query into the terminal and sends it.

[0417] The user enters the inquiry into their own terminal and clicks the send button. For example, they enter "The service has stopped. What should I do?" The entered inquiry is sent from the terminal to the server via the network.

[0418] Input: User inquiry (e.g. "My service has stopped. What should I do?").

[0419] Output: The query is sent to the server.

[0420] Step 2:

[0421] The server receives the query and stores it in a database.

[0422] The server receives the inquiry sent by the user and temporarily stores it in memory.Then, it stores the inquiry in a database.At this time, in addition to the inquiry content, it also stores metadata such as the date and time and user ID.

[0423] Input: User's inquiry.

[0424] Output: Query details and metadata stored in a database.

[0425] Step 3:

[0426] The server automatically summarizes the query using a generative AI model.

[0427] The server retrieves the query content from the database and inputs it into the generative AI model. The generative AI model analyzes the query content, extracts key information, and generates a summary. For example, the query "The service has stopped. What should I do?" is summarized as "The service has stopped."

[0428] Input: The query retrieved from the database.

[0429] Output: A summary from the generative AI model (e.g., "The service has stopped").

[0430] Step 4:

[0431] The server selects relevant computer resource management commands based on the abstract content.

[0432] The server selects an appropriate command based on the summary obtained from the generative AI model. For example, for the summary "The service has stopped," the command "sudo systemctl status some_service" is selected. This selection is performed by a rule-based engine or script within the server.

[0433] Input: A summary from a generative AI model.

[0434] Output: The selected computer resource management command (e.g., sudo systemctl status some_service).

[0435] Step 5:

[0436] The server executes the selected command and collects the logs.

[0437] The server runs the selected command and collects logs as its output, for example, run the command sudo systemctl status some_service to get log data about the status of the service.

[0438] Input: Selected computer resource management command.

[0439] Output: The captured log data.

[0440] Step 6:

[0441] The logs collected by the server are analyzed using a generative AI model.

[0442] The server inputs the collected log data into a generative AI model for analysis. The generative AI model then examines the log contents in detail to identify the cause of the problem. For example, it might analyze and extract information such as "some_service has stopped due to insufficient memory."

[0443] Input: Collected log data.

[0444] Output: Analysis results from the generative AI model (e.g., "some_service has stopped due to lack of memory").

[0445] Step 7:

[0446] The server generates an easy-to-understand explanation for the user based on the analysis results of the generated AI model.

[0447] The server generates an explanation in a form that is easy for the user to understand based on the analysis results of the generative AI model. The generative AI model converts the analysis results into an explanation such as "The service has stopped due to insufficient memory. Please check your memory usage and restart if necessary."

[0448] Input: Analysis results of the generative AI model.

[0449] Output: A generated, user-friendly explanation (e.g., "The service has stopped due to low memory. Please check your memory usage and restart if necessary").

[0450] Step 8:

[0451] The server provides the generated explanation to the operator.

[0452] The server provides the generated explanation to an interface accessible to the operator, who then checks the explanation provided by the server on his / her terminal.

[0453] Input: The generated description.

[0454] Output: The description provided to the operator.

[0455] Step 9:

[0456] The operator responds to the user based on the explanation.

[0457] The operator responds to the user based on the explanation provided by the server and instructs the user on specific measures to take, for example, "The service has stopped due to a lack of memory. Please check the memory usage and restart if necessary."

[0458] Input: A description provided by the server.

[0459] Output: Specific measures provided to the user.

[0460] (Application example 1)

[0461] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0462] Modern factories employ a large number of robots, and when one of these robots breaks down, a rapid and appropriate response is required. However, detecting a robot's malfunction and identifying its cause requires a high level of specialized knowledge, making a rapid response often difficult. Furthermore, it takes time and effort for maintenance staff to manually analyze all log data and find the optimal solution. As a result, in many factories, responding to robot malfunctions takes a long time, which can lead to reduced productivity. Furthermore, analyzing complex log data and summarizing inquiries requires a lot of manual work, making efficient operation difficult. A system that can solve these issues is needed.

[0463] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0464] In this invention, the server includes: means for accepting inquiries from users; means for summarizing the received inquiries; means for executing related computer commands based on the summaries and collecting logs; means for analyzing the collected logs and converting them into an easy-to-understand format; means for providing the converted logs to an operator; and means installed on a mobile device that includes an application for processing the inquiries and displaying the log analysis results. This allows maintenance staff to quickly and efficiently identify the cause of robot failures and take appropriate action. Furthermore, the automatic summarization of inquiries and automatic analysis of log data improves work efficiency.

[0465] "User" means a person or entity that queries the System.

[0466] "Inquiry content" refers to detailed information about a question or problem that a user sends to the system.

[0467] "Means for receiving" refers to the method by which the system receives inquiries from users.

[0468] "Means of summarizing" refers to a method for concisely summarizing the content of inquiries received.

[0469] "Relevant computer commands" are system commands that are executed based on the abstracted query.

[0470] A "log" is recorded information such as system operation history and error messages.

[0471] "Means of collection" refers to the method for collecting the necessary log data.

[0472] "Means of analysis" refers to the method of analyzing collected log data to identify problems and solutions.

[0473] "Means for providing" refers to a method for presenting analysis results and other information to an operator.

[0474] An "operator" is a person who manages the system and responds to inquiries from users.

[0475] A "mobile device" is a portable electronic device such as a smartphone or tablet.

[0476] "Installation" is the act of introducing application software onto specific hardware.

[0477] An "application" is a software program designed to provide a particular function or service.

[0478] "Generative AI" is an artificial intelligence technology that automates the analysis of inquiry content and logs.

[0479] The present invention relates to a system for quickly and efficiently dealing with robot failures in a factory. An embodiment of this system will be described in detail below.

[0480] The entire system consists of a server that accepts inquiries from users, a server that summarizes the inquiries using generative AI, a means for executing related computer commands based on the summarized content and collecting logs, a means for analyzing the collected logs and converting them into an easy-to-understand format, a means for providing the converted content to the operator, and an application installed on a mobile device.

[0481] First, a user uses a mobile device to input an inquiry about a robot malfunction or operational problem and send it to the server. For example, a user might send an inquiry such as, "My robot has stopped. What should I do?"

[0482] The server summarizes the received query using a generative AI model. In this case, OpenAI's GPT-3 is used as the AI ​​model. If the query is "My robot has stopped. What should I do?", the summary will be "My robot has stopped." Based on this summary, the system selects an appropriate computer command. For example, it could execute a command to "check the robot's status" and collect related log data.

[0483] Next, the collected log data is analyzed again using generative AI and converted into a format that is easy for users to understand. For example, if the log contains information such as "A motor error has occurred. The temperature is too high," the analysis result will be converted into a simple explanation such as "The robot's motor is experiencing an error. Please check the motor temperature and cool it if necessary." This process also uses OpenAI's GPT-3.

[0484] The converted information is provided to the operator, who then provides feedback on countermeasures to the user via a mobile device, allowing the user to quickly and accurately resolve the robot's problems.

[0485] As a concrete example, the following is an example of a prompt sentence to be input to a generative AI model:

[0486] Summary of your inquiry:

[0487] Please summarize your inquiry in one sentence:

[0488] My robot has stopped working, what should I do?

[0489] Log analysis:

[0490] Please analyze the following logs and clearly explain the problem and solution:

[0491] Robot motor error - Memory error detected - Temperature rise

[0492] This system enables factory maintenance staff, even those without advanced skills, to quickly identify the cause of a robot malfunction and take appropriate action, thereby improving productivity and enabling efficient malfunction response.

[0493] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0494] Step 1:

[0495] The user uses a mobile terminal to input an inquiry about a robot malfunction or operational problem and clicks the send button. At this point, the input is the inquiry entered by the user into the terminal, and the output is the inquiry data sent to the server. The server receives this data.

[0496] Step 2:

[0497] The server inputs the received query content into a generative AI model (for example, OpenAI's GPT-3) and summarizes the query content in one sentence. The prompt uses the format "Please summarize the following query content in one sentence:\n\n{query content}\n". The input is the received query data, and data processing is a summary process by the generative AI. The output is the summarized query content.

[0498] Step 3:

[0499] The server selects an appropriate computer command based on the abstract. For example, for the abstract "The robot has stopped," it selects the command sudo systemctl status robot_service to check the robot's status. The input is the abstracted query, and the output is the selected computer command.

[0500] Step 4:

[0501] The server executes the selected computer command and collects log data. Specifically, it collects the output obtained by executing the command (e.g., service status information obtained as a result of sudo systemctl status robot_service) as a log. The input is the selected computer command, the data calculation is the command execution process, and the output is the collected log data.

[0502] Step 5:

[0503] The collected log data is again input into the generative AI model, where it is analyzed and converted into an easy-to-understand format. The prompt sentence is "Analyze the following log and provide a clear explanation of the problem and solution:\n\n{log data}\n". The input is the collected log data, and the output is the analyzed result (e.g., "An error has occurred in the robot's motor. Check the motor temperature and cool it if necessary").

[0504] Step 6:

[0505] The server provides the analysis results to the operator. Based on this information, the operator provides appropriate feedback on countermeasures to the user via their mobile device. The input is the analysis results, and the output is specific countermeasure information provided to the user. The operator communicates this information to the user, who then uses it to solve the robot's problems.

[0506] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0507] This invention combines a system that accepts inquiries from users, summarizes the contents, and collects and analyzes related logs with an emotion engine that recognizes the emotions of the user. Detailed embodiments of this system are described below.

[0508] First, the user inputs the inquiry using the terminal and clicks the send button. The inquiry includes a detailed description of the technical problem or malfunction. The terminal then sends the user's input information to the server.

[0509] The server stores the received inquiry and sends it to the generation AI, which summarizes the inquiry and converts it into a concise format. This process allows the operator to grasp a lot of information in a short amount of time.

[0510] Next, the server uses an emotion engine to recognize the user's emotion from the inquiry. The emotion engine uses natural language processing technology to analyze the emotion from the user's sentence. For example, if the user says "I'm in a lot of trouble," the emotion engine will recognize emotions such as "stress" and "urgent need."

[0511] The emotions recognized by the emotion engine are used to determine the priority of the inquiry. For example, if the inquiry is highly angry or stressed, it will be treated as a high priority. The emotion engine can also advise the operator on the appropriate response method based on the recognized emotion.

[0512] Based on the summary and the perceived emotion, the server selects the relevant computer command. For example, if the summary says "Service has stopped" and the user is showing high stress, the server needs to respond quickly, so it will immediately run the sudo systemctl status some_service command and collect the necessary logs.

[0513] The collected logs are then analyzed using the generation AI and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation such as "The service has stopped due to lack of memory. Check the memory usage and restart it if necessary."

[0514] Finally, the server sends the notification content adjusted according to the generated explanation and the recognized emotion to the operator's terminal. The operator responds to the user's inquiry promptly and appropriately based on the provided explanation and emotion information. The operator then provides the user with specific measures via the terminal, and the user can follow the instructions to resolve the problem.

[0515] As a concrete example, the following shows the flow when a user inquires, "The service has stopped. What should I do?" and expresses the emotion, "I'm very troubled." The server receives this inquiry, and the generation AI summarizes it as "The service has stopped." The emotion engine then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating, "Some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick response, and the user follows the instructions to implement the response and resolves the problem.

[0516] In this way, the present invention recognizes the user's emotions and takes them into consideration when responding to inquiries, thereby reducing the burden on operators and increasing user satisfaction.

[0517] The processing flow will be explained below.

[0518] Step 1:

[0519] The user uses the terminal to enter the inquiry details and clicks the send button.

[0520] Step 2:

[0521] The terminal sends the inquiry to the server.

[0522] Step 3:

[0523] The server receives the query and stores it in a database.

[0524] Step 4:

[0525] The server sends the received query content to the generation AI, which summarizes the query content.

[0526] Step 5:

[0527] The generation AI summarizes the query, and the server receives the summary.

[0528] Step 6:

[0529] The server sends the summarized query content to the emotion engine to analyze the user's emotions.

[0530] Step 7:

[0531] The emotion engine recognizes the user's emotion from the summary content and sends the result to the server.

[0532] Step 8:

[0533] The server selects relevant computer commands based on the recognized emotions and summary content.

[0534] Step 9:

[0535] The server executes selected computer commands and collects logs.

[0536] Step 10:

[0537] The server sends the collected logs to the generation AI, requesting it to analyze the logs and generate easy-to-understand explanations.

[0538] Step 11:

[0539] The generation AI analyzes the logs, generates easy-to-understand explanations, and sends the results to the server.

[0540] Step 12:

[0541] The server sends a notification to the operator's terminal based on the generated description and the recognized emotion.

[0542] Step 13:

[0543] An operator uses the terminal to check the provided explanation and emotional information and inform the user of a response plan.

[0544] Step 14:

[0545] The user uses the terminal and follows the instructions of the operator to carry out operations to solve the problem.

[0546] Step 15:

[0547] The user reports that the problem has been resolved to the operator, and the result is recorded on the server.

[0548] Example 2

[0549] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0550] Conventional inquiry response systems have difficulty quickly and appropriately summarizing user inquiries, recognizing emotions, and determining response priorities. Furthermore, converting collected logs into an easy-to-understand format is time-consuming, increasing the burden on operators. This raises concerns about a decline in user satisfaction.

[0551] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting a user's inquiry, means for summarizing the accepted inquiry using a generative AI model, means for executing related computer commands based on the summarized content and collecting logs, means for analyzing the collected logs using the generative AI model and converting them into an easy-to-understand format, emotion recognition means for recognizing the user's emotion from the inquiry, means for determining the priority of the inquiry based on the recognized emotion, means for providing notification content according to the priority, and means for providing the converted content to the operator. This makes it possible to quickly and appropriately summarize the user's inquiry, recognize the emotion and determine the priority of the response, convert the collected logs into an easy-to-understand format, reduce the burden on the operator, and improve user satisfaction.

[0552] A "user" is a person or entity that uses the system to make an inquiry.

[0553] A "terminal" is an electronic device that a user operates to input and send inquiry details.

[0554] A "server" is a central system that processes and responds to inquiries received.

[0555] An "inquiry" is a message containing a problem or question that a user sends to the system.

[0556] A "generative AI model" is an artificial intelligence that learns from large amounts of data and is used to summarize and analyze user input.

[0557] "Summarization" is the process or result of converting detailed query content into a concise form.

[0558] A "computer command" is an instruction that a server executes to initiate a particular operation or process.

[0559] A "log" is recorded data about the operating status of a system or service and events that have occurred.

[0560] "Emotion recognition means" refers to a technology or system for analyzing and recognizing emotions from the content of a user's inquiry.

[0561] "Priority" is an index for determining the urgency and importance of a response based on the content of the inquiry and the user's feelings.

[0562] An "operator" is a person in charge of managing the system and dealing directly with users.

[0563] "Notification content" is information about the processing result, the user's feelings, and priority that is sent by the server to the operator.

[0564] "Analysis" is the process or result of examining data or logs in detail and extracting useful information.

[0565] "Converting into a format" means reconstructing collected data and logs into a format that is easy for operators to understand.

[0566] A "system" is a collection of hardware and software configured to perform a particular function.

[0567] The present invention provides a system that efficiently summarizes the content of inquiries from users, analyzes related logs, and recognizes the user's emotions to determine the priority of responses. Specific embodiments of this system are described below.

[0568] First, the user uses the terminal to enter the inquiry content and clicks the send button. The inquiry content includes a detailed description of the technical problem or malfunction. For example, the user might enter "The service has stopped. What should I do?" The terminal then sends the user's input information to the server. This transmission is done using an HTTP request or an API call.

[0569] The server stores the received query content in a database and sends the content to a generative AI model. An example of a generative AI model is GPT-3, a widely used artificial intelligence model. This model learns from large amounts of text data and has the ability to automatically summarize the input text. The generative AI model summarizes the query content in a concise format, such as "The service has been stopped."

[0570] Next, the server uses an emotion recognition means to recognize the user's emotion from the inquiry. Natural language processing technologies such as IBM Watson's Tone Analyzer are used as emotion recognition means. For example, if the user says "I'm in a lot of trouble," the emotion recognition means will recognize the emotion as "urgent need."

[0571] The server determines the priority of the query based on the emotion recognition results. For example, if the query indicates high anger or stress, it is treated as a high priority. The server then selects and executes the relevant computer command and collects the necessary logs. For example, if the summary reads "Service has stopped" and the user indicates high stress, the server will need to respond quickly, so it will run the sudo systemctl status some_service command and collect logs.

[0572] The collected logs are then analyzed using the generative AI model and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generative AI model converts this information into a simple explanation such as "The service has stopped due to lack of memory. Please check your memory usage and restart it if necessary."

[0573] Finally, the server sends the notification content, adjusted according to the generated explanation and the recognized emotion, to the operator's terminal. The operator responds promptly and appropriately to the user's inquiry based on the provided explanation and emotion information. The operator then provides the user with specific solutions via the terminal, allowing the user to solve the problem by following the instructions. In this way, the present invention recognizes the user's emotion and takes it into consideration when responding to inquiries, thereby reducing the burden on the operator and increasing user satisfaction.

[0574] As a concrete example, let's look at the flow when a user inquires, "The service has stopped. What should I do?" and expresses the emotion, "I'm very troubled." The server receives this inquiry, and the generative AI summarizes it as "The service has stopped." The emotion recognition means then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating, "Some_service has stopped due to insufficient memory." The generative AI model converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick solution, and the user can follow the instructions to implement the solution and resolve the problem.

[0575] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0576] Step 1:

[0577] The user uses the terminal to enter the inquiry and clicks the send button. The data entered is a specific problem or question. For example, "The service has stopped. What should I do?" is entered and sent. This is the input.

[0578] Step 2:

[0579] The terminal sends the inquiry entered by the user to the server. The specific operation performed at this time is to send data via an HTTP request. The input data is the inquiry entered by the user, and the output data is text data sent to the server.

[0580] Step 3:

[0581] The server stores the received query in a database. The input data is the query received from the terminal, and the output data is the query data stored in the database. Specifically, the server writes data to the database using SQL queries, etc.

[0582] Step 4:

[0583] The server sends the saved query content to the generative AI model. The input data is the query content saved in the database, and the output data is the text data sent to the generative AI model. Specifically, data is sent to the generative AI model using an HTTP request or API call.

[0584] Step 5:

[0585] The generative AI model summarizes the query content. The input data is the query content sent from the server, and the output data is the summarized text. Specifically, the generative AI model analyzes the text, extracts the important parts, and converts them into a concise form. For example, a summary such as "The service has been stopped" is generated.

[0586] Step 6:

[0587] The server uses the emotion recognition means to recognize the user's emotion from the summarized inquiry content. The input data is the summarized inquiry content, and the output data is the recognized emotion information. Specifically, the emotion recognition means analyzes the text using natural language processing (NLP) technology and extracts emotions. For example, an emotion such as "very troubled" is recognized as "urgent."

[0588] Step 7:

[0589] The server determines the priority of the inquiry based on the recognized emotion data. The input data is the recognized emotion information, and the output data is the priority information of the inquiry. Specifically, the server evaluates the emotion data and classifies the priority as high, medium, low, etc. For example, if the emotion data is recognized as "urgent," the inquiry is treated as high priority.

[0590] Step 8:

[0591] The server selects and executes the relevant computer command based on priority. The input data is the query priority information, and the output data is the execution result of the executed command. Specific operations include running a shell command to check the system status. For example, the sudo systemctl status some_service command is executed, and a log stating "some_service has stopped due to insufficient memory" is collected.

[0592] Step 9:

[0593] The collected logs are then analyzed again using the generative AI model and converted into an easy-to-understand format. The input data is the collected logs, and the output data is the analyzed simple explanatory text. Specifically, the generative AI model analyzes the logs and converts them into a format that is easy for users and operators to understand. For example, it generates an explanation such as "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary."

[0594] Step 10:

[0595] The server then sends the notification content, adjusted according to the generated explanation and the recognized emotion, to the operator's terminal. The input data is a simple explanation text and emotion information, and the output data is the notification content provided to the operator. Specifically, the server sends an appropriate notification to the operator's terminal, and the operator responds to the user based on that.

[0596] Step 11:

[0597] The operator will then provide the user with specific countermeasures based on the provided explanation. The input data is the explanation provided by the server, and the output data is feedback to the user. Specifically, the operator will tell the user to "check memory usage and reboot if necessary."

[0598] Step 12:

[0599] The user takes specific actions to solve the problem according to the feedback from the operator. The input data are instructions from the operator, and the output data are the measures taken and their results. Specific actions include the user checking memory usage on the terminal and restarting the service if necessary.

[0600] In this way, the system recognizes the user's emotions and takes them into consideration when responding to inquiries, thereby reducing the burden on operators and increasing user satisfaction.

[0601] (Application example 2)

[0602] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0603] In modern security services, it is extremely important to quickly and accurately handle user-reported issues. However, when user reports are verbose or emotionally charged, a system is needed to efficiently summarize them and respond quickly. Furthermore, responses that do not take user emotions into consideration can lead to significant dissatisfaction and further problems. Therefore, there is a need for systems that can understand user emotions and respond appropriately based on those emotions.

[0604] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for summarizing the accepted inquiry, means for executing related computer commands based on the summarized inquiry and collecting logs, means for analyzing the logs and converting them into an easy-to-understand format, means for recognizing the user's emotion based on the summarized inquiry and the analyzed log, means for determining a priority according to the recognized emotion, and means for providing the converted content and priority information to an operator. This enables a quick and appropriate response that takes the user's emotion into consideration.

[0605] "User" means any person or entity that submits an inquiry using this system.

[0606] "Inquiry" is the details of the problem or question reported by the user.

[0607] A "summarization means" is a technology that has the ability to convert the content of a query into a concise format.

[0608] "Generative AI" is an artificial intelligence technology for automatically summarizing and analyzing inquiry content.

[0609] A "computer command" is an instruction to perform a particular task.

[0610] A "log" is a record of system actions and events.

[0611] "Means of analysis" refers to the technology used to analyze collected logs and convert them into an easy-to-understand format.

[0612] "Means for recognizing emotions" refers to technology that determines the emotions of users based on their inquiries.

[0613] The "means for determining priority" is a function that determines the order of processing priorities based on the recognized emotions.

[0614] An "operator" is a person who operates the system and responds to user inquiries.

[0615] "Transformed content" is information that has been processed through summarization and analysis.

[0616] "Priority information" is information about the priority of processing determined by recognizing emotions.

[0617] This invention combines a system that accepts inquiries from users, summarizes the contents, and collects and analyzes related logs with an emotion engine that recognizes the emotions of the user. Detailed embodiments of this system are described below.

[0618] First, the user inputs the inquiry using the terminal and clicks the send button. The inquiry includes a detailed description of the technical problem or malfunction. The terminal then sends the user's input information to the server.

[0619] The server stores the received inquiry and sends it to the generation AI, which summarizes the inquiry and converts it into a concise format. This process allows the operator to grasp a lot of information in a short amount of time.

[0620] Next, the server uses an emotion engine to recognize the user's emotion from the inquiry. The emotion engine uses natural language processing technology to analyze the emotion from the user's sentence. For example, if the user says "I'm in a lot of trouble," the emotion engine will recognize emotions such as "stress" and "urgent need."

[0621] The emotions recognized by the emotion engine are used to determine the priority of the inquiry. For example, if the inquiry is highly angry or stressed, it will be treated as a high priority. The emotion engine can also advise the operator on the appropriate response method based on the recognized emotion.

[0622] Based on the summary and the perceived emotion, the server selects the relevant computer command. For example, if the summary says "Service has stopped" and the user is showing high stress, the server needs to respond quickly, so it will immediately run the sudo systemctl status some_service command and collect the necessary logs.

[0623] The collected logs are then analyzed using the generation AI and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation such as "The service has stopped due to lack of memory. Check the memory usage and restart it if necessary."

[0624] Finally, the server sends the notification content adjusted according to the generated explanation and the recognized emotion to the operator's terminal. The operator responds to the user's inquiry promptly and appropriately based on the provided explanation and emotion information. The operator then provides the user with specific measures via the terminal, and the user can follow the instructions to resolve the problem.

[0625] As a concrete example, the following shows the flow when a user reports that "my account may have been compromised" and expresses the emotion "very troubled." The server receives this inquiry, and the generation AI summarizes it as "my account is suspected to have been compromised." The emotion engine then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating "some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick response, and the user follows the instructions to implement the response and resolve the problem.

[0626] As a result, the present invention can recognize the user's emotions and respond to inquiries taking these into consideration, thereby reducing the burden on operators and increasing user satisfaction.

[0627] It also uses a generative AI model to summarize the query, an emotion engine to recognize emotions, and then executes the associated computer command. For each step, the following prompts are available:

[0628] Inquiry:

[0629] -------

[0630] I think my account may have been accessed illegally. I've noticed some suspicious activity since this morning. I'm in a lot of trouble.

[0631] summary:

[0632] ------

[0633] 1. Suspected unauthorized access to your account.

[0634] 2. Suspicious activity is observed.

[0635] 3. Users are very confused.

[0636] Emotion recognition:

[0637] --------------

[0638] Very confused (urgent)

[0639] The hardware used includes servers and devices, while the software includes generative AI models, emotion engines, and natural language processing technologies. The application of these technologies enables efficient and emotion-sensitive user support.

[0640] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0641] Step 1:

[0642] The user uses the terminal to input the inquiry content and clicks the send button. The input inquiry content (data) is sent from the terminal to the server. The input is the user's report content, and the output is the inquiry data sent to the server.

[0643] Step 2:

[0644] The server stores the query content received and sends it to the generative AI model, which then summarizes the query content. The input here is the query data received from the user, and the output is the summary data converted into a concise format.

[0645] Step 3:

[0646] The server sends the summarized query content to the emotion engine to recognize the user's emotion. The emotion engine uses natural language processing technology to analyze emotions. The input is the summary data, and the output is emotion data such as "confusion" or "urgency."

[0647] Step 4:

[0648] The server determines the priority of the query based on the recognized emotion data. For example, if the emotion is "urgent" or "angry," the query is set as a high priority. The input is emotion data, and the output is priority information.

[0649] Step 5:

[0650] The server selects and executes relevant computer commands based on the summary content and priority information. For example, run the command sudo systemctl status some_service to collect the required logs. The input is the summary data and priority information, and the output is the collected log data.

[0651] Step 6:

[0652] The server sends the collected log data to the generative AI model, which analyzes the logs and converts them into an easy-to-understand format. For example, it may convert the information into "The service has stopped due to insufficient memory." The input is the log data, and the output is simple explanatory data.

[0653] Step 7:

[0654] The server sends the generated explanation data and priority information to the operator's terminal. The operator responds promptly and appropriately to the user's inquiry based on the provided explanation and emotion information. The input is the explanation data and priority information, and the output is the information notified to the operator.

[0655] Step 8:

[0656] The operator communicates specific countermeasures to the user via the terminal. The user can then follow the instructions to implement the countermeasures and solve the problem. The input is the instructions from the operator, and the output is the countermeasure implemented by the user.

[0657] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0658] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0659] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0660] [Third embodiment]

[0661] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0662] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0663] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0664] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0665] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0666] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0667] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0668] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0669] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0670] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0671] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0672] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0673] The present invention relates to a system that receives inquiries from users, summarizes the inquiries, and collects and analyzes related logs. Detailed embodiments of this system will be described below.

[0674] First, the user sends a message regarding the system malfunction to the inquiry desk. The user enters the inquiry content using a terminal and clicks the send button to make the inquiry. This content is sent to the server, which receives it and stores it in a database.

[0675] The server then begins the process of summarizing the received inquiry. Using a generation AI, the server automatically summarizes the inquiry based on the necessary information. For example, if a user sends a query such as "My service has stopped. What should I do?", the generation AI converts this into a summary such as "My service has stopped."

[0676] Based on the summary, the server selects the relevant computer command. For example, if the summary is "Service has stopped," the server selects the command sudo systemctl status some_service. This command is executed within the server, and the relevant logs are collected as output.

[0677] The collected logs are then analyzed again using the generation AI. The server inputs the log data into the generation AI, and the server converts the resulting information into an easy-to-understand format. For example, if the log contains the content "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation: "The service has stopped due to lack of memory. Please check your memory usage and restart if necessary."

[0678] Finally, the server provides the generated explanation to the operator, who then responds promptly and appropriately to the user's inquiry based on the explanation. The operator then informs the user of the solution via the terminal, and the user can follow the solution to solve the problem.

[0679] As a concrete example, the flow when a user makes an inquiry saying, "The service has stopped. What should I do?" is shown below. The server receives this inquiry and the generation AI summarizes it as "The service has stopped." The server then selects and executes the sudo systemctl status some_service command, collecting a log stating, "Some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation saying, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. The operator conveys this explanation to the user, who then follows the instructions to take measures and resolve the problem.

[0680] In this way, the present invention enables even less skilled operators to isolate and handle advanced system faults, thereby enabling the efficient use of expert resources.

[0681] The processing flow will be explained below.

[0682] Step 1:

[0683] The user uses the terminal to enter the inquiry details and clicks the send button.

[0684] Step 2:

[0685] The terminal transmits the input inquiry to the server.

[0686] Step 3:

[0687] The server receives the query and stores it in a database.

[0688] Step 4:

[0689] The server sends the received query to the generation AI, which generates a summary.

[0690] Step 5:

[0691] The server selects the appropriate computer command based on the generated summary.

[0692] Step 6:

[0693] The server executes selected computer commands and collects relevant logs.

[0694] Step 7:

[0695] The server sends the collected logs to a generation AI, which generates an easy-to-understand explanation.

[0696] Step 8:

[0697] The server sends the generated explanation to the operator's terminal for display.

[0698] Step 9:

[0699] The operator will inform the user of the countermeasures via the terminal.

[0700] Step 10:

[0701] The user follows the operator's instructions and performs operations to solve the problem through the terminal.

[0702] Step 11:

[0703] After the user has resolved the problem, he reports the results to the operator, who then records the results on the server.

[0704] Example 1

[0705] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0706] There is a need to respond to user inquiries quickly and effectively and identify the cause of system failures. However, with conventional methods, manually summarizing the content of inquiries and collecting and analyzing logs takes a great deal of time and effort, making it difficult for operators without specialized knowledge to provide advanced responses. Furthermore, in situations where a quick response is required, delays can result in a decrease in user satisfaction.

[0707] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0708] In this invention, the server includes means for accepting inquiries from users, means for automatically summarizing the accepted inquiries using a generative AI model, means for executing related computer resource management commands based on the summarized content and collecting logs, means for analyzing the collected log data using the generative AI model and converting it into an easy-to-understand format, and means for providing the converted content to an operator, thereby enabling even operators without specialized knowledge to respond to user inquiries quickly and accurately.

[0709] "User" refers to an individual or company representative who queries the system.

[0710] "Inquiry content" refers to information entered and sent by a user regarding a system malfunction or question.

[0711] A "generative AI model" refers to an artificial intelligence algorithm that generates and analyzes text based on large amounts of data.

[0712] "Summary" refers to a sentence that briefly summarizes the main information of the inquiry.

[0713] "Computer resource management commands" refer to instructions executed by a server to check or manipulate the state of the system.

[0714] A "log" refers to data that records various events and activities that occur on a computer system.

[0715] "Analysis" refers to the process of examining collected log data in detail to identify the cause of the problem and how to solve it.

[0716] "Operator" refers to the person in charge of operating the system and dealing with users.

[0717] MODE FOR CARRYING OUT THE INVENTION

[0718] The present invention relates to a system that receives inquiries from users, summarizes the inquiries, and collects and analyzes related logs. Detailed embodiments of this system will be described below.

[0719] First, the user uses their own device (PC or smartphone) to enter the inquiry and clicks the send button. For example, if the user enters something like "The service has stopped. What should I do?", the inquiry is sent from the user's device to the server.

[0720] The server stores the query received from the user in a database. The stored data includes not only the query content but also metadata such as date and time and user ID. This storage process is performed using a database management system on the server (e.g., MySQL, PostgreSQL, etc.).

[0721] The server then inputs the saved query content into a generative AI model for summarization. This summarization process uses natural language processing techniques to concisely summarize the key information in the query content. For example, in response to a query such as "The service has stopped. What should I do?", the generative AI model generates the summary "The service has stopped."

[0722] Based on the summary, the server selects the appropriate computer resource management command. This selection process is performed by a rule-based engine or script within the server. For example, for the summary "Service has stopped," the server selects the command sudo systemctl status some_service.

[0723] The server executes the selected commands and collects the resulting logs, which contain important information about the system's state and are stored using an on-server log management system (e.g., ELK stack, Splunk, etc.).

[0724] The collected log data is then input back into the generative AI model for analysis. During this analysis process, the log contents are examined in detail to identify the cause of the problem and how to resolve it. The generative AI model analyzes the log contents and extracts information such as "some_service has stopped due to insufficient memory."

[0725] The server generates an easy-to-understand explanation for the user based on the analysis results of the generative AI model. The generative AI model converts the analysis results into a simple explanation such as "The service has stopped due to insufficient memory. Please check your memory usage and restart if necessary."

[0726] Finally, the server provides the generated explanation to the operator. The operator responds to the user based on the explanation provided. The operator communicates the explanation to the user through their own terminal and provides specific countermeasures. For example, the operator might instruct the user, "The service has stopped due to insufficient memory. Please check the memory usage and restart if necessary."

[0727] As a concrete example, let's consider the case where a user makes an inquiry saying, "The service has stopped. What should I do?" The server receives the inquiry and summarizes it as "The service has stopped" using the generative AI model. The server then selects and executes the sudo systemctl status some_service command, collecting a log stating, "Some_service has stopped due to insufficient memory." The generative AI model converts this log into an explanation saying, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides this to the operator. The operator then conveys this explanation to the user, who then follows the instructions to take measures and resolve the problem.

[0728] Below are some examples of prompts for generative AI models:

[0729] "When a user asks, 'My service is down, what do I do?' Summarize and create a concise answer."

[0730] "Based on the log data 'some_service has stopped due to insufficient memory', please generate an easy-to-understand explanation for the user."

[0731] As described above, the present invention enables even operators without specialized knowledge to respond to user inquiries quickly and accurately.

[0732] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0733] Step 1:

[0734] The user inputs a query into the terminal and sends it.

[0735] The user enters the inquiry into their own terminal and clicks the send button. For example, they enter "The service has stopped. What should I do?" The entered inquiry is sent from the terminal to the server via the network.

[0736] Input: User inquiry (e.g. "My service has stopped. What should I do?").

[0737] Output: The query is sent to the server.

[0738] Step 2:

[0739] The server receives the query and stores it in a database.

[0740] The server receives the inquiry sent by the user and temporarily stores it in memory.Then, it stores the inquiry in a database.At this time, in addition to the inquiry content, it also stores metadata such as the date and time and user ID.

[0741] Input: User's inquiry.

[0742] Output: Query details and metadata stored in a database.

[0743] Step 3:

[0744] The server automatically summarizes the query using a generative AI model.

[0745] The server retrieves the query content from the database and inputs it into the generative AI model. The generative AI model analyzes the query content, extracts key information, and generates a summary. For example, the query "The service has stopped. What should I do?" is summarized as "The service has stopped."

[0746] Input: The query retrieved from the database.

[0747] Output: A summary from the generative AI model (e.g., "The service has stopped").

[0748] Step 4:

[0749] The server selects relevant computer resource management commands based on the abstract content.

[0750] The server selects an appropriate command based on the summary obtained from the generative AI model. For example, for the summary "The service has stopped," the command "sudo systemctl status some_service" is selected. This selection is performed by a rule-based engine or script within the server.

[0751] Input: A summary from a generative AI model.

[0752] Output: The selected computer resource management command (e.g., sudo systemctl status some_service).

[0753] Step 5:

[0754] The server executes the selected command and collects the logs.

[0755] The server runs the selected command and collects logs as its output, for example, run the command sudo systemctl status some_service to get log data about the status of the service.

[0756] Input: Selected computer resource management command.

[0757] Output: The captured log data.

[0758] Step 6:

[0759] The logs collected by the server are analyzed using a generative AI model.

[0760] The server inputs the collected log data into a generative AI model for analysis. The generative AI model then examines the log contents in detail to identify the cause of the problem. For example, it might analyze and extract information such as "some_service has stopped due to insufficient memory."

[0761] Input: Collected log data.

[0762] Output: Analysis results from the generative AI model (e.g., "some_service has stopped due to lack of memory").

[0763] Step 7:

[0764] The server generates an easy-to-understand explanation for the user based on the analysis results of the generated AI model.

[0765] The server generates an explanation in a form that is easy for the user to understand based on the analysis results of the generative AI model. The generative AI model converts the analysis results into an explanation such as "The service has stopped due to insufficient memory. Please check your memory usage and restart if necessary."

[0766] Input: Analysis results of the generative AI model.

[0767] Output: A generated, user-friendly explanation (e.g., "The service has stopped due to low memory. Please check your memory usage and restart if necessary").

[0768] Step 8:

[0769] The server provides the generated explanation to the operator.

[0770] The server provides the generated explanation to an interface accessible to the operator, who then checks the explanation provided by the server on his / her terminal.

[0771] Input: The generated description.

[0772] Output: The description provided to the operator.

[0773] Step 9:

[0774] The operator responds to the user based on the explanation.

[0775] The operator responds to the user based on the explanation provided by the server and instructs the user on specific measures to take, for example, "The service has stopped due to a lack of memory. Please check the memory usage and restart if necessary."

[0776] Input: A description provided by the server.

[0777] Output: Specific measures provided to the user.

[0778] (Application example 1)

[0779] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0780] Modern factories employ a large number of robots, and when one of these robots breaks down, a rapid and appropriate response is required. However, detecting a robot's malfunction and identifying its cause requires a high level of specialized knowledge, making a rapid response often difficult. Furthermore, it takes time and effort for maintenance staff to manually analyze all log data and find the optimal solution. As a result, in many factories, responding to robot malfunctions takes a long time, which can lead to reduced productivity. Furthermore, analyzing complex log data and summarizing inquiries requires a lot of manual work, making efficient operation difficult. A system that can solve these issues is needed.

[0781] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0782] In this invention, the server includes: means for accepting inquiries from users; means for summarizing the received inquiries; means for executing related computer commands based on the summaries and collecting logs; means for analyzing the collected logs and converting them into an easy-to-understand format; means for providing the converted logs to an operator; and means installed on a mobile device that includes an application for processing the inquiries and displaying the log analysis results. This allows maintenance staff to quickly and efficiently identify the cause of robot failures and take appropriate action. Furthermore, the automatic summarization of inquiries and automatic analysis of log data improves work efficiency.

[0783] "User" means a person or entity that queries the System.

[0784] "Inquiry content" refers to detailed information about a question or problem that a user sends to the system.

[0785] "Means for receiving" refers to the method by which the system receives inquiries from users.

[0786] "Means of summarizing" refers to a method for concisely summarizing the content of inquiries received.

[0787] "Relevant computer commands" are system commands that are executed based on the abstracted query.

[0788] A "log" is recorded information such as system operation history and error messages.

[0789] "Means of collection" refers to the method for collecting the necessary log data.

[0790] "Means of analysis" refers to the method of analyzing collected log data to identify problems and solutions.

[0791] "Means for providing" refers to a method for presenting analysis results and other information to an operator.

[0792] An "operator" is a person who manages the system and responds to inquiries from users.

[0793] A "mobile device" is a portable electronic device such as a smartphone or tablet.

[0794] "Installation" is the act of introducing application software onto specific hardware.

[0795] An "application" is a software program designed to provide a particular function or service.

[0796] "Generative AI" is an artificial intelligence technology that automates the analysis of inquiry content and logs.

[0797] The present invention relates to a system for quickly and efficiently dealing with robot failures in a factory. An embodiment of this system will be described in detail below.

[0798] The entire system consists of a server that accepts inquiries from users, a server that summarizes the inquiries using generative AI, a means for executing related computer commands based on the summarized content and collecting logs, a means for analyzing the collected logs and converting them into an easy-to-understand format, a means for providing the converted content to the operator, and an application installed on a mobile device.

[0799] First, a user uses a mobile device to input an inquiry about a robot malfunction or operational problem and send it to the server. For example, a user might send an inquiry such as, "My robot has stopped. What should I do?"

[0800] The server summarizes the received query using a generative AI model. In this case, OpenAI's GPT-3 is used as the AI ​​model. If the query is "My robot has stopped. What should I do?", the summary will be "My robot has stopped." Based on this summary, the system selects an appropriate computer command. For example, it could execute a command to "check the robot's status" and collect related log data.

[0801] Next, the collected log data is analyzed again using generative AI and converted into a format that is easy for users to understand. For example, if the log contains information such as "A motor error has occurred. The temperature is too high," the analysis result will be converted into a simple explanation such as "The robot's motor is experiencing an error. Please check the motor temperature and cool it if necessary." This process also uses OpenAI's GPT-3.

[0802] The converted information is provided to the operator, who then provides feedback on countermeasures to the user via a mobile device, allowing the user to quickly and accurately resolve the robot's problems.

[0803] As a concrete example, the following is an example of a prompt sentence to be input to a generative AI model:

[0804] Summary of your inquiry:

[0805] Please summarize your inquiry in one sentence:

[0806] My robot has stopped working, what should I do?

[0807] Log analysis:

[0808] Please analyze the following logs and clearly explain the problem and solution:

[0809] Robot motor error - Memory error detected - Temperature rise

[0810] This system enables factory maintenance staff, even those without advanced skills, to quickly identify the cause of a robot malfunction and take appropriate action, thereby improving productivity and enabling efficient malfunction response.

[0811] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0812] Step 1:

[0813] The user uses a mobile terminal to input an inquiry about a robot malfunction or operational problem and clicks the send button. At this point, the input is the inquiry entered by the user into the terminal, and the output is the inquiry data sent to the server. The server receives this data.

[0814] Step 2:

[0815] The server inputs the received query content into a generative AI model (for example, OpenAI's GPT-3) and summarizes the query content in one sentence. The prompt uses the format "Please summarize the following query content in one sentence:\n\n{query content}\n". The input is the received query data, and data processing is a summary process by the generative AI. The output is the summarized query content.

[0816] Step 3:

[0817] The server selects an appropriate computer command based on the abstract. For example, for the abstract "The robot has stopped," it selects the command sudo systemctl status robot_service to check the robot's status. The input is the abstracted query, and the output is the selected computer command.

[0818] Step 4:

[0819] The server executes the selected computer command and collects log data. Specifically, it collects the output obtained by executing the command (e.g., service status information obtained as a result of sudo systemctl status robot_service) as a log. The input is the selected computer command, the data calculation is the command execution process, and the output is the collected log data.

[0820] Step 5:

[0821] The collected log data is again input into the generative AI model, where it is analyzed and converted into an easy-to-understand format. The prompt sentence is "Analyze the following log and provide a clear explanation of the problem and solution:\n\n{log data}\n". The input is the collected log data, and the output is the analyzed result (e.g., "An error has occurred in the robot's motor. Check the motor temperature and cool it if necessary").

[0822] Step 6:

[0823] The server provides the analysis results to the operator. Based on this information, the operator provides appropriate feedback on countermeasures to the user via their mobile device. The input is the analysis results, and the output is specific countermeasure information provided to the user. The operator communicates this information to the user, who then uses it to solve the robot's problems.

[0824] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0825] This invention combines a system that accepts inquiries from users, summarizes the contents, and collects and analyzes related logs with an emotion engine that recognizes the emotions of the user. Detailed embodiments of this system are described below.

[0826] First, the user inputs the inquiry using the terminal and clicks the send button. The inquiry includes a detailed description of the technical problem or malfunction. The terminal then sends the user's input information to the server.

[0827] The server stores the received inquiry and sends it to the generation AI, which summarizes the inquiry and converts it into a concise format. This process allows the operator to grasp a lot of information in a short amount of time.

[0828] Next, the server uses an emotion engine to recognize the user's emotion from the inquiry. The emotion engine uses natural language processing technology to analyze the emotion from the user's sentence. For example, if the user says "I'm in a lot of trouble," the emotion engine will recognize emotions such as "stress" and "urgent need."

[0829] The emotions recognized by the emotion engine are used to determine the priority of the inquiry. For example, if the inquiry is highly angry or stressed, it will be treated as a high priority. The emotion engine can also advise the operator on the appropriate response method based on the recognized emotion.

[0830] Based on the summary and the perceived emotion, the server selects the relevant computer command. For example, if the summary says "Service has stopped" and the user is showing high stress, the server needs to respond quickly, so it will immediately run the sudo systemctl status some_service command and collect the necessary logs.

[0831] The collected logs are then analyzed using the generation AI and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation such as "The service has stopped due to lack of memory. Check the memory usage and restart it if necessary."

[0832] Finally, the server sends the notification content adjusted according to the generated explanation and the recognized emotion to the operator's terminal. The operator responds to the user's inquiry promptly and appropriately based on the provided explanation and emotion information. The operator then provides the user with specific measures via the terminal, and the user can follow the instructions to resolve the problem.

[0833] As a concrete example, the following shows the flow when a user inquires, "The service has stopped. What should I do?" and expresses the emotion, "I'm very troubled." The server receives this inquiry, and the generation AI summarizes it as "The service has stopped." The emotion engine then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating, "Some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick response, and the user follows the instructions to implement the response and resolves the problem.

[0834] In this way, the present invention recognizes the user's emotions and takes them into consideration when responding to inquiries, thereby reducing the burden on operators and increasing user satisfaction.

[0835] The processing flow will be explained below.

[0836] Step 1:

[0837] The user uses the terminal to enter the inquiry details and clicks the send button.

[0838] Step 2:

[0839] The terminal sends the inquiry to the server.

[0840] Step 3:

[0841] The server receives the query and stores it in a database.

[0842] Step 4:

[0843] The server sends the received query content to the generation AI, which summarizes the query content.

[0844] Step 5:

[0845] The generation AI summarizes the query, and the server receives the summary.

[0846] Step 6:

[0847] The server sends the summarized query content to the emotion engine to analyze the user's emotions.

[0848] Step 7:

[0849] The emotion engine recognizes the user's emotion from the summary content and sends the result to the server.

[0850] Step 8:

[0851] The server selects relevant computer commands based on the recognized emotions and summary content.

[0852] Step 9:

[0853] The server executes selected computer commands and collects logs.

[0854] Step 10:

[0855] The server sends the collected logs to the generation AI, requesting it to analyze the logs and generate easy-to-understand explanations.

[0856] Step 11:

[0857] The generation AI analyzes the logs, generates easy-to-understand explanations, and sends the results to the server.

[0858] Step 12:

[0859] The server sends a notification to the operator's terminal based on the generated description and the recognized emotion.

[0860] Step 13:

[0861] An operator uses the terminal to check the provided explanation and emotional information and inform the user of a response plan.

[0862] Step 14:

[0863] The user uses the terminal and follows the instructions of the operator to carry out operations to solve the problem.

[0864] Step 15:

[0865] The user reports that the problem has been resolved to the operator, and the result is recorded on the server.

[0866] Example 2

[0867] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0868] Conventional inquiry response systems have difficulty quickly and appropriately summarizing user inquiries, recognizing emotions, and determining response priorities. Furthermore, converting collected logs into an easy-to-understand format is time-consuming, increasing the burden on operators. This raises concerns about a decline in user satisfaction.

[0869] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting a user's inquiry, means for summarizing the accepted inquiry using a generative AI model, means for executing related computer commands based on the summarized content and collecting logs, means for analyzing the collected logs using the generative AI model and converting them into an easy-to-understand format, emotion recognition means for recognizing the user's emotion from the inquiry, means for determining the priority of the inquiry based on the recognized emotion, means for providing notification content according to the priority, and means for providing the converted content to the operator. This makes it possible to quickly and appropriately summarize the user's inquiry, recognize the emotion and determine the priority of the response, convert the collected logs into an easy-to-understand format, reduce the burden on the operator, and improve user satisfaction.

[0870] A "user" is a person or entity that uses the system to make an inquiry.

[0871] A "terminal" is an electronic device that a user operates to input and send inquiry details.

[0872] A "server" is a central system that processes and responds to inquiries received.

[0873] An "inquiry" is a message containing a problem or question that a user sends to the system.

[0874] A "generative AI model" is an artificial intelligence that learns from large amounts of data and is used to summarize and analyze user input.

[0875] "Summarization" is the process or result of converting detailed query content into a concise form.

[0876] A "computer command" is an instruction that a server executes to initiate a particular operation or process.

[0877] A "log" is recorded data about the operating status of a system or service and events that have occurred.

[0878] "Emotion recognition means" refers to a technology or system for analyzing and recognizing emotions from the content of a user's inquiry.

[0879] "Priority" is an index for determining the urgency and importance of a response based on the content of the inquiry and the user's feelings.

[0880] An "operator" is a person in charge of managing the system and dealing directly with users.

[0881] "Notification content" is information about the processing result, the user's feelings, and priority that is sent by the server to the operator.

[0882] "Analysis" is the process or result of examining data or logs in detail and extracting useful information.

[0883] "Converting into a format" means reconstructing collected data and logs into a format that is easy for operators to understand.

[0884] A "system" is a collection of hardware and software configured to perform a particular function.

[0885] The present invention provides a system that efficiently summarizes the content of inquiries from users, analyzes related logs, and recognizes the user's emotions to determine the priority of responses. Specific embodiments of this system are described below.

[0886] First, the user uses the terminal to enter the inquiry content and clicks the send button. The inquiry content includes a detailed description of the technical problem or malfunction. For example, the user might enter "The service has stopped. What should I do?" The terminal then sends the user's input information to the server. This transmission is done using an HTTP request or an API call.

[0887] The server stores the received query content in a database and sends the content to a generative AI model. An example of a generative AI model is GPT-3, a widely used artificial intelligence model. This model learns from large amounts of text data and has the ability to automatically summarize the input text. The generative AI model summarizes the query content in a concise format, such as "The service has been stopped."

[0888] Next, the server uses an emotion recognition means to recognize the user's emotion from the inquiry. Natural language processing technologies such as IBM Watson's Tone Analyzer are used as emotion recognition means. For example, if the user says "I'm in a lot of trouble," the emotion recognition means will recognize the emotion as "urgent need."

[0889] The server determines the priority of the query based on the emotion recognition results. For example, if the query indicates high anger or stress, it is treated as a high priority. The server then selects and executes the relevant computer command and collects the necessary logs. For example, if the summary reads "Service has stopped" and the user indicates high stress, the server will need to respond quickly, so it will run the sudo systemctl status some_service command and collect logs.

[0890] The collected logs are then analyzed using the generative AI model and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generative AI model converts this information into a simple explanation such as "The service has stopped due to lack of memory. Please check your memory usage and restart it if necessary."

[0891] Finally, the server sends the notification content, adjusted according to the generated explanation and the recognized emotion, to the operator's terminal. The operator responds promptly and appropriately to the user's inquiry based on the provided explanation and emotion information. The operator then provides the user with specific solutions via the terminal, allowing the user to solve the problem by following the instructions. In this way, the present invention recognizes the user's emotion and takes it into consideration when responding to inquiries, thereby reducing the burden on the operator and increasing user satisfaction.

[0892] As a concrete example, let's look at the flow when a user inquires, "The service has stopped. What should I do?" and expresses the emotion, "I'm very troubled." The server receives this inquiry, and the generative AI summarizes it as "The service has stopped." The emotion recognition means then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating, "Some_service has stopped due to insufficient memory." The generative AI model converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick solution, and the user can follow the instructions to implement the solution and resolve the problem.

[0893] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0894] Step 1:

[0895] The user uses the terminal to enter the inquiry and clicks the send button. The data entered is a specific problem or question. For example, "The service has stopped. What should I do?" is entered and sent. This is the input.

[0896] Step 2:

[0897] The terminal sends the inquiry entered by the user to the server. The specific operation performed at this time is to send data via an HTTP request. The input data is the inquiry entered by the user, and the output data is text data sent to the server.

[0898] Step 3:

[0899] The server stores the received query in a database. The input data is the query received from the terminal, and the output data is the query data stored in the database. Specifically, the server writes data to the database using SQL queries, etc.

[0900] Step 4:

[0901] The server sends the saved query content to the generative AI model. The input data is the query content saved in the database, and the output data is the text data sent to the generative AI model. Specifically, data is sent to the generative AI model using an HTTP request or API call.

[0902] Step 5:

[0903] The generative AI model summarizes the query content. The input data is the query content sent from the server, and the output data is the summarized text. Specifically, the generative AI model analyzes the text, extracts the important parts, and converts them into a concise form. For example, a summary such as "The service has been stopped" is generated.

[0904] Step 6:

[0905] The server uses the emotion recognition means to recognize the user's emotion from the summarized inquiry content. The input data is the summarized inquiry content, and the output data is the recognized emotion information. Specifically, the emotion recognition means analyzes the text using natural language processing (NLP) technology and extracts emotions. For example, an emotion such as "very troubled" is recognized as "urgent."

[0906] Step 7:

[0907] The server determines the priority of the inquiry based on the recognized emotion data. The input data is the recognized emotion information, and the output data is the priority information of the inquiry. Specifically, the server evaluates the emotion data and classifies the priority as high, medium, low, etc. For example, if the emotion data is recognized as "urgent," the inquiry is treated as high priority.

[0908] Step 8:

[0909] The server selects and executes the relevant computer command based on priority. The input data is the query priority information, and the output data is the execution result of the executed command. Specific operations include running a shell command to check the system status. For example, the sudo systemctl status some_service command is executed, and a log stating "some_service has stopped due to insufficient memory" is collected.

[0910] Step 9:

[0911] The collected logs are then analyzed again using the generative AI model and converted into an easy-to-understand format. The input data is the collected logs, and the output data is the analyzed simple explanatory text. Specifically, the generative AI model analyzes the logs and converts them into a format that is easy for users and operators to understand. For example, it generates an explanation such as "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary."

[0912] Step 10:

[0913] The server then sends the notification content, adjusted according to the generated explanation and the recognized emotion, to the operator's terminal. The input data is a simple explanation text and emotion information, and the output data is the notification content provided to the operator. Specifically, the server sends an appropriate notification to the operator's terminal, and the operator responds to the user based on that.

[0914] Step 11:

[0915] The operator will then provide the user with specific countermeasures based on the provided explanation. The input data is the explanation provided by the server, and the output data is feedback to the user. Specifically, the operator will tell the user to "check memory usage and reboot if necessary."

[0916] Step 12:

[0917] The user takes specific actions to solve the problem according to the feedback from the operator. The input data are instructions from the operator, and the output data are the measures taken and their results. Specific actions include the user checking memory usage on the terminal and restarting the service if necessary.

[0918] In this way, the system recognizes the user's emotions and takes them into consideration when responding to inquiries, thereby reducing the burden on operators and increasing user satisfaction.

[0919] (Application example 2)

[0920] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0921] In modern security services, it is extremely important to quickly and accurately handle user-reported issues. However, when user reports are verbose or emotionally charged, a system is needed to efficiently summarize them and respond quickly. Furthermore, responses that do not take user emotions into consideration can lead to significant dissatisfaction and further problems. Therefore, there is a need for systems that can understand user emotions and respond appropriately based on those emotions.

[0922] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for summarizing the accepted inquiry, means for executing related computer commands based on the summarized inquiry and collecting logs, means for analyzing the logs and converting them into an easy-to-understand format, means for recognizing the user's emotion based on the summarized inquiry and the analyzed log, means for determining a priority according to the recognized emotion, and means for providing the converted content and priority information to an operator. This enables a quick and appropriate response that takes the user's emotion into consideration.

[0923] "User" means any person or entity that submits an inquiry using this system.

[0924] "Inquiry" is the details of the problem or question reported by the user.

[0925] A "summarization means" is a technology that has the ability to convert the content of a query into a concise format.

[0926] "Generative AI" is an artificial intelligence technology for automatically summarizing and analyzing inquiry content.

[0927] A "computer command" is an instruction to perform a particular task.

[0928] A "log" is a record of system actions and events.

[0929] "Means of analysis" refers to the technology used to analyze collected logs and convert them into an easy-to-understand format.

[0930] "Means for recognizing emotions" refers to technology that determines the emotions of users based on their inquiries.

[0931] The "means for determining priority" is a function that determines the order of processing priorities based on the recognized emotions.

[0932] An "operator" is a person who operates the system and responds to user inquiries.

[0933] "Transformed content" is information that has been processed through summarization and analysis.

[0934] "Priority information" is information about the priority of processing determined by recognizing emotions.

[0935] This invention combines a system that accepts inquiries from users, summarizes the contents, and collects and analyzes related logs with an emotion engine that recognizes the emotions of the user. Detailed embodiments of this system are described below.

[0936] First, the user inputs the inquiry using the terminal and clicks the send button. The inquiry includes a detailed description of the technical problem or malfunction. The terminal then sends the user's input information to the server.

[0937] The server stores the received inquiry and sends it to the generation AI, which summarizes the inquiry and converts it into a concise format. This process allows the operator to grasp a lot of information in a short amount of time.

[0938] Next, the server uses an emotion engine to recognize the user's emotion from the inquiry. The emotion engine uses natural language processing technology to analyze the emotion from the user's sentence. For example, if the user says "I'm in a lot of trouble," the emotion engine will recognize emotions such as "stress" and "urgent need."

[0939] The emotions recognized by the emotion engine are used to determine the priority of the inquiry. For example, if the inquiry is highly angry or stressed, it will be treated as a high priority. The emotion engine can also advise the operator on the appropriate response method based on the recognized emotion.

[0940] Based on the summary and the perceived emotion, the server selects the relevant computer command. For example, if the summary says "Service has stopped" and the user is showing high stress, the server needs to respond quickly, so it will immediately run the sudo systemctl status some_service command and collect the necessary logs.

[0941] The collected logs are then analyzed using the generation AI and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation such as "The service has stopped due to lack of memory. Check the memory usage and restart it if necessary."

[0942] Finally, the server sends the notification content adjusted according to the generated explanation and the recognized emotion to the operator's terminal. The operator responds to the user's inquiry promptly and appropriately based on the provided explanation and emotion information. The operator then provides the user with specific measures via the terminal, and the user can follow the instructions to resolve the problem.

[0943] As a concrete example, the following shows the flow when a user reports that "my account may have been compromised" and expresses the emotion "very troubled." The server receives this inquiry, and the generation AI summarizes it as "my account is suspected to have been compromised." The emotion engine then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating "some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick response, and the user follows the instructions to implement the response and resolve the problem.

[0944] As a result, the present invention can recognize the user's emotions and respond to inquiries taking these into consideration, thereby reducing the burden on operators and increasing user satisfaction.

[0945] It also uses a generative AI model to summarize the query, an emotion engine to recognize emotions, and then executes the associated computer command. For each step, the following prompts are available:

[0946] Inquiry:

[0947] -------

[0948] I think my account may have been accessed illegally. I've noticed some suspicious activity since this morning. I'm in a lot of trouble.

[0949] summary:

[0950] ------

[0951] 1. Suspected unauthorized access to your account.

[0952] 2. Suspicious activity is observed.

[0953] 3. Users are very confused.

[0954] Emotion recognition:

[0955] --------------

[0956] Very confused (urgent)

[0957] The hardware used includes servers and devices, while the software includes generative AI models, emotion engines, and natural language processing technologies. The application of these technologies enables efficient and emotion-sensitive user support.

[0958] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0959] Step 1:

[0960] The user uses the terminal to input the inquiry content and clicks the send button. The input inquiry content (data) is sent from the terminal to the server. The input is the user's report content, and the output is the inquiry data sent to the server.

[0961] Step 2:

[0962] The server stores the query content received and sends it to the generative AI model, which then summarizes the query content. The input here is the query data received from the user, and the output is the summary data converted into a concise format.

[0963] Step 3:

[0964] The server sends the summarized query content to the emotion engine to recognize the user's emotion. The emotion engine uses natural language processing technology to analyze emotions. The input is the summary data, and the output is emotion data such as "confusion" or "urgency."

[0965] Step 4:

[0966] The server determines the priority of the query based on the recognized emotion data. For example, if the emotion is "urgent" or "angry," the query is set as a high priority. The input is emotion data, and the output is priority information.

[0967] Step 5:

[0968] The server selects and executes relevant computer commands based on the summary content and priority information. For example, run the command sudo systemctl status some_service to collect the required logs. The input is the summary data and priority information, and the output is the collected log data.

[0969] Step 6:

[0970] The server sends the collected log data to the generative AI model, which analyzes the logs and converts them into an easy-to-understand format. For example, it may convert the information into "The service has stopped due to insufficient memory." The input is the log data, and the output is simple explanatory data.

[0971] Step 7:

[0972] The server sends the generated explanation data and priority information to the operator's terminal. The operator responds promptly and appropriately to the user's inquiry based on the provided explanation and emotion information. The input is the explanation data and priority information, and the output is the information notified to the operator.

[0973] Step 8:

[0974] The operator communicates specific countermeasures to the user via the terminal. The user can then follow the instructions to implement the countermeasures and solve the problem. The input is the instructions from the operator, and the output is the countermeasure implemented by the user.

[0975] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0976] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0977] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0978] [Fourth embodiment]

[0979] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0980] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0981] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0982] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0983] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0984] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0985] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0986] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0987] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0988] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0989] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0990] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0991] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0992] The present invention relates to a system that receives inquiries from users, summarizes the inquiries, and collects and analyzes related logs. Detailed embodiments of this system will be described below.

[0993] First, the user sends a message regarding the system malfunction to the inquiry desk. The user enters the inquiry content using a terminal and clicks the send button to make the inquiry. This content is sent to the server, which receives it and stores it in a database.

[0994] The server then begins the process of summarizing the received inquiry. Using a generation AI, the server automatically summarizes the inquiry based on the necessary information. For example, if a user sends a query such as "My service has stopped. What should I do?", the generation AI converts this into a summary such as "My service has stopped."

[0995] Based on the summary, the server selects the relevant computer command. For example, if the summary is "Service has stopped," the server selects the command sudo systemctl status some_service. This command is executed within the server, and the relevant logs are collected as output.

[0996] The collected logs are then analyzed again using the generation AI. The server inputs the log data into the generation AI, and the server converts the resulting information into an easy-to-understand format. For example, if the log contains the content "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation: "The service has stopped due to lack of memory. Please check your memory usage and restart if necessary."

[0997] Finally, the server provides the generated explanation to the operator, who then responds promptly and appropriately to the user's inquiry based on the explanation. The operator then informs the user of the solution via the terminal, and the user can follow the solution to solve the problem.

[0998] As a concrete example, the flow when a user makes an inquiry saying, "The service has stopped. What should I do?" is shown below. The server receives this inquiry and the generation AI summarizes it as "The service has stopped." The server then selects and executes the sudo systemctl status some_service command, collecting a log stating, "Some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation saying, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. The operator conveys this explanation to the user, who then follows the instructions to take measures and resolve the problem.

[0999] In this way, the present invention enables even less skilled operators to isolate and handle advanced system faults, thereby enabling the efficient use of expert resources.

[1000] The processing flow will be explained below.

[1001] Step 1:

[1002] The user uses the terminal to enter the inquiry details and clicks the send button.

[1003] Step 2:

[1004] The terminal transmits the input inquiry to the server.

[1005] Step 3:

[1006] The server receives the query and stores it in a database.

[1007] Step 4:

[1008] The server sends the received query to the generation AI, which generates a summary.

[1009] Step 5:

[1010] The server selects the appropriate computer command based on the generated summary.

[1011] Step 6:

[1012] The server executes selected computer commands and collects relevant logs.

[1013] Step 7:

[1014] The server sends the collected logs to a generation AI, which generates an easy-to-understand explanation.

[1015] Step 8:

[1016] The server sends the generated explanation to the operator's terminal for display.

[1017] Step 9:

[1018] The operator will inform the user of the countermeasures via the terminal.

[1019] Step 10:

[1020] The user follows the operator's instructions and performs operations to solve the problem through the terminal.

[1021] Step 11:

[1022] After the user has resolved the problem, he reports the results to the operator, who then records the results on the server.

[1023] Example 1

[1024] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1025] There is a need to respond to user inquiries quickly and effectively and identify the cause of system failures. However, with conventional methods, manually summarizing the content of inquiries and collecting and analyzing logs takes a great deal of time and effort, making it difficult for operators without specialized knowledge to provide advanced responses. Furthermore, in situations where a quick response is required, delays can result in a decrease in user satisfaction.

[1026] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1027] In this invention, the server includes means for accepting inquiries from users, means for automatically summarizing the accepted inquiries using a generative AI model, means for executing related computer resource management commands based on the summarized content and collecting logs, means for analyzing the collected log data using the generative AI model and converting it into an easy-to-understand format, and means for providing the converted content to an operator, thereby enabling even operators without specialized knowledge to respond to user inquiries quickly and accurately.

[1028] "User" refers to an individual or company representative who queries the system.

[1029] "Inquiry content" refers to information entered and sent by a user regarding a system malfunction or question.

[1030] A "generative AI model" refers to an artificial intelligence algorithm that generates and analyzes text based on large amounts of data.

[1031] "Summary" refers to a sentence that briefly summarizes the main information of the inquiry.

[1032] "Computer resource management commands" refer to instructions executed by a server to check or manipulate the state of the system.

[1033] A "log" refers to data that records various events and activities that occur on a computer system.

[1034] "Analysis" refers to the process of examining collected log data in detail to identify the cause of the problem and how to solve it.

[1035] "Operator" refers to the person in charge of operating the system and dealing with users.

[1036] MODE FOR CARRYING OUT THE INVENTION

[1037] The present invention relates to a system that receives inquiries from users, summarizes the inquiries, and collects and analyzes related logs. Detailed embodiments of this system will be described below.

[1038] First, the user uses their own device (PC or smartphone) to enter the inquiry and clicks the send button. For example, if the user enters something like "The service has stopped. What should I do?", the inquiry is sent from the user's device to the server.

[1039] The server stores the query received from the user in a database. The stored data includes not only the query content but also metadata such as date and time and user ID. This storage process is performed using a database management system on the server (e.g., MySQL, PostgreSQL, etc.).

[1040] The server then inputs the saved query content into a generative AI model for summarization. This summarization process uses natural language processing techniques to concisely summarize the key information in the query content. For example, in response to a query such as "The service has stopped. What should I do?", the generative AI model generates the summary "The service has stopped."

[1041] Based on the summary, the server selects the appropriate computer resource management command. This selection process is performed by a rule-based engine or script within the server. For example, for the summary "Service has stopped," the server selects the command sudo systemctl status some_service.

[1042] The server executes the selected commands and collects the resulting logs, which contain important information about the system's state and are stored using an on-server log management system (e.g., ELK stack, Splunk, etc.).

[1043] The collected log data is then input back into the generative AI model for analysis. During this analysis process, the log contents are examined in detail to identify the cause of the problem and how to resolve it. The generative AI model analyzes the log contents and extracts information such as "some_service has stopped due to insufficient memory."

[1044] The server generates an easy-to-understand explanation for the user based on the analysis results of the generative AI model. The generative AI model converts the analysis results into a simple explanation such as "The service has stopped due to insufficient memory. Please check your memory usage and restart if necessary."

[1045] Finally, the server provides the generated explanation to the operator. The operator responds to the user based on the explanation provided. The operator communicates the explanation to the user through their own terminal and provides specific countermeasures. For example, the operator might instruct the user, "The service has stopped due to insufficient memory. Please check the memory usage and restart if necessary."

[1046] As a concrete example, let's consider the case where a user makes an inquiry saying, "The service has stopped. What should I do?" The server receives the inquiry and summarizes it as "The service has stopped" using the generative AI model. The server then selects and executes the sudo systemctl status some_service command, collecting a log stating, "Some_service has stopped due to insufficient memory." The generative AI model converts this log into an explanation saying, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides this to the operator. The operator then conveys this explanation to the user, who then follows the instructions to take measures and resolve the problem.

[1047] Below are some examples of prompts for generative AI models:

[1048] "When a user asks, 'My service is down, what do I do?' Summarize and create a concise answer."

[1049] "Based on the log data 'some_service has stopped due to insufficient memory', please generate an easy-to-understand explanation for the user."

[1050] As described above, the present invention enables even operators without specialized knowledge to respond to user inquiries quickly and accurately.

[1051] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1052] Step 1:

[1053] The user inputs a query into the terminal and sends it.

[1054] The user enters the inquiry into their own terminal and clicks the send button. For example, they enter "The service has stopped. What should I do?" The entered inquiry is sent from the terminal to the server via the network.

[1055] Input: User inquiry (e.g. "My service has stopped. What should I do?").

[1056] Output: The query is sent to the server.

[1057] Step 2:

[1058] The server receives the query and stores it in a database.

[1059] The server receives the inquiry sent by the user and temporarily stores it in memory.Then, it stores the inquiry in a database.At this time, in addition to the inquiry content, it also stores metadata such as the date and time and user ID.

[1060] Input: User's inquiry.

[1061] Output: Query details and metadata stored in a database.

[1062] Step 3:

[1063] The server automatically summarizes the query using a generative AI model.

[1064] The server retrieves the query content from the database and inputs it into the generative AI model. The generative AI model analyzes the query content, extracts key information, and generates a summary. For example, the query "The service has stopped. What should I do?" is summarized as "The service has stopped."

[1065] Input: The query retrieved from the database.

[1066] Output: A summary from the generative AI model (e.g., "The service has stopped").

[1067] Step 4:

[1068] The server selects relevant computer resource management commands based on the abstract content.

[1069] The server selects an appropriate command based on the summary obtained from the generative AI model. For example, for the summary "The service has stopped," the command "sudo systemctl status some_service" is selected. This selection is performed by a rule-based engine or script within the server.

[1070] Input: A summary from a generative AI model.

[1071] Output: The selected computer resource management command (e.g., sudo systemctl status some_service).

[1072] Step 5:

[1073] The server executes the selected command and collects the logs.

[1074] The server runs the selected command and collects logs as its output, for example, run the command sudo systemctl status some_service to get log data about the status of the service.

[1075] Input: Selected computer resource management command.

[1076] Output: The captured log data.

[1077] Step 6:

[1078] The logs collected by the server are analyzed using a generative AI model.

[1079] The server inputs the collected log data into a generative AI model for analysis. The generative AI model then examines the log contents in detail to identify the cause of the problem. For example, it might analyze and extract information such as "some_service has stopped due to insufficient memory."

[1080] Input: Collected log data.

[1081] Output: Analysis results from the generative AI model (e.g., "some_service has stopped due to lack of memory").

[1082] Step 7:

[1083] The server generates an easy-to-understand explanation for the user based on the analysis results of the generated AI model.

[1084] The server generates an explanation in a form that is easy for the user to understand based on the analysis results of the generative AI model. The generative AI model converts the analysis results into an explanation such as "The service has stopped due to insufficient memory. Please check your memory usage and restart if necessary."

[1085] Input: Analysis results of the generative AI model.

[1086] Output: A generated, user-friendly explanation (e.g., "The service has stopped due to low memory. Please check your memory usage and restart if necessary").

[1087] Step 8:

[1088] The server provides the generated explanation to the operator.

[1089] The server provides the generated explanation to an interface accessible to the operator, who then checks the explanation provided by the server on his / her terminal.

[1090] Input: The generated description.

[1091] Output: The description provided to the operator.

[1092] Step 9:

[1093] The operator responds to the user based on the explanation.

[1094] The operator responds to the user based on the explanation provided by the server and instructs the user on specific measures to take, for example, "The service has stopped due to a lack of memory. Please check the memory usage and restart if necessary."

[1095] Input: A description provided by the server.

[1096] Output: Specific measures provided to the user.

[1097] (Application example 1)

[1098] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1099] Modern factories employ a large number of robots, and when one of these robots breaks down, a rapid and appropriate response is required. However, detecting a robot's malfunction and identifying its cause requires a high level of specialized knowledge, making a rapid response often difficult. Furthermore, it takes time and effort for maintenance staff to manually analyze all log data and find the optimal solution. As a result, in many factories, responding to robot malfunctions takes a long time, which can lead to reduced productivity. Furthermore, analyzing complex log data and summarizing inquiries requires a lot of manual work, making efficient operation difficult. A system that can solve these issues is needed.

[1100] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1101] In this invention, the server includes: means for accepting inquiries from users; means for summarizing the received inquiries; means for executing related computer commands based on the summaries and collecting logs; means for analyzing the collected logs and converting them into an easy-to-understand format; means for providing the converted logs to an operator; and means installed on a mobile device that includes an application for processing the inquiries and displaying the log analysis results. This allows maintenance staff to quickly and efficiently identify the cause of robot failures and take appropriate action. Furthermore, the automatic summarization of inquiries and automatic analysis of log data improves work efficiency.

[1102] "User" means a person or entity that queries the System.

[1103] "Inquiry content" refers to detailed information about a question or problem that a user sends to the system.

[1104] "Means for receiving" refers to the method by which the system receives inquiries from users.

[1105] "Means of summarizing" refers to a method for concisely summarizing the content of inquiries received.

[1106] "Relevant computer commands" are system commands that are executed based on the abstracted query.

[1107] A "log" is recorded information such as system operation history and error messages.

[1108] "Means of collection" refers to the method for collecting the necessary log data.

[1109] "Means of analysis" refers to the method of analyzing collected log data to identify problems and solutions.

[1110] "Means for providing" refers to a method for presenting analysis results and other information to an operator.

[1111] An "operator" is a person who manages the system and responds to inquiries from users.

[1112] A "mobile device" is a portable electronic device such as a smartphone or tablet.

[1113] "Installation" is the act of introducing application software onto specific hardware.

[1114] An "application" is a software program designed to provide a particular function or service.

[1115] "Generative AI" is an artificial intelligence technology that automates the analysis of inquiry content and logs.

[1116] The present invention relates to a system for quickly and efficiently dealing with robot failures in a factory. An embodiment of this system will be described in detail below.

[1117] The entire system consists of a server that accepts inquiries from users, a server that summarizes the inquiries using generative AI, a means for executing related computer commands based on the summarized content and collecting logs, a means for analyzing the collected logs and converting them into an easy-to-understand format, a means for providing the converted content to the operator, and an application installed on a mobile device.

[1118] First, a user uses a mobile device to input an inquiry about a robot malfunction or operational problem and send it to the server. For example, a user might send an inquiry such as, "My robot has stopped. What should I do?"

[1119] The server summarizes the received query using a generative AI model. In this case, OpenAI's GPT-3 is used as the AI ​​model. If the query is "My robot has stopped. What should I do?", the summary will be "My robot has stopped." Based on this summary, the system selects an appropriate computer command. For example, it could execute a command to "check the robot's status" and collect related log data.

[1120] Next, the collected log data is analyzed again using generative AI and converted into a format that is easy for users to understand. For example, if the log contains information such as "A motor error has occurred. The temperature is too high," the analysis result will be converted into a simple explanation such as "The robot's motor is experiencing an error. Please check the motor temperature and cool it if necessary." This process also uses OpenAI's GPT-3.

[1121] The converted information is provided to the operator, who then provides feedback on countermeasures to the user via a mobile device, allowing the user to quickly and accurately resolve the robot's problems.

[1122] As a concrete example, the following is an example of a prompt sentence to be input to a generative AI model:

[1123] Summary of your inquiry:

[1124] Please summarize your inquiry in one sentence:

[1125] My robot has stopped working, what should I do?

[1126] Log analysis:

[1127] Please analyze the following logs and clearly explain the problem and solution:

[1128] Robot motor error - Memory error detected - Temperature rise

[1129] This system enables factory maintenance staff, even those without advanced skills, to quickly identify the cause of a robot malfunction and take appropriate action, thereby improving productivity and enabling efficient malfunction response.

[1130] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1131] Step 1:

[1132] The user uses a mobile terminal to input an inquiry about a robot malfunction or operational problem and clicks the send button. At this point, the input is the inquiry entered by the user into the terminal, and the output is the inquiry data sent to the server. The server receives this data.

[1133] Step 2:

[1134] The server inputs the received query content into a generative AI model (for example, OpenAI's GPT-3) and summarizes the query content in one sentence. The prompt uses the format "Please summarize the following query content in one sentence:\n\n{query content}\n". The input is the received query data, and data processing is a summary process by the generative AI. The output is the summarized query content.

[1135] Step 3:

[1136] The server selects an appropriate computer command based on the abstract. For example, for the abstract "The robot has stopped," it selects the command sudo systemctl status robot_service to check the robot's status. The input is the abstracted query, and the output is the selected computer command.

[1137] Step 4:

[1138] The server executes the selected computer command and collects log data. Specifically, it collects the output obtained by executing the command (e.g., service status information obtained as a result of sudo systemctl status robot_service) as a log. The input is the selected computer command, the data calculation is the command execution process, and the output is the collected log data.

[1139] Step 5:

[1140] The collected log data is again input into the generative AI model, where it is analyzed and converted into an easy-to-understand format. The prompt sentence is "Analyze the following log and provide a clear explanation of the problem and solution:\n\n{log data}\n". The input is the collected log data, and the output is the analyzed result (e.g., "An error has occurred in the robot's motor. Check the motor temperature and cool it if necessary").

[1141] Step 6:

[1142] The server provides the analysis results to the operator. Based on this information, the operator provides appropriate feedback on countermeasures to the user via their mobile device. The input is the analysis results, and the output is specific countermeasure information provided to the user. The operator communicates this information to the user, who then uses it to solve the robot's problems.

[1143] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1144] This invention combines a system that accepts inquiries from users, summarizes the contents, and collects and analyzes related logs with an emotion engine that recognizes the emotions of the user. Detailed embodiments of this system are described below.

[1145] First, the user inputs the inquiry using the terminal and clicks the send button. The inquiry includes a detailed description of the technical problem or malfunction. The terminal then sends the user's input information to the server.

[1146] The server stores the received inquiry and sends it to the generation AI, which summarizes the inquiry and converts it into a concise format. This process allows the operator to grasp a lot of information in a short amount of time.

[1147] Next, the server uses an emotion engine to recognize the user's emotion from the inquiry. The emotion engine uses natural language processing technology to analyze the emotion from the user's sentence. For example, if the user says "I'm in a lot of trouble," the emotion engine will recognize emotions such as "stress" and "urgent need."

[1148] The emotions recognized by the emotion engine are used to determine the priority of the inquiry. For example, if the inquiry is highly angry or stressed, it will be treated as a high priority. The emotion engine can also advise the operator on the appropriate response method based on the recognized emotion.

[1149] Based on the summary and the perceived emotion, the server selects the relevant computer command. For example, if the summary says "Service has stopped" and the user is showing high stress, the server needs to respond quickly, so it will immediately run the sudo systemctl status some_service command and collect the necessary logs.

[1150] The collected logs are then analyzed using the generation AI and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation such as "The service has stopped due to lack of memory. Check the memory usage and restart it if necessary."

[1151] Finally, the server sends the notification content adjusted according to the generated explanation and the recognized emotion to the operator's terminal. The operator responds to the user's inquiry promptly and appropriately based on the provided explanation and emotion information. The operator then provides the user with specific measures via the terminal, and the user can follow the instructions to resolve the problem.

[1152] As a concrete example, the following shows the flow when a user inquires, "The service has stopped. What should I do?" and expresses the emotion, "I'm very troubled." The server receives this inquiry, and the generation AI summarizes it as "The service has stopped." The emotion engine then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating, "Some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick response, and the user follows the instructions to implement the response and resolves the problem.

[1153] In this way, the present invention recognizes the user's emotions and takes them into consideration when responding to inquiries, thereby reducing the burden on operators and increasing user satisfaction.

[1154] The processing flow will be explained below.

[1155] Step 1:

[1156] The user uses the terminal to enter the inquiry details and clicks the send button.

[1157] Step 2:

[1158] The terminal sends the inquiry to the server.

[1159] Step 3:

[1160] The server receives the query and stores it in a database.

[1161] Step 4:

[1162] The server sends the received query content to the generation AI, which summarizes the query content.

[1163] Step 5:

[1164] The generation AI summarizes the query, and the server receives the summary.

[1165] Step 6:

[1166] The server sends the summarized query content to the emotion engine to analyze the user's emotions.

[1167] Step 7:

[1168] The emotion engine recognizes the user's emotion from the summary content and sends the result to the server.

[1169] Step 8:

[1170] The server selects relevant computer commands based on the recognized emotions and summary content.

[1171] Step 9:

[1172] The server executes selected computer commands and collects logs.

[1173] Step 10:

[1174] The server sends the collected logs to the generation AI, requesting it to analyze the logs and generate easy-to-understand explanations.

[1175] Step 11:

[1176] The generation AI analyzes the logs, generates easy-to-understand explanations, and sends the results to the server.

[1177] Step 12:

[1178] The server sends a notification to the operator's terminal based on the generated description and the recognized emotion.

[1179] Step 13:

[1180] An operator uses the terminal to check the provided explanation and emotional information and inform the user of a response plan.

[1181] Step 14:

[1182] The user uses the terminal and follows the instructions of the operator to carry out operations to solve the problem.

[1183] Step 15:

[1184] The user reports that the problem has been resolved to the operator, and the result is recorded on the server.

[1185] Example 2

[1186] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1187] Conventional inquiry response systems have difficulty quickly and appropriately summarizing user inquiries, recognizing emotions, and determining response priorities. Furthermore, converting collected logs into an easy-to-understand format is time-consuming, increasing the burden on operators. This raises concerns about a decline in user satisfaction.

[1188] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting a user's inquiry, means for summarizing the accepted inquiry using a generative AI model, means for executing related computer commands based on the summarized content and collecting logs, means for analyzing the collected logs using the generative AI model and converting them into an easy-to-understand format, emotion recognition means for recognizing the user's emotion from the inquiry, means for determining the priority of the inquiry based on the recognized emotion, means for providing notification content according to the priority, and means for providing the converted content to the operator. This makes it possible to quickly and appropriately summarize the user's inquiry, recognize the emotion and determine the priority of the response, convert the collected logs into an easy-to-understand format, reduce the burden on the operator, and improve user satisfaction.

[1189] A "user" is a person or entity that uses the system to make an inquiry.

[1190] A "terminal" is an electronic device that a user operates to input and send inquiry details.

[1191] A "server" is a central system that processes and responds to inquiries received.

[1192] An "inquiry" is a message containing a problem or question that a user sends to the system.

[1193] A "generative AI model" is an artificial intelligence that learns from large amounts of data and is used to summarize and analyze user input.

[1194] "Summarization" is the process or result of converting detailed query content into a concise form.

[1195] A "computer command" is an instruction that a server executes to initiate a particular operation or process.

[1196] A "log" is recorded data about the operating status of a system or service and events that have occurred.

[1197] "Emotion recognition means" refers to a technology or system for analyzing and recognizing emotions from the content of a user's inquiry.

[1198] "Priority" is an index for determining the urgency and importance of a response based on the content of the inquiry and the user's feelings.

[1199] An "operator" is a person in charge of managing the system and dealing directly with users.

[1200] "Notification content" is information about the processing result, the user's feelings, and priority that is sent by the server to the operator.

[1201] "Analysis" is the process or result of examining data or logs in detail and extracting useful information.

[1202] "Converting into a format" means reconstructing collected data and logs into a format that is easy for operators to understand.

[1203] A "system" is a collection of hardware and software configured to perform a particular function.

[1204] The present invention provides a system that efficiently summarizes the content of inquiries from users, analyzes related logs, and recognizes the user's emotions to determine the priority of responses. Specific embodiments of this system are described below.

[1205] First, the user uses the terminal to enter the inquiry content and clicks the send button. The inquiry content includes a detailed description of the technical problem or malfunction. For example, the user might enter "The service has stopped. What should I do?" The terminal then sends the user's input information to the server. This transmission is done using an HTTP request or an API call.

[1206] The server stores the received query content in a database and sends the content to a generative AI model. An example of a generative AI model is GPT-3, a widely used artificial intelligence model. This model learns from large amounts of text data and has the ability to automatically summarize the input text. The generative AI model summarizes the query content in a concise format, such as "The service has been stopped."

[1207] Next, the server uses an emotion recognition means to recognize the user's emotion from the inquiry. Natural language processing technologies such as IBM Watson's Tone Analyzer are used as emotion recognition means. For example, if the user says "I'm in a lot of trouble," the emotion recognition means will recognize the emotion as "urgent need."

[1208] The server determines the priority of the query based on the emotion recognition results. For example, if the query indicates high anger or stress, it is treated as a high priority. The server then selects and executes the relevant computer command and collects the necessary logs. For example, if the summary reads "Service has stopped" and the user indicates high stress, the server will need to respond quickly, so it will run the sudo systemctl status some_service command and collect logs.

[1209] The collected logs are then analyzed using the generative AI model and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generative AI model converts this information into a simple explanation such as "The service has stopped due to lack of memory. Please check your memory usage and restart it if necessary."

[1210] Finally, the server sends the notification content, adjusted according to the generated explanation and the recognized emotion, to the operator's terminal. The operator responds promptly and appropriately to the user's inquiry based on the provided explanation and emotion information. The operator then provides the user with specific solutions via the terminal, allowing the user to solve the problem by following the instructions. In this way, the present invention recognizes the user's emotion and takes it into consideration when responding to inquiries, thereby reducing the burden on the operator and increasing user satisfaction.

[1211] As a concrete example, let's look at the flow when a user inquires, "The service has stopped. What should I do?" and expresses the emotion, "I'm very troubled." The server receives this inquiry, and the generative AI summarizes it as "The service has stopped." The emotion recognition means then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating, "Some_service has stopped due to insufficient memory." The generative AI model converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick solution, and the user can follow the instructions to implement the solution and resolve the problem.

[1212] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1213] Step 1:

[1214] The user uses the terminal to enter the inquiry and clicks the send button. The data entered is a specific problem or question. For example, "The service has stopped. What should I do?" is entered and sent. This is the input.

[1215] Step 2:

[1216] The terminal sends the inquiry entered by the user to the server. The specific operation performed at this time is to send data via an HTTP request. The input data is the inquiry entered by the user, and the output data is text data sent to the server.

[1217] Step 3:

[1218] The server stores the received query in a database. The input data is the query received from the terminal, and the output data is the query data stored in the database. Specifically, the server writes data to the database using SQL queries, etc.

[1219] Step 4:

[1220] The server sends the saved query content to the generative AI model. The input data is the query content saved in the database, and the output data is the text data sent to the generative AI model. Specifically, data is sent to the generative AI model using an HTTP request or API call.

[1221] Step 5:

[1222] The generative AI model summarizes the query content. The input data is the query content sent from the server, and the output data is the summarized text. Specifically, the generative AI model analyzes the text, extracts the important parts, and converts them into a concise form. For example, a summary such as "The service has been stopped" is generated.

[1223] Step 6:

[1224] The server uses the emotion recognition means to recognize the user's emotion from the summarized inquiry content. The input data is the summarized inquiry content, and the output data is the recognized emotion information. Specifically, the emotion recognition means analyzes the text using natural language processing (NLP) technology and extracts emotions. For example, an emotion such as "very troubled" is recognized as "urgent."

[1225] Step 7:

[1226] The server determines the priority of the inquiry based on the recognized emotion data. The input data is the recognized emotion information, and the output data is the priority information of the inquiry. Specifically, the server evaluates the emotion data and classifies the priority as high, medium, low, etc. For example, if the emotion data is recognized as "urgent," the inquiry is treated as high priority.

[1227] Step 8:

[1228] The server selects and executes the relevant computer command based on priority. The input data is the query priority information, and the output data is the execution result of the executed command. Specific operations include running a shell command to check the system status. For example, the sudo systemctl status some_service command is executed, and a log stating "some_service has stopped due to insufficient memory" is collected.

[1229] Step 9:

[1230] The collected logs are then analyzed again using the generative AI model and converted into an easy-to-understand format. The input data is the collected logs, and the output data is the analyzed simple explanatory text. Specifically, the generative AI model analyzes the logs and converts them into a format that is easy for users and operators to understand. For example, it generates an explanation such as "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary."

[1231] Step 10:

[1232] The server then sends the notification content, adjusted according to the generated explanation and the recognized emotion, to the operator's terminal. The input data is a simple explanation text and emotion information, and the output data is the notification content provided to the operator. Specifically, the server sends an appropriate notification to the operator's terminal, and the operator responds to the user based on that.

[1233] Step 11:

[1234] The operator will then provide the user with specific countermeasures based on the provided explanation. The input data is the explanation provided by the server, and the output data is feedback to the user. Specifically, the operator will tell the user to "check memory usage and reboot if necessary."

[1235] Step 12:

[1236] The user takes specific actions to solve the problem according to the feedback from the operator. The input data are instructions from the operator, and the output data are the measures taken and their results. Specific actions include the user checking memory usage on the terminal and restarting the service if necessary.

[1237] In this way, the system recognizes the user's emotions and takes them into consideration when responding to inquiries, thereby reducing the burden on operators and increasing user satisfaction.

[1238] (Application example 2)

[1239] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1240] In modern security services, it is extremely important to quickly and accurately handle user-reported issues. However, when user reports are verbose or emotionally charged, a system is needed to efficiently summarize them and respond quickly. Furthermore, responses that do not take user emotions into consideration can lead to significant dissatisfaction and further problems. Therefore, there is a need for systems that can understand user emotions and respond appropriately based on those emotions.

[1241] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting an inquiry from a user, means for summarizing the accepted inquiry, means for executing related computer commands based on the summarized inquiry and collecting logs, means for analyzing the logs and converting them into an easy-to-understand format, means for recognizing the user's emotion based on the summarized inquiry and the analyzed log, means for determining a priority according to the recognized emotion, and means for providing the converted content and priority information to an operator. This enables a quick and appropriate response that takes the user's emotion into consideration.

[1242] "User" means any person or entity that submits an inquiry using this system.

[1243] "Inquiry" is the details of the problem or question reported by the user.

[1244] A "summarization means" is a technology that has the ability to convert the content of a query into a concise format.

[1245] "Generative AI" is an artificial intelligence technology for automatically summarizing and analyzing inquiry content.

[1246] A "computer command" is an instruction to perform a particular task.

[1247] A "log" is a record of system actions and events.

[1248] "Means of analysis" refers to the technology used to analyze collected logs and convert them into an easy-to-understand format.

[1249] "Means for recognizing emotions" refers to technology that determines the emotions of users based on their inquiries.

[1250] The "means for determining priority" is a function that determines the order of processing priorities based on the recognized emotions.

[1251] An "operator" is a person who operates the system and responds to user inquiries.

[1252] "Transformed content" is information that has been processed through summarization and analysis.

[1253] "Priority information" is information about the priority of processing determined by recognizing emotions.

[1254] This invention combines a system that accepts inquiries from users, summarizes the contents, and collects and analyzes related logs with an emotion engine that recognizes the emotions of the user. Detailed embodiments of this system are described below.

[1255] First, the user inputs the inquiry using the terminal and clicks the send button. The inquiry includes a detailed description of the technical problem or malfunction. The terminal then sends the user's input information to the server.

[1256] The server stores the received inquiry and sends it to the generation AI, which summarizes the inquiry and converts it into a concise format. This process allows the operator to grasp a lot of information in a short amount of time.

[1257] Next, the server uses an emotion engine to recognize the user's emotion from the inquiry. The emotion engine uses natural language processing technology to analyze the emotion from the user's sentence. For example, if the user says "I'm in a lot of trouble," the emotion engine will recognize emotions such as "stress" and "urgent need."

[1258] The emotions recognized by the emotion engine are used to determine the priority of the inquiry. For example, if the inquiry is highly angry or stressed, it will be treated as a high priority. The emotion engine can also advise the operator on the appropriate response method based on the recognized emotion.

[1259] Based on the summary and the perceived emotion, the server selects the relevant computer command. For example, if the summary says "Service has stopped" and the user is showing high stress, the server needs to respond quickly, so it will immediately run the sudo systemctl status some_service command and collect the necessary logs.

[1260] The collected logs are then analyzed using the generation AI and converted into a format that is easy for operators to understand. For example, if a log shows that "some_service has stopped due to lack of memory," the generation AI converts this information into a simple explanation such as "The service has stopped due to lack of memory. Check the memory usage and restart it if necessary."

[1261] Finally, the server sends the notification content adjusted according to the generated explanation and the recognized emotion to the operator's terminal. The operator responds to the user's inquiry promptly and appropriately based on the provided explanation and emotion information. The operator then provides the user with specific measures via the terminal, and the user can follow the instructions to resolve the problem.

[1262] As a concrete example, the following shows the flow when a user reports that "my account may have been compromised" and expresses the emotion "very troubled." The server receives this inquiry, and the generation AI summarizes it as "my account is suspected to have been compromised." The emotion engine then recognizes the user's emotion as "urgent." The server quickly executes the sudo systemctl status some_service command and collects a log stating "some_service has stopped due to insufficient memory." The generation AI converts this log into an explanation, "The service has stopped due to insufficient memory. Please check memory usage and restart if necessary," and provides it to the operator. Based on this explanation, the operator provides the user with a quick response, and the user follows the instructions to implement the response and resolve the problem.

[1263] As a result, the present invention can recognize the user's emotions and respond to inquiries taking these into consideration, thereby reducing the burden on operators and increasing user satisfaction.

[1264] It also uses a generative AI model to summarize the query, an emotion engine to recognize emotions, and then executes the associated computer command. For each step, the following prompts are available:

[1265] Inquiry:

[1266] -------

[1267] I think my account may have been accessed illegally. I've noticed some suspicious activity since this morning. I'm in a lot of trouble.

[1268] summary:

[1269] ------

[1270] 1. Suspected unauthorized access to your account.

[1271] 2. Suspicious activity is observed.

[1272] 3. Users are very confused.

[1273] Emotion recognition:

[1274] --------------

[1275] Very confused (urgent)

[1276] The hardware used includes servers and devices, while the software includes generative AI models, emotion engines, and natural language processing technologies. The application of these technologies enables efficient and emotion-sensitive user support.

[1277] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1278] Step 1:

[1279] The user uses the terminal to input the inquiry content and clicks the send button. The input inquiry content (data) is sent from the terminal to the server. The input is the user's report content, and the output is the inquiry data sent to the server.

[1280] Step 2:

[1281] The server stores the query content received and sends it to the generative AI model, which then summarizes the query content. The input here is the query data received from the user, and the output is the summary data converted into a concise format.

[1282] Step 3:

[1283] The server sends the summarized query content to the emotion engine to recognize the user's emotion. The emotion engine uses natural language processing technology to analyze emotions. The input is the summary data, and the output is emotion data such as "confusion" or "urgency."

[1284] Step 4:

[1285] The server determines the priority of the query based on the recognized emotion data. For example, if the emotion is "urgent" or "angry," the query is set as a high priority. The input is emotion data, and the output is priority information.

[1286] Step 5:

[1287] The server selects and executes relevant computer commands based on the summary content and priority information. For example, run the command sudo systemctl status some_service to collect the required logs. The input is the summary data and priority information, and the output is the collected log data.

[1288] Step 6:

[1289] The server sends the collected log data to the generative AI model, which analyzes the logs and converts them into an easy-to-understand format. For example, it may convert the information into "The service has stopped due to insufficient memory." The input is the log data, and the output is simple explanatory data.

[1290] Step 7:

[1291] The server sends the generated explanation data and priority information to the operator's terminal. The operator responds promptly and appropriately to the user's inquiry based on the provided explanation and emotion information. The input is the explanation data and priority information, and the output is the information notified to the operator.

[1292] Step 8:

[1293] The operator communicates specific countermeasures to the user via the terminal. The user can then follow the instructions to implement the countermeasures and solve the problem. The input is the instructions from the operator, and the output is the countermeasure implemented by the user.

[1294] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1295] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1296] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1297] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1298] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1299] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1300] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1301] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1302] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1303] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1304] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1305] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1306] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1307] 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.

[1308] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1309] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1310] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1311] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1312] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1313] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1314] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1315] The following is further disclosed regarding the above embodiment.

[1316] (Claim 1)

[1317] A means for accepting inquiries from users;

[1318] a means for summarizing received inquiries;

[1319] means for executing relevant computer commands and collecting logs based on the summarized content;

[1320] A means to analyze the collected logs and convert them into an easy-to-understand format,

[1321] means for providing the transformed content to an operator;

[1322] A system including:

[1323] (Claim 2)

[1324] The system according to claim 1, wherein the summarizing means automatically summarizes the inquiry content using a generation AI.

[1325] (Claim 3)

[1326] 2. The system of claim 1, wherein the means for analyzing the log and converting it into an easy-to-understand format uses a generating AI to analyze the log.

[1327] "Example 1"

[1328] (Claim 1)

[1329] A means for accepting inquiries from users;

[1330] A means of automatically summarizing received inquiries using a generative AI model; and

[1331] means for executing relevant computer resource management commands and collecting logs based on the summarized content;

[1332] A means to analyze collected log data using a generative AI model and convert it into an easy-to-understand format;

[1333] means for providing the converted content to an operator;

[1334] A system including:

[1335] (Claim 2)

[1336] 10. The system of claim 1, further comprising means for automatically summarizing query content using a generative AI model.

[1337] (Claim 3)

[1338] 10. The system of claim 1, further comprising means for analyzing the log data using a generative AI model and converting it into an understandable format.

[1339] "Application Example 1"

[1340] (Claim 1)

[1341] A means for accepting inquiries from users;

[1342] a means for summarizing received inquiries;

[1343] means for executing relevant computer commands and collecting logs based on the summarized content;

[1344] A means to analyze the collected logs and convert them into an easy-to-understand format,

[1345] means for providing the transformed content to an operator;

[1346] A means including an application installed on a mobile terminal, which processes the inquiry content and displays the log analysis results;

[1347] A system including:

[1348] (Claim 2)

[1349] The system according to claim 1, wherein the summarizing means automatically summarizes the inquiry content using a generation AI.

[1350] (Claim 3)

[1351] 2. The system of claim 1, wherein the means for analyzing the log and converting it into an easy-to-understand format uses a generating AI to analyze the log.

[1352] "Example 2: Combining Emotion Engines"

[1353] (Claim 1)

[1354] A means for accepting inquiries from users;

[1355] A means for summarizing received inquiries using a generative AI model; and

[1356] means for executing relevant computer commands and collecting logs based on the summarized content;

[1357] A means to analyze the collected logs using a generative AI model and convert them into an easy-to-understand format,

[1358] emotion recognition means for recognizing the emotion of a user from the content of an inquiry;

[1359] a means for prioritizing inquiries based on the perceived sentiment;

[1360] a means for providing notification contents according to priority to an operator;

[1361] means for providing the transformed content to an operator;

[1362] A system including:

[1363] (Claim 2)

[1364] 2. The system according to claim 1, wherein the emotion recognition means analyzes the emotion of the user based on the summarized content and determines the priority of the inquiry.

[1365] (Claim 3)

[1366] The system of claim 1, which uses a generative AI model to analyze based on the summarized content and collected logs.

[1367] "Application example 2 when combining emotion engines"

[1368] (Claim 1)

[1369] A means for accepting inquiries from users;

[1370] a means for summarizing received inquiries;

[1371] means for executing relevant computer commands and collecting logs based on the summarized content;

[1372] A means to analyze the collected logs and convert them into an easy-to-understand format,

[1373] means for recognizing user emotions based on the summarized inquiry content and the analyzed log;

[1374] a means for determining a priority according to the recognized emotion;

[1375] means for providing the transformed content and priority information to an operator;

[1376] A system including:

[1377] (Claim 2)

[1378] The system according to claim 1, wherein the summarizing means automatically summarizes the inquiry content using a generation AI.

[1379] (Claim 3)

[1380] 2. The system of claim 1, wherein the means for analyzing the log and converting it into an easy-to-understand format uses a generating AI to analyze the log. [Explanation of symbols]

[1381] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for accepting inquiries from users; a means for summarizing received inquiries; means for executing relevant computer commands and collecting logs based on the summarized content; A means to analyze the collected logs and convert them into an easy-to-understand format, means for providing the transformed content to an operator; A system including:

2. 2. The system according to claim 1, wherein the summarizing means automatically summarizes the inquiry content using a generation AI.

3. 2. The system according to claim 1, wherein the means for analyzing the log and converting it into an easy-to-understand format uses a generating AI to analyze the log.

Images