System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting alarm information; means for transmitting the input alarm information to a server; means for analyzing the alarm information and generating an analysis result; means for translating the analysis result and presenting a correction method; and means for transmitting the presented correction method to a terminal.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] During base station construction work, English alarms frequently emitted by radios when radio waves are emitted are difficult for new or inexperienced engineers to understand and respond appropriately. This reduces work efficiency and takes time to resolve errors. Furthermore, staff with specialized knowledge and experience are always required to respond, making it difficult to efficiently utilize human resources. To solve these issues, a system is needed that can quickly and accurately interpret the alarm content and automatically provide appropriate corrective measures. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for inputting alarm information and transmitting it to a server, and a means for analyzing the alarm information using natural language processing technology and generating an analysis result. The system further includes a means for translating the analysis result and presenting corrective measures, and a means for transmitting the presented corrective measures to a terminal. This makes it easier to understand the content of the alarm, and provides specific corrective measures, enabling even new or inexperienced engineers to respond quickly and accurately. Furthermore, the system includes a means for referencing a past database or knowledge base based on the analysis result to obtain the optimal corrective measure, further improving the accuracy and efficiency of the response.

[0006] "Alarm information" refers to warning and error messages generated by radios and other communications equipment.

[0007] "Input means" refers to an interface or method by which a user inputs alarm information into a device.

[0008] The "transmitting means" is a communication means for transmitting the input alarm information to the server.

[0009] The "means for analysis" refers to a means for analyzing received alarm information using natural language processing technology or the like, and identifying its meaning and cause.

[0010] The "analysis result" is information about the meaning and cause of the alarm information obtained by the analysis means.

[0011] "Translation means" refers to the methods and techniques used to convert the analysis results from one language to another.

[0012] "Corrective measures" are specific steps and measures for resolving problems that are indicated based on the analysis results.

[0013] "Presentation means" refers to the methods and techniques for providing the translated analysis results and corrective measures to the user as information.

[0014] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0015] A "server" is a computer system that receives transmitted alarm information and performs analysis and interpretation.

[0016] A "database" is a collection of information that records past alarm information and corrective measures.

[0017] A "knowledge base" is a collection of information that organizes specialized knowledge and past response cases.

[0018] "Natural language processing technology" is a technology that enables computers to understand and process human language. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

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

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

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

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0034] 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.

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

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention provides a system for improving the efficiency of alarm response during base station construction work. Specific embodiments for carrying out the present invention will be described below.

[0041] 1. Alarm input acquisition

[0042] The user inputs the English alarm message displayed on the radio into the LINE message screen using a smartphone or other device, and the alarm information is then acquired by the device.

[0043] 2. Alarm details transmission

[0044] The alarm information acquired by the device is sent to the server. Specifically, the input alarm information is converted into JSON format and sent to the server as an HTTP request. The server receives this request and prepares for analysis.

[0045] 3. Alarm Analysis

[0046] The server adds the received alarm information to an analysis queue. It then calls the generative AI model, which extracts the alarm information from the queue and begins analysis. The generative AI model uses natural language processing technology to analyze the meaning of the alarm information and identify causes and countermeasures.

[0047] 4. Alarm translation and correction method provided

[0048] Once the server receives the analysis results, it calls up a translation model to translate the alarm information into Japanese. Once translation is complete, it references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will present corrective measures, including steps to check the power supply connection status.

[0049] 5. Send results

[0050] The server sends the translation results and correction instructions to the device. The sent content is received by the device as an HTTP response and converted into a LINE message format.

[0051] 6. Results confirmation and processing

[0052] The device will display the translation results and corrective measures on the LINE message screen. The user can check this and take the necessary corrective measures as instructed. For example, if the message "A power error has been detected. Please check the power connection" is displayed, the user should check the power connection to the BBU (baseband unit) and reconnect it.

[0053] As a concrete example, consider the following scenario: A user inputs an alarm saying, "Power supply error detected. Please check the power connection." The device sends this alarm information to a server, which analyzes it using a generative AI model. The analysis results are translated into Japanese and displayed as, "A power supply error has been detected. Please check the power connection." Furthermore, the server refers to a database and presents a specific corrective measure: "Check the BBU's power connection and reconnect if necessary." Ultimately, the user follows this procedure and takes the appropriate action, quickly resolving the problem.

[0054] This system will enable even engineers without specialized knowledge to respond quickly and accurately when an alarm occurs, which is expected to improve work efficiency and quality.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The user enters the English alarm message displayed on the radio into the LINE message screen. The device receives this input and prepares for the next process.

[0058] Step 2:

[0059] The device converts the input alarm message into JSON format and sends it as an HTTP request to the server, which receives the request.

[0060] Step 3:

[0061] The server adds the received alarm message to the analysis queue, then invokes the generative AI model to take the alarm message from the queue and start analyzing it.

[0062] Step 4:

[0063] The generative AI model uses natural language processing technology to semantically analyze the alarm message, specifically analyzing the structure and content of the message to identify the type and cause of the error.

[0064] Step 5:

[0065] The server receives the analysis results and calls the appropriate translation model based on the results. The translation model translates the English alarm content into Japanese.

[0066] Step 6:

[0067] The server compares the translated analysis results with historical and knowledge bases to find the appropriate corrective action, for example, if a power error is detected, it may include steps to check the power connection.

[0068] Step 7:

[0069] The server combines the translation results with specific corrective actions to generate a response message, which is presented to the user in a format that is easy to understand.

[0070] Step 8:

[0071] The server generates a response message and sends it to the device as an HTTP response. The device receives this response and converts it into a LINE message format based on the analysis and translation results.

[0072] Step 9:

[0073] The device displays the translation result and correction instructions on the LINE message screen, and the user can check the message and understand the content.

[0074] Step 10:

[0075] The user follows the suggested corrective measures and takes the necessary corrective action, for example, by performing specific steps such as reconnecting the power or checking the cables.

[0076] This processing step enables a quick and accurate response when an alarm occurs, improving the efficiency and quality of work.

[0077] Example 1

[0078] 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."

[0079] Responding to alarms during base station construction work requires a high level of specialized knowledge, making it difficult to respond quickly. Furthermore, the lack of a way to effectively utilize case studies from other sites and past data makes it difficult to solve problems efficiently. A system that can resolve this situation and enable even non-experts to respond quickly and accurately is needed.

[0080] 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.

[0081] In this invention, the server includes a means for adding alarm information to an analysis queue, a means for analyzing the alarm information using a generative AI model to generate an analysis result, and a means for translating the analysis result and presenting a corrective measure. This allows even non-experts to respond to alarms quickly and accurately. Furthermore, by utilizing a past database and knowledge base, it is possible to efficiently present appropriate corrective measures.

[0082] "Alarm information" refers to warnings and error messages that are generated by radios and other equipment during base station construction work.

[0083] A "terminal" is a device, such as a smartphone or tablet, that a user uses to input and display alarm information.

[0084] "JSON format" is an abbreviation for JavaScript Object Notation, and is a data format for sending alarm information to a server.

[0085] "Server" refers to a computer system that receives alarm information, analyzes, translates, and suggests corrective measures.

[0086] The "analysis queue" is a data queue that stores alarm information received within the server and analyzes it sequentially.

[0087] A "generative AI model" is an artificial intelligence model used to analyze alarm information and understand its meaning.

[0088] "Natural language processing technology" is a technology used by generative AI models to analyze the text of alarm information and understand its meaning.

[0089] A "translation model" is an artificial intelligence model used to translate analysis results into a language that the user can understand.

[0090] "Corrective measures" are specific steps and measures for resolving alarm problems that the server presents based on the analysis results and past databases and knowledge bases.

[0091] "LINE message format" refers to the format of a message application that a device uses to notify a user of alarm analysis results and corrective measures.

[0092] A "database" is a system that maintains records of past alarm information and corrective measures.

[0093] A "knowledge base" is an information aggregation system that accumulates expert knowledge and past experience.

[0094] The present invention is a system for improving the efficiency of alarm response during base station construction work. The program processing procedure of this system is described in detail below.

[0095] Alarm Input Acquisition

[0096] The user inputs the English alarm message displayed on the radio into the LINE message screen on a smartphone, tablet, or other device. This causes the alarm information to be acquired by the device. For example, the user can input the alarm message "Power supply error detected. Please check the power connection." into their device.

[0097] Alarm details transmission

[0098] The device converts the acquired alarm information into JSON format. The converted alarm information is sent to the server as an HTTP POST request. For example, the device sends data to the server in the format "{"alarm_message": "Power supply error detected. Please check the power connection."}". The server receives this request and prepares it for analysis.

[0099] Alarm Analysis

[0100] The server adds the received alarm information to the analysis queue. It then calls the generative AI model, which retrieves the alarm information from the analysis queue and begins analysis. The generative AI model uses natural language processing technology to analyze the meaning of the alarm information and identify the cause and countermeasures. For example, the generative AI model understands the meaning of "Power supply error detected. Please check the power connection." and realizes that it is a power-related problem.

[0101] Alarm translation and correction method suggestions

[0102] Once the server obtains the analysis results, it calls the translation model to translate the alarm information into Japanese. For example, the server translates "Power supply error detected. Please check the power connection." into "A power supply error has been detected. Please check the power connection." It then references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will suggest the corrective measure, "Check the BBU's power connection and reconnect if necessary."

[0103] Send results

[0104] The server sends the generated translation result and corrective measures to the device. The sent content is received by the device as an HTTP response, which the device converts into a LINE message format. For example, the response from the server is sent in the following format: {"translated_message": "A power supply error has been detected. Please check the power connection.", "corrective_action": "Check the BBU power connection and reconnect if necessary."}.

[0105] Result confirmation and processing

[0106] The device will display the translation results and corrective measures on the LINE message screen. The user will check this message and follow the instructions to take the necessary corrective measures. For example, if the message "A power error has been detected. Please check the power connection," is displayed, the user should check the power connection to the BBU (baseband unit) and reconnect it.

[0107] Specific examples

[0108] As a concrete example, consider the case where a user inputs an alarm saying, "Power supply error detected. Please check the power connection." The device sends this alarm information to the server, which analyzes it using a generative AI model. The analysis results are translated into Japanese and displayed as, "A power supply error has been detected. Please check the power connection." Furthermore, by referencing the database, the server presents a specific corrective measure: "Check the BBU power connection and reconnect if necessary." Ultimately, the problem is resolved quickly when the user follows this procedure and takes the appropriate action.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1:

[0111] Alarm Input Acquisition

[0112] The alarm information is acquired by the user by entering the alarm message displayed on the radio into the LINE message screen of their smartphone or tablet. Specifically, the user enters the alarm message "Power supply error detected. Please check the power connection." The entered alarm information is saved in the device's internal memory.

[0113] Input: Alarm message displayed on the radio

[0114] Output: Alarm information entered on the LINE message screen

[0115] Step 2:

[0116] Alarm details transmission

[0117] The alarm information acquired by the device is converted into JSON format and sent to the server. When converting the message, it is converted into a JSON format such as "{"alarm_message": "Power supply error detected. Please check the power connection."}". The converted alarm information is sent as an HTTP POST request. The server receives this request and saves the log in a database.

[0118] Input: Alarm information entered on the LINE message screen

[0119] Output: Alarm information in JSON format sent to the server as an HTTP POST request

[0120] Step 3:

[0121] Alarm Analysis

[0122] The server adds the received alarm information to an analysis queue. The generative AI model extracts the alarm information from the queue and analyzes it using natural language processing techniques. Specifically, it understands the alarm information through processes such as tokenization, semantic analysis, and context understanding. For example, it understands that the message "Power supply error detected. Please check the power connection" is a power-related problem.

[0123] Input: Alarm information in JSON format sent to the server

[0124] Output: Analysis results from the generative AI model

[0125] Step 4:

[0126] Alarm translation and correction method suggestions

[0127] The server obtains the analysis results obtained from the generative AI model and calls the translation model to translate the alarm information into Japanese. For example, it translates "Power supply error detected. Please check the power connection." into "A power supply error has been detected. Please check the power connection." The server then refers to its past database and knowledge base to search for an appropriate corrective measure. For example, it identifies the corrective measure as "Check the power connection of the BBU and reconnect if necessary."

[0128] Input: Analysis results from generative AI model

[0129] Output: Japanese translation by translation model and correction method

[0130] Step 5:

[0131] Send results

[0132] The server generates an HTTP response that sends the translation result and corrective actions to the device. The response is received by the device and converted into a LINE message format. For example, the following format is sent to the device: {"translated_message": "A power supply error has been detected. Please check the power connection.", "corrective_action": "Check the BBU power connection and reconnect if necessary."}.

[0133] Input: Japanese translation by translation model and correction method

[0134] Output: Translation results converted into LINE message format and correction methods

[0135] Step 6:

[0136] Result confirmation and processing

[0137] The device displays the translation result and corrective measures on the LINE message screen. The user can check the result and follow the instructions to take the necessary corrective measures. For example, if a user sees the message "A power supply error has been detected. Please check the power supply connection," they can check the power supply connection of the BBU and reconnect it if necessary.

[0138] Input: Translation results converted to LINE message format and correction methods

[0139] Output: User takes corrective action

[0140] (Application example 1)

[0141] 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."

[0142] One challenge is the difficulty of quickly and accurately analyzing alarm information generated by robots in factories and presenting appropriate corrective measures. In particular, when non-expert engineers respond to alarms, it can be difficult to quickly find appropriate countermeasures, which can reduce work efficiency and delay problem resolution.

[0143] 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.

[0144] In this invention, the server includes means for inputting alarm information, means for transmitting the input alarm information to the server, means for analyzing the alarm information and generating an analysis result, means for translating the analysis result and presenting a corrective procedure, means for transmitting the presented corrective procedure to a terminal, and means for displaying the corrective procedure via a smart device based on the alarm information, thereby enabling a prompt and accurate response to alarms issued by robots in a factory.

[0145] "Alarm information" is information about errors and warning messages generated by robots in the factory.

[0146] "Input means" refers to a means for inputting alarm information using a smart device or terminal.

[0147] The "transmission means" is a means for transmitting input alarm information to the server.

[0148] The "analysis means" is a means by which the server analyzes alarm information and generates an analysis result.

[0149] The "translation means" is a means for translating the generated analysis results and presenting corrective measures.

[0150] The "presentation means" is a means for transmitting the translated analysis results and corrective measures to the terminal.

[0151] The "means for displaying via a smart device" refers to a means for displaying corrective procedures on a smart device based on alarm information.

[0152] "Corrective measures" are specific procedures or measures to resolve a problem that are identified based on alarm information.

[0153] This invention is a system for quickly and accurately managing alarm information generated by robots in factories and suggesting appropriate corrective measures. Specifically, it implements a series of processes: inputting and transmitting alarm information, analyzing it, translating it, and suggesting corrective measures.

[0154] First, to input alarm information, a smart device (e.g., smart glasses or a smartphone) is used. The user inputs alarm information into the terminal using this smart device. For example, if the robot issues an "emergency stop error" alarm, the user can voice-input "Emergency stop error detected. Please check the emergency stop button." into the smart glasses.

[0155] Next, the terminal converts the input alarm information into JSON format and sends it as an HTTP request to the server, which receives the request and adds the alarm information to the analysis queue.

[0156] The server uses the generative AI model to analyze the alarm information. It uses natural language processing technology to analyze the content of the alarm information and identify the cause and countermeasures. For example, in the case of the alarm information "Emergency stop error detected," the generative AI model determines that the status of the emergency stop button needs to be checked.

[0157] The analysis results are translated into Japanese, and the server refers to a past database and knowledge base to search for appropriate corrective measures. For example, a corrective measure such as "Check the emergency stop button" is presented.

[0158] The server sends the translation results and correction instructions to the device, which receives them, converts them into a LINE message format, and displays them to the user. The user can then check the correction instructions on their smart device and take action according to the instructions.

[0159] For example, if the message "A power error has been detected. Please check the power connection" appears, the user can quickly resolve the issue by checking the robot's power connection and reconnecting it if necessary.

[0160] An example of a prompt is as follows:

[0161] Smart glasses display: "Please speak alarm information:"

[0162] User speaks: "Emergency stop error detected. Please check the emergency stop button."

[0163] This system will enable even engineers without specialized knowledge to respond to alarms quickly and accurately, and is expected to improve work efficiency and quality within the factory.

[0164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0165] Step 1:

[0166] A user inputs alarm information using a smart device. For example, the user inputs alarm information by voice using smart glasses. The input is converted into text and stored in the terminal as text alarm information.

[0167] Input: Alarm information (audio)

[0168] Output: Alarm information (text format)

[0169] Step 2:

[0170] The device converts the input alarm information into JSON format and sends it as an HTTP request to the server. The server receives this request and adds the alarm information to a queue.

[0171] Input: Alarm information (text format)

[0172] Output: Alarm information (JSON format)

[0173] Step 3:

[0174] The server calls the generative AI model, retrieves the alarm information from the queue, and begins analysis. The generative AI model uses natural language processing technology to analyze the content of the alarm information and identify the cause and countermeasures.

[0175] Input: Alarm information (JSON format)

[0176] Data processing: Analysis using natural language processing technology

[0177] Output: Analysis results (text format)

[0178] Step 4:

[0179] The server retrieves the analysis results and translates them into Japanese using a translation model. It then searches for appropriate corrective measures by referencing past databases and knowledge bases, and identifies specific corrective steps.

[0180] Input: Analysis results (text format)

[0181] Data processing: Translation and database reference to find corrective procedures

[0182] Output: Translation results and correction methods (text format)

[0183] Step 5:

[0184] The server then sends the translated analysis results and corrective measures to the device, which then receives them, converts them into LINE message format, and displays them to the user.

[0185] Input: Translation results and correction methods (text format)

[0186] Data processing: conversion to message format

[0187] Output: LINE message

[0188] Step 6:

[0189] The user checks the translation results and corrective measures displayed in the LINE message and follows the instructions to respond to the alarm. For example, if the message says "Please check the emergency stop button," the user should actually check the emergency stop button and take the necessary steps.

[0190] Input: LINE message (displayed corrective action)

[0191] Output: Physical alarm response WeChat, for example, button confirmation and appropriate operation

[0192] 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.

[0193] The present invention is a system for improving the efficiency of alarm responses during base station construction work, and is equipped with a function that recognizes the user's emotions and optimizes the response. Below, we will explain in detail how the system can be combined with an emotion engine.

[0194] 1. Alarm input acquisition

[0195] The user inputs the English alarm message displayed on the radio into the LINE message screen using a smartphone or other device, and the alarm information is then acquired by the device.

[0196] 2. User Emotion Recognition

[0197] The device activates an emotion engine that recognizes emotions from the user's input, facial expressions, voice, etc. For example, it analyzes whether the user is feeling anxious or impatient when inputting.

[0198] 3. Alarm details transmission

[0199] The alarm information and user emotion data acquired by the device are sent to the server. Specifically, this information is converted into JSON format and sent to the server as an HTTP request. The server receives this request.

[0200] 4. Alarm Analysis

[0201] The server adds the received alarm information to the analysis queue. Then, it calls the generative AI model, which extracts the alarm information from the queue and begins analyzing it. By analyzing the information while also referring to emotional data, it fine-tunes the response to the user.

[0202] 5. Alarm translation and correction method provided

[0203] Once the server receives the analysis results, it calls up a translation model to translate the alarm information into Japanese. Once translation is complete, it references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will present corrective measures, including steps to check the power supply connection status.

[0204] 6. Emotion-Based Response Modulation

[0205] The server adjusts the tone and content of the response message based on the user's emotional state, for example providing more polite and detailed instructions if the user is impatient.

[0206] 7. Send results

[0207] The server generates a translation result, provides corrections, and sends a response adjusted based on the emotion to the device. The content is received by the device as an HTTP response and converted into a LINE message format.

[0208] 8. Results confirmation and processing

[0209] The device will display the translation results and correction methods on the LINE message screen along with the adjusted response. The user can review and understand the content. If necessary, additional support and help will be provided.

[0210] 9. Implementation of specific correction work

[0211] The user follows the suggested corrective measures and takes the necessary corrective action, for example, by performing specific steps such as reconnecting the power or checking the cables.

[0212] As a concrete example, consider the following scenario: If a user inputs an alarm saying "Power supply error detected. Please check the power connection." and the emotion engine recognizes that the user is feeling anxious, the server will generate a response such as "A power supply error has been detected. Please do not worry. Please stay calm and check the power connection and reconnect if necessary." In this way, instructions that take the user's emotions into consideration can be provided, enabling faster and more accurate responses.

[0213] This system not only enables a quick and accurate response when an alarm occurs, but also provides support that takes the user's emotions into consideration, thereby improving work efficiency and quality and helping to reduce user stress.

[0214] The processing flow will be explained below.

[0215] Step 1:

[0216] The user types the English alarm message displayed on the radio into the LINE message screen. The device receives this message.

[0217] Step 2:

[0218] As soon as the device receives the user's input, it starts the emotion engine, which analyzes the user's facial expressions and voice tone to recognize the user's emotional state.

[0219] Step 3:

[0220] The alarm information and recognized emotion data acquired by the device are converted into JSON format and sent as an HTTP request to the server, which receives the request.

[0221] Step 4:

[0222] The server adds the received alarm information to the analysis queue. Then it calls the generative AI model, which retrieves the alarm information from the queue and begins analysis. In parallel, it also references emotion data and adjusts the analysis results.

[0223] Step 5:

[0224] The generative AI model uses natural language processing technology to perform semantic analysis of the alarm message, specifically analyzing the content of the error message and identifying its type and cause.

[0225] Step 6:

[0226] The server retrieves the analysis results, calls up a translation model, and translates the alarm information into Japanese. Based on the translated content, it references past databases and knowledge bases to search for appropriate corrective measures.

[0227] Step 7:

[0228] The server combines the translation results with the correction methods and adjusts the response message based on the emotional data provided by the emotion engine. For example, if the user is feeling anxious, the response message will be changed to a calming tone.

[0229] Step 8:

[0230] The server sends the adjusted response message to the device as an HTTP response. The device receives this response and converts it into a LINE message format.

[0231] Step 9:

[0232] The device displays the translation results and corrections on the LINE message screen, and the displayed content is tailored to the user's emotional state.

[0233] Step 10:

[0234] The user takes appropriate corrective action according to the suggested corrective measures. For example, if the user checks the power connection status and tries to reconnect it, a message will be displayed stating, "A power error has been detected. Please stay calm and check the power connection and reconnect if necessary."

[0235] These specific processing steps enable a quick and accurate response when an alarm occurs, and since the user's emotions are taken into consideration, stress is reduced and work efficiency is improved. In addition, the emotion recognition function provides support so that the user can continue working with peace of mind.

[0236] Example 2

[0237] 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."

[0238] Alarm responses during base station construction work require rapid and accurate responses, but user stress and frustration can reduce work efficiency. Alarm information is often displayed in different languages, often resulting in delays in translation and presentation of corrective measures. Conventional systems lack optimal support that combines emotion recognition and natural language processing, increasing the burden on users and resulting in reduced work quality. Therefore, a system that optimizes responses based on user emotions and provides rapid and accurate responses is needed.

[0239] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0240] In this invention, the server includes means for adding alarm information to an analysis queue and calling a generative AI model for analysis, means for translating the analysis results and presenting corrective measures, and means for adjusting a response message based on the user's emotional state. This enables prompt and accurate support while taking the user's emotions into consideration when an alarm occurs, improving work efficiency and quality and reducing user stress.

[0241] "Alarm information" is a message indicating an abnormality or warning that occurs during base station construction work.

[0242] The "means for inputting" is an interface that allows a user to input alarm information into the system using a smartphone or other terminal.

[0243] A "terminal" is a device for acquiring and transmitting alarm information and user emotion data, and includes smartphones, tablets, etc.

[0244] An "emotion recognition engine" is software or an algorithm that analyzes emotions from user input, facial expressions, voice, etc.

[0245] The JSON format is a text-based data exchange format that structures data and facilitates communication between systems.

[0246] A "server" is a computer system that receives alarm information and emotion data, analyzes them, and generates responses.

[0247] An "analysis queue" is a data structure for processing alarm information awaiting analysis in order.

[0248] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze alarm information and generate appropriate responses or corrective measures.

[0249] "Translation" is the process of converting the analysis results from the original text into another language (for example, Japanese).

[0250] "Corrective measures" refer to specific procedures and measures to resolve problems based on alarm information.

[0251] The "means for adjusting the response message" is a process for changing the tone and content of the response message based on the user's emotional state.

[0252] "LINE message format" refers to the message format used in the LINE application.

[0253] The present invention provides a system for improving the efficiency of alarm responses during base station construction work, and is particularly equipped with a function for recognizing a user's emotions and optimizing responses. Specific embodiments will be described below.

[0254] Hardware and software used

[0255] The hardware used includes devices such as smartphones and tablets, as well as servers equipped with high-performance CPUs and GPUs, while the software used includes the LINE messaging app, an emotion recognition engine (e.g., emotion recognition API), a generative AI model (e.g., language generation model), and a translation model (e.g., automatic translation API).

[0256] Explanation of program processing

[0257] Alarm Input Acquisition

[0258] The user inputs the English alarm information displayed on the radio as a LINE message on a smartphone or other device. The device then acquires the alarm information. At this time, the user opens the chat screen of the LINE app and inputs the English alarm message as text.

[0259] User Emotion Recognition

[0260] The device activates an emotion engine to recognize emotions from the user's input, facial expressions, and voice. The device uses data acquired from the smartphone's camera and microphone and executes emotion recognition algorithms. For example, the emotion engine detects if the user looks anxious or if their voice is trembling.

[0261] Alarm details transmission

[0262] The device converts the acquired alarm information and user emotion data into JSON format and sends it to the server as an HTTP request. The server receives this request. Specifically, the device sends the data using the "POST" method, and the server parses the data using a function such as "JSON.parse()".

[0263] Alarm Analysis

[0264] The server adds the received alarm information to the analysis queue, then calls the generative AI model to begin analysis. The server then removes the alarm information from the queue and passes it to the AI ​​model as input data. When the generative AI model analyzes the input "Power supply error detected," it finds abnormal patterns from past data.

[0265] Alarm translation and correction method suggestions

[0266] The server calls up the translation model and translates the alarm information into Japanese. It then refers to the past database and knowledge base to search for the appropriate corrective action. For example, the corrective action for a "Power supply error" might be to "Check the power supply connection status."

[0267] Emotion-Based Response Modulation

[0268] The server adjusts the tone and content of the response message based on the user's emotional state. For example, if the user is feeling anxious, the server uses more reassuring and polite language. The server generates a message like, "Don't worry. Stay calm and check the steps."

[0269] Send results

[0270] The server sends the translation results, correction methods, and responses adjusted based on emotions to the device. The server sends the data as an HTTP response, which the device receives. The device then converts the received data into LINE message format.

[0271] Result confirmation and processing

[0272] The device displays the translation result and correction methods on the LINE message screen along with the adjusted response. The user can review and understand the content. The device may also record the message display timestamp and the user's reaction data.

[0273] Implementing specific correction work

[0274] The user follows the suggested corrective action and performs the necessary corrective action, such as reconnecting the power or checking the cables. The user follows the detailed steps, including arrows and diagrams.

[0275] Examples of concrete examples and prompts

[0276] For example, if a user inputs the alarm "Power supply error detected. Please check the power connection" into the LINE app and unconsciously shows signs of restlessness, the emotion engine will recognize this as anxiety. The server will receive this and generate a response such as "A power supply error has been detected. Please stay calm and check the power connection and reconnect if necessary," and send it as a LINE message.

[0277] An example prompt is:

[0278] "Please enter the alarm displayed on your radio. Also, briefly describe the emotions you felt as you typed."

[0279] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0280] Step 1:

[0281] The user inputs the English alarm information displayed on the radio as a LINE message on a smartphone or other device. The input alarm information is then acquired by the device. Specifically, the user opens the LINE app and inputs alarm information such as "Power supply error detected. Please check the power connection" into the chat screen. The input data is saved in text format in the device's memory.

[0282] Step 2:

[0283] The device launches an emotion recognition engine to recognize emotions from the user's input, facial expressions, voice, etc. Input data includes the user's input text, camera footage, and voice. The emotion recognition engine analyzes this data and detects the emotion the user is feeling (e.g., anxiety, impatience). The output data is generated in JSON format, listing the type of emotion recognized and its intensity.

[0284] Step 3:

[0285] The device converts the acquired alarm information and user emotion data into JSON format and sends it to the server as an HTTP request. Specifically, the device combines the alarm information and emotion data into a single JSON object and sends it to the server using a "POST" request. The input data is the alarm information and emotion data, and the output data is a status indicating that the transmission was successful.

[0286] Step 4:

[0287] The server adds the received alarm information to the analysis queue and calls the generative AI model to begin analysis. The input data includes the JSON object sent from the client. Specifically, the server adds this data to the analysis queue and passes it to the generative AI model in the appropriate order. The generative AI model understands the content of the alarm from the alarm statement and generates specific countermeasures. The output data is the type of alarm and the corresponding countermeasures.

[0288] Step 5:

[0289] The server calls the translation model and translates the alarm information into Japanese. The input data includes the alarm text from the analysis results. Specifically, the server calls the translation API and translates from English to Japanese. The output data is the translated Japanese alarm text.

[0290] Step 6:

[0291] The server references historical databases and knowledge bases to search for appropriate corrective measures based on the analysis results. Input data includes alarm information translated into Japanese and analysis results. Specifically, the server executes a database query to retrieve relevant corrective measures. The output data is detailed instructions for the corrective measures.

[0292] Step 7:

[0293] The server adjusts the tone and content of the response message based on the user's emotional state. The input data includes the user's emotional data and corrective action instructions. Specifically, the server analyzes the emotional data and generates an emotion-sensitive message, such as "Don't worry. Please stay calm and review the steps." The output data is the adjusted response message.

[0294] Step 8:

[0295] The server generates a translation result, provides corrective measures, and sends a response adjusted based on the emotion to the device. The input data includes the translated alarm information, corrective measures, and an adjusted response message. Specifically, the server compiles this information into a single JSON object and sends it to the device as an "HTTP response." The output data is a status indicating successful transmission.

[0296] Step 9:

[0297] The device displays the translation result and correction method on the LINE message screen along with an adjusted response. The input data includes a JSON object received from the server. Specifically, the device parses the JSON data, converts it into a LINE message format, and displays it to the user. The output is when the user checks it and understands the content.

[0298] Step 10:

[0299] The user follows the presented corrective measures and performs the necessary corrective work. The input data includes the corrective measures displayed in the LINE message. As specific actions, the user performs specific steps such as reconnecting the power and checking the cables. The output is that the work has been completed.

[0300] (Application example 2)

[0301] 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."

[0302] Conventional alarm response systems respond uniformly without considering the user's emotional state, which can delay appropriate responses and increase stress, especially when the user is feeling anxious or impatient. Furthermore, the translation of alarm information and the presentation of corrective measures are also uniform, making it difficult to provide individualized responses tailored to the user's situation. Furthermore, there was no way to recognize the user's emotions and optimize the response based on them. This resulted in problems with reduced accuracy and speed of responses.

[0303] 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 inputting alarm information, means for transmitting the input alarm information and emotion data to the server, means for analyzing the alarm information and emotion data and generating an analysis result, means for translating the analysis result and presenting a corrective measure, means for adjusting the presented corrective measure based on the emotion and transmitting it to the terminal, and means for recognizing the user's emotion. This enables individual responses that take the user's emotion into consideration, improving the accuracy and speed of alarm responses. It also makes it possible to reduce user stress and provide more effective support.

[0304] "Alarm information" refers to warning or error information issued by a system or device, which alerts the user to a specific problem or alerts the user to a particular problem.

[0305] "Emotion data" is data that indicates the emotional state of a user analyzed from facial expressions, voice, and text input.

[0306] A "server" is a central control unit that receives, analyzes, and processes data sent by users.

[0307] The "analysis result" is the result information obtained by the server analyzing the alarm information and emotion data.

[0308] "Corrective measures" indicate specific procedures and methods for dealing with alarm information.

[0309] "Translation" refers to the process of converting analysis results and corrective measures into a language that is easy for users to understand.

[0310] A "terminal" is a connected device used by a user, such as a smartphone or smart glasses.

[0311] "Means for recognizing emotions" refers to technology that identifies emotions from a user's facial expressions, voice, and text input.

[0312] "Adjustment" refers to the process of optimizing the corrective measures and response content based on the user's emotional data.

[0313] A specific example of the present invention is a system called "Security Emotion Manager," the details of which are given below.

[0314] First, a user inputs alarm information from a security system using a smartphone or smart glasses. This alarm information is input by the user, and the specific content of the alarm is obtained in text format.

[0315] The device then uses its built-in camera and microphone to recognize the user's emotional state. It then uses DeepFace facial recognition software and other voice emotion recognition engines to extract emotional data from the user's facial expressions and voice. This emotional data is then sent to the server along with the alarm information. The device then converts this data into JSON format and sends it as an HTTP request.

[0316] The server analyzes the received alarm information and emotion data and generates an analysis result. It uses natural language processing technology to understand the content of the alarm information. Furthermore, it supplements the analysis result with a generative AI model and suggests the optimal corrective measures by referencing past databases and knowledge bases.

[0317] Once the analysis and corrective measures are ready, the server can adjust this information based on the user's emotions—for example, by providing more polite and specific instructions if the user is feeling anxious—using a generative AI model.

[0318] Finally, the adjusted instructions and corrective measures are sent to the terminal and displayed on the user's device, allowing the user to review them and take specific corrective actions, enabling the user to respond appropriately and promptly.

[0319] As a concrete example, consider a case where a user inputs alarm text information such as "Unauthorized access detected. Please verify the security status." and provides an image path as "user_image.jpg" and an audio path as "user_voice.wav." The server generates an optimal corrective action based on this information and provides a response tailored to the user's emotions. For example, if the user expresses impatience, a specific instruction such as "Unauthorized access detected. Please remain calm. Please verify the security status." is returned.

[0320] The system recognizes the user's emotions and takes them into consideration when providing assistance, improving the accuracy and speed of responses and reducing user stress. It also utilizes cutting-edge technologies such as DeepFace and generative AI models to improve the overall user experience.

[0321] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0322] Step 1:

[0323] A user inputs alarm information from a security system using a smartphone or smart glasses. For example, the user inputs text such as "Unauthorized access detected. Please verify the security status." and sends it to an application on the device. The input of this procedure is the alarm information in text format, and the output is the alarm information received by the device.

[0324] Step 2:

[0325] The device recognizes the user's emotions. The device's built-in camera takes a photo of the user's face and a microphone records their voice. Then, using facial recognition software "DeepFace" and a voice emotion recognition engine, these data are analyzed to extract emotional data. The input for this procedure is the user's facial image and voice data, and the output is emotional data that indicates the user's emotional state.

[0326] Step 3:

[0327] The alarm information and emotion data acquired by the device are converted into JSON format and sent to the server as an HTTP request. The input for this data transmission is the alarm information and emotion data, and the output is a transmission completion notification to the server.

[0328] Step 4:

[0329] The server analyzes the received alarm information and emotional data. First, it uses natural language processing technology to analyze the alarm information and understand its content. Next, it uses a generative AI model to supplement the analysis results and perform a deeper analysis of the meaning and impact of the alarm information. The input to this process is the alarm information and emotional data received by the server, and the output is the analysis results.

[0330] Step 5:

[0331] Based on the analysis results, the server searches for corrective measures by referring to a past database or knowledge base. For example, it refers to how similar alarms have been handled in the past and proposes the optimal corrective measures. The input to this procedure is the analysis results, and the output is the corrective measures.

[0332] Step 6:

[0333] The server adjusts the corrective measures and response messages based on the user's emotional data. For example, if the user feels anxious, the server adjusts the response messages to include polite and specific instructions. The inputs to this procedure are the corrective measures and the user's emotional data, and the output is the adjusted response message.

[0334] Step 7:

[0335] The server sends the adjusted response message and the correction method to the terminal. The input of this data transmission is the adjusted response message and the correction method, and the output is a transmission completion notification to the terminal.

[0336] Step 8:

[0337] The terminal displays the received response message and corrective action to the user. The user confirms it and performs specific corrective action. The input of this procedure is the message and corrective action received by the terminal, and the output is the specific operation or response by the user.

[0338] This allows the user to deal with the alarm quickly and appropriately, and receive emotional support.

[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 provides a system for improving the efficiency of alarm response during base station construction work. Specific embodiments for carrying out the present invention will be described below.

[0356] 1. Alarm input acquisition

[0357] The user inputs the English alarm message displayed on the radio into the LINE message screen using a smartphone or other device, and the alarm information is then acquired by the device.

[0358] 2. Alarm details transmission

[0359] The alarm information acquired by the device is sent to the server. Specifically, the input alarm information is converted into JSON format and sent to the server as an HTTP request. The server receives this request and prepares for analysis.

[0360] 3. Alarm Analysis

[0361] The server adds the received alarm information to an analysis queue. It then calls the generative AI model, which extracts the alarm information from the queue and begins analysis. The generative AI model uses natural language processing technology to analyze the meaning of the alarm information and identify causes and countermeasures.

[0362] 4. Alarm translation and correction method provided

[0363] Once the server receives the analysis results, it calls up a translation model to translate the alarm information into Japanese. Once translation is complete, it references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will present corrective measures, including steps to check the power supply connection status.

[0364] 5. Send results

[0365] The server sends the translation results and correction instructions to the device. The sent content is received by the device as an HTTP response and converted into a LINE message format.

[0366] 6. Results confirmation and processing

[0367] The device will display the translation results and corrective measures on the LINE message screen. The user can check this and take the necessary corrective measures as instructed. For example, if the message "A power error has been detected. Please check the power connection" is displayed, the user should check the power connection to the BBU (baseband unit) and reconnect it.

[0368] As a concrete example, consider the following scenario: A user inputs an alarm saying, "Power supply error detected. Please check the power connection." The device sends this alarm information to a server, which analyzes it using a generative AI model. The analysis results are translated into Japanese and displayed as, "A power supply error has been detected. Please check the power connection." Furthermore, the server refers to a database and presents a specific corrective measure: "Check the BBU's power connection and reconnect if necessary." Ultimately, the user follows this procedure and takes the appropriate action, quickly resolving the problem.

[0369] This system will enable even engineers without specialized knowledge to respond quickly and accurately when an alarm occurs, which is expected to improve work efficiency and quality.

[0370] The processing flow will be explained below.

[0371] Step 1:

[0372] The user enters the English alarm message displayed on the radio into the LINE message screen. The device receives this input and prepares for the next process.

[0373] Step 2:

[0374] The device converts the input alarm message into JSON format and sends it as an HTTP request to the server, which receives the request.

[0375] Step 3:

[0376] The server adds the received alarm message to the analysis queue, then invokes the generative AI model to take the alarm message from the queue and start analyzing it.

[0377] Step 4:

[0378] The generative AI model uses natural language processing technology to semantically analyze the alarm message, specifically analyzing the structure and content of the message to identify the type and cause of the error.

[0379] Step 5:

[0380] The server receives the analysis results and calls the appropriate translation model based on the results. The translation model translates the English alarm content into Japanese.

[0381] Step 6:

[0382] The server compares the translated analysis results with historical and knowledge bases to find the appropriate corrective action, for example, if a power error is detected, it may include steps to check the power connection.

[0383] Step 7:

[0384] The server combines the translation results with specific corrective actions to generate a response message, which is presented to the user in a format that is easy to understand.

[0385] Step 8:

[0386] The server generates a response message and sends it to the device as an HTTP response. The device receives this response and converts it into a LINE message format based on the analysis and translation results.

[0387] Step 9:

[0388] The device displays the translation result and correction instructions on the LINE message screen, and the user can check the message and understand the content.

[0389] Step 10:

[0390] The user follows the suggested corrective measures and takes the necessary corrective action, for example, by performing specific steps such as reconnecting the power or checking the cables.

[0391] This processing step enables a quick and accurate response when an alarm occurs, improving the efficiency and quality of work.

[0392] Example 1

[0393] 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."

[0394] Responding to alarms during base station construction work requires a high level of specialized knowledge, making it difficult to respond quickly. Furthermore, the lack of a way to effectively utilize case studies from other sites and past data makes it difficult to solve problems efficiently. A system that can resolve this situation and enable even non-experts to respond quickly and accurately is needed.

[0395] 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.

[0396] In this invention, the server includes a means for adding alarm information to an analysis queue, a means for analyzing the alarm information using a generative AI model to generate an analysis result, and a means for translating the analysis result and presenting a corrective measure. This allows even non-experts to respond to alarms quickly and accurately. Furthermore, by utilizing a past database and knowledge base, it is possible to efficiently present appropriate corrective measures.

[0397] "Alarm information" refers to warnings and error messages that are generated by radios and other equipment during base station construction work.

[0398] A "terminal" is a device, such as a smartphone or tablet, that a user uses to input and display alarm information.

[0399] "JSON format" is an abbreviation for JavaScript Object Notation, and is a data format for sending alarm information to a server.

[0400] "Server" refers to a computer system that receives alarm information, analyzes, translates, and suggests corrective measures.

[0401] The "analysis queue" is a data queue that stores alarm information received within the server and analyzes it sequentially.

[0402] A "generative AI model" is an artificial intelligence model used to analyze alarm information and understand its meaning.

[0403] "Natural language processing technology" is a technology used by generative AI models to analyze the text of alarm information and understand its meaning.

[0404] A "translation model" is an artificial intelligence model used to translate analysis results into a language that the user can understand.

[0405] "Corrective measures" are specific steps and measures for resolving alarm problems that the server presents based on the analysis results and past databases and knowledge bases.

[0406] "LINE message format" refers to the format of a message application that a device uses to notify a user of alarm analysis results and corrective measures.

[0407] A "database" is a system that maintains records of past alarm information and corrective measures.

[0408] A "knowledge base" is an information aggregation system that accumulates expert knowledge and past experience.

[0409] The present invention is a system for improving the efficiency of alarm response during base station construction work. The program processing procedure of this system is described in detail below.

[0410] Alarm Input Acquisition

[0411] The user inputs the English alarm message displayed on the radio into the LINE message screen on a smartphone, tablet, or other device. This causes the alarm information to be acquired by the device. For example, the user can input the alarm message "Power supply error detected. Please check the power connection." into their device.

[0412] Alarm details transmission

[0413] The device converts the acquired alarm information into JSON format. The converted alarm information is sent to the server as an HTTP POST request. For example, the device sends data to the server in the format "{"alarm_message": "Power supply error detected. Please check the power connection."}". The server receives this request and prepares it for analysis.

[0414] Alarm Analysis

[0415] The server adds the received alarm information to the analysis queue. It then calls the generative AI model, which retrieves the alarm information from the analysis queue and begins analysis. The generative AI model uses natural language processing technology to analyze the meaning of the alarm information and identify the cause and countermeasures. For example, the generative AI model understands the meaning of "Power supply error detected. Please check the power connection." and realizes that it is a power-related problem.

[0416] Alarm translation and correction method suggestions

[0417] Once the server obtains the analysis results, it calls the translation model to translate the alarm information into Japanese. For example, the server translates "Power supply error detected. Please check the power connection." into "A power supply error has been detected. Please check the power connection." It then references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will suggest the corrective measure, "Check the BBU's power connection and reconnect if necessary."

[0418] Send results

[0419] The server sends the generated translation result and corrective measures to the device. The sent content is received by the device as an HTTP response, which the device converts into a LINE message format. For example, the response from the server is sent in the following format: {"translated_message": "A power supply error has been detected. Please check the power connection.", "corrective_action": "Check the BBU power connection and reconnect if necessary."}.

[0420] Result confirmation and processing

[0421] The device will display the translation results and corrective measures on the LINE message screen. The user will check this message and follow the instructions to take the necessary corrective measures. For example, if the message "A power error has been detected. Please check the power connection," is displayed, the user should check the power connection to the BBU (baseband unit) and reconnect it.

[0422] Specific examples

[0423] As a concrete example, consider the case where a user inputs an alarm saying, "Power supply error detected. Please check the power connection." The device sends this alarm information to the server, which analyzes it using a generative AI model. The analysis results are translated into Japanese and displayed as, "A power supply error has been detected. Please check the power connection." Furthermore, by referencing the database, the server presents a specific corrective measure: "Check the BBU power connection and reconnect if necessary." Ultimately, the problem is resolved quickly when the user follows this procedure and takes the appropriate action.

[0424] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0425] Step 1:

[0426] Alarm Input Acquisition

[0427] The alarm information is acquired by the user by entering the alarm message displayed on the radio into the LINE message screen of their smartphone or tablet. Specifically, the user enters the alarm message "Power supply error detected. Please check the power connection." The entered alarm information is saved in the device's internal memory.

[0428] Input: Alarm message displayed on the radio

[0429] Output: Alarm information entered on the LINE message screen

[0430] Step 2:

[0431] Alarm details transmission

[0432] The alarm information acquired by the device is converted into JSON format and sent to the server. When converting the message, it is converted into a JSON format such as "{"alarm_message": "Power supply error detected. Please check the power connection."}". The converted alarm information is sent as an HTTP POST request. The server receives this request and saves the log in a database.

[0433] Input: Alarm information entered on the LINE message screen

[0434] Output: Alarm information in JSON format sent to the server as an HTTP POST request

[0435] Step 3:

[0436] Alarm Analysis

[0437] The server adds the received alarm information to an analysis queue. The generative AI model extracts the alarm information from the queue and analyzes it using natural language processing techniques. Specifically, it understands the alarm information through processes such as tokenization, semantic analysis, and context understanding. For example, it understands that the message "Power supply error detected. Please check the power connection" is a power-related problem.

[0438] Input: Alarm information in JSON format sent to the server

[0439] Output: Analysis results from the generative AI model

[0440] Step 4:

[0441] Alarm translation and correction method suggestions

[0442] The server obtains the analysis results obtained from the generative AI model and calls the translation model to translate the alarm information into Japanese. For example, it translates "Power supply error detected. Please check the power connection." into "A power supply error has been detected. Please check the power connection." The server then refers to its past database and knowledge base to search for an appropriate corrective measure. For example, it identifies the corrective measure as "Check the power connection of the BBU and reconnect if necessary."

[0443] Input: Analysis results from generative AI model

[0444] Output: Japanese translation by translation model and correction method

[0445] Step 5:

[0446] Send results

[0447] The server generates an HTTP response that sends the translation result and corrective actions to the device. The response is received by the device and converted into a LINE message format. For example, the following format is sent to the device: {"translated_message": "A power supply error has been detected. Please check the power connection.", "corrective_action": "Check the BBU power connection and reconnect if necessary."}.

[0448] Input: Japanese translation by translation model and correction method

[0449] Output: Translation results converted into LINE message format and correction methods

[0450] Step 6:

[0451] Result confirmation and processing

[0452] The device displays the translation result and corrective measures on the LINE message screen. The user can check the result and follow the instructions to take the necessary corrective measures. For example, if a user sees the message "A power supply error has been detected. Please check the power supply connection," they can check the power supply connection of the BBU and reconnect it if necessary.

[0453] Input: Translation results converted to LINE message format and correction methods

[0454] Output: User takes corrective action

[0455] (Application example 1)

[0456] 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."

[0457] One challenge is the difficulty of quickly and accurately analyzing alarm information generated by robots in factories and presenting appropriate corrective measures. In particular, when non-expert engineers respond to alarms, it can be difficult to quickly find appropriate countermeasures, which can reduce work efficiency and delay problem resolution.

[0458] 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.

[0459] In this invention, the server includes means for inputting alarm information, means for transmitting the input alarm information to the server, means for analyzing the alarm information and generating an analysis result, means for translating the analysis result and presenting a corrective procedure, means for transmitting the presented corrective procedure to a terminal, and means for displaying the corrective procedure via a smart device based on the alarm information, thereby enabling a prompt and accurate response to alarms issued by robots in a factory.

[0460] "Alarm information" is information about errors and warning messages generated by robots in the factory.

[0461] "Input means" refers to a means for inputting alarm information using a smart device or terminal.

[0462] The "transmission means" is a means for transmitting input alarm information to the server.

[0463] The "analysis means" is a means by which the server analyzes alarm information and generates an analysis result.

[0464] The "translation means" is a means for translating the generated analysis results and presenting corrective measures.

[0465] The "presentation means" is a means for transmitting the translated analysis results and corrective measures to the terminal.

[0466] The "means for displaying via a smart device" refers to a means for displaying corrective procedures on a smart device based on alarm information.

[0467] "Corrective measures" are specific procedures or measures to resolve a problem that are identified based on alarm information.

[0468] This invention is a system for quickly and accurately managing alarm information generated by robots in factories and suggesting appropriate corrective measures. Specifically, it implements a series of processes: inputting and transmitting alarm information, analyzing it, translating it, and suggesting corrective measures.

[0469] First, to input alarm information, a smart device (e.g., smart glasses or a smartphone) is used. The user inputs alarm information into the terminal using this smart device. For example, if the robot issues an "emergency stop error" alarm, the user can voice-input "Emergency stop error detected. Please check the emergency stop button." into the smart glasses.

[0470] Next, the terminal converts the input alarm information into JSON format and sends it as an HTTP request to the server, which receives the request and adds the alarm information to the analysis queue.

[0471] The server uses the generative AI model to analyze the alarm information. It uses natural language processing technology to analyze the content of the alarm information and identify the cause and countermeasures. For example, in the case of the alarm information "Emergency stop error detected," the generative AI model determines that the status of the emergency stop button needs to be checked.

[0472] The analysis results are translated into Japanese, and the server refers to a past database and knowledge base to search for appropriate corrective measures. For example, a corrective measure such as "Check the emergency stop button" is presented.

[0473] The server sends the translation results and correction instructions to the device, which receives them, converts them into a LINE message format, and displays them to the user. The user can then check the correction instructions on their smart device and take action according to the instructions.

[0474] For example, if the message "A power error has been detected. Please check the power connection" appears, the user can quickly resolve the issue by checking the robot's power connection and reconnecting it if necessary.

[0475] An example of a prompt is as follows:

[0476] Smart glasses display: "Please speak alarm information:"

[0477] User speaks: "Emergency stop error detected. Please check the emergency stop button."

[0478] This system will enable even engineers without specialized knowledge to respond to alarms quickly and accurately, and is expected to improve work efficiency and quality within the factory.

[0479] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0480] Step 1:

[0481] A user inputs alarm information using a smart device. For example, the user inputs alarm information by voice using smart glasses. The input is converted into text and stored in the terminal as text alarm information.

[0482] Input: Alarm information (audio)

[0483] Output: Alarm information (text format)

[0484] Step 2:

[0485] The device converts the input alarm information into JSON format and sends it as an HTTP request to the server. The server receives this request and adds the alarm information to a queue.

[0486] Input: Alarm information (text format)

[0487] Output: Alarm information (JSON format)

[0488] Step 3:

[0489] The server calls the generative AI model, retrieves the alarm information from the queue, and begins analysis. The generative AI model uses natural language processing technology to analyze the content of the alarm information and identify the cause and countermeasures.

[0490] Input: Alarm information (JSON format)

[0491] Data processing: Analysis using natural language processing technology

[0492] Output: Analysis results (text format)

[0493] Step 4:

[0494] The server retrieves the analysis results and translates them into Japanese using a translation model. It then searches for appropriate corrective measures by referencing past databases and knowledge bases, and identifies specific corrective steps.

[0495] Input: Analysis results (text format)

[0496] Data processing: Translation and database reference to find corrective procedures

[0497] Output: Translation results and correction methods (text format)

[0498] Step 5:

[0499] The server then sends the translated analysis results and corrective measures to the device, which then receives them, converts them into LINE message format, and displays them to the user.

[0500] Input: Translation results and correction methods (text format)

[0501] Data processing: conversion to message format

[0502] Output: LINE message

[0503] Step 6:

[0504] The user checks the translation results and corrective measures displayed in the LINE message and follows the instructions to respond to the alarm. For example, if the message says "Please check the emergency stop button," the user should actually check the emergency stop button and take the necessary steps.

[0505] Input: LINE message (displayed corrective action)

[0506] Output: Physical alarm response WeChat, for example, button confirmation and appropriate operation

[0507] 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.

[0508] The present invention is a system for improving the efficiency of alarm responses during base station construction work, and is equipped with a function that recognizes the user's emotions and optimizes the response. Below, we will explain in detail how the system can be combined with an emotion engine.

[0509] 1. Alarm input acquisition

[0510] The user inputs the English alarm message displayed on the radio into the LINE message screen using a smartphone or other device, and the alarm information is then acquired by the device.

[0511] 2. User Emotion Recognition

[0512] The device activates an emotion engine that recognizes emotions from the user's input, facial expressions, voice, etc. For example, it analyzes whether the user is feeling anxious or impatient when inputting.

[0513] 3. Alarm details transmission

[0514] The alarm information and user emotion data acquired by the device are sent to the server. Specifically, this information is converted into JSON format and sent to the server as an HTTP request. The server receives this request.

[0515] 4. Alarm Analysis

[0516] The server adds the received alarm information to the analysis queue. Then, it calls the generative AI model, which extracts the alarm information from the queue and begins analyzing it. By analyzing the information while also referring to emotional data, it fine-tunes the response to the user.

[0517] 5. Alarm translation and correction method provided

[0518] Once the server receives the analysis results, it calls up a translation model to translate the alarm information into Japanese. Once translation is complete, it references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will present corrective measures, including steps to check the power supply connection status.

[0519] 6. Emotion-Based Response Modulation

[0520] The server adjusts the tone and content of the response message based on the user's emotional state, for example providing more polite and detailed instructions if the user is impatient.

[0521] 7. Send results

[0522] The server generates a translation result, provides corrections, and sends a response adjusted based on the emotion to the device. The content is received by the device as an HTTP response and converted into a LINE message format.

[0523] 8. Results confirmation and processing

[0524] The device will display the translation results and correction methods on the LINE message screen along with the adjusted response. The user can review and understand the content. If necessary, additional support and help will be provided.

[0525] 9. Implementation of specific correction work

[0526] The user follows the suggested corrective measures and takes the necessary corrective action, for example, by performing specific steps such as reconnecting the power or checking the cables.

[0527] As a concrete example, consider the following scenario: If a user inputs an alarm saying "Power supply error detected. Please check the power connection." and the emotion engine recognizes that the user is feeling anxious, the server will generate a response such as "A power supply error has been detected. Please do not worry. Please stay calm and check the power connection and reconnect if necessary." In this way, instructions that take the user's emotions into consideration can be provided, enabling faster and more accurate responses.

[0528] This system not only enables a quick and accurate response when an alarm occurs, but also provides support that takes the user's emotions into consideration, thereby improving work efficiency and quality and helping to reduce user stress.

[0529] The processing flow will be explained below.

[0530] Step 1:

[0531] The user types the English alarm message displayed on the radio into the LINE message screen. The device receives this message.

[0532] Step 2:

[0533] As soon as the device receives the user's input, it starts the emotion engine, which analyzes the user's facial expressions and voice tone to recognize the user's emotional state.

[0534] Step 3:

[0535] The alarm information and recognized emotion data acquired by the device are converted into JSON format and sent as an HTTP request to the server, which receives the request.

[0536] Step 4:

[0537] The server adds the received alarm information to the analysis queue. Then it calls the generative AI model, which retrieves the alarm information from the queue and begins analysis. In parallel, it also references emotion data and adjusts the analysis results.

[0538] Step 5:

[0539] The generative AI model uses natural language processing technology to perform semantic analysis of the alarm message, specifically analyzing the content of the error message and identifying its type and cause.

[0540] Step 6:

[0541] The server retrieves the analysis results, calls up a translation model, and translates the alarm information into Japanese. Based on the translated content, it references past databases and knowledge bases to search for appropriate corrective measures.

[0542] Step 7:

[0543] The server combines the translation results with the correction methods and adjusts the response message based on the emotional data provided by the emotion engine. For example, if the user is feeling anxious, the response message will be changed to a calming tone.

[0544] Step 8:

[0545] The server sends the adjusted response message to the device as an HTTP response. The device receives this response and converts it into a LINE message format.

[0546] Step 9:

[0547] The device displays the translation results and corrections on the LINE message screen, and the displayed content is tailored to the user's emotional state.

[0548] Step 10:

[0549] The user takes appropriate corrective action according to the suggested corrective measures. For example, if the user checks the power connection status and tries to reconnect it, a message will be displayed stating, "A power error has been detected. Please stay calm and check the power connection and reconnect if necessary."

[0550] These specific processing steps enable a quick and accurate response when an alarm occurs, and since the user's emotions are taken into consideration, stress is reduced and work efficiency is improved. In addition, the emotion recognition function provides support so that the user can continue working with peace of mind.

[0551] Example 2

[0552] 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."

[0553] Alarm responses during base station construction work require rapid and accurate responses, but user stress and frustration can reduce work efficiency. Alarm information is often displayed in different languages, often resulting in delays in translation and presentation of corrective measures. Conventional systems lack optimal support that combines emotion recognition and natural language processing, increasing the burden on users and resulting in reduced work quality. Therefore, a system that optimizes responses based on user emotions and provides rapid and accurate responses is needed.

[0554] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0555] In this invention, the server includes means for adding alarm information to an analysis queue and calling a generative AI model for analysis, means for translating the analysis results and presenting corrective measures, and means for adjusting a response message based on the user's emotional state. This enables prompt and accurate support while taking the user's emotions into consideration when an alarm occurs, improving work efficiency and quality and reducing user stress.

[0556] "Alarm information" is a message indicating an abnormality or warning that occurs during base station construction work.

[0557] The "means for inputting" is an interface that allows a user to input alarm information into the system using a smartphone or other terminal.

[0558] A "terminal" is a device for acquiring and transmitting alarm information and user emotion data, and includes smartphones, tablets, etc.

[0559] An "emotion recognition engine" is software or an algorithm that analyzes emotions from user input, facial expressions, voice, etc.

[0560] The JSON format is a text-based data exchange format that structures data and facilitates communication between systems.

[0561] A "server" is a computer system that receives alarm information and emotion data, analyzes them, and generates responses.

[0562] An "analysis queue" is a data structure for processing alarm information awaiting analysis in order.

[0563] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze alarm information and generate appropriate responses or corrective measures.

[0564] "Translation" is the process of converting the analysis results from the original text into another language (for example, Japanese).

[0565] "Corrective measures" refer to specific procedures and measures to resolve problems based on alarm information.

[0566] The "means for adjusting the response message" is a process for changing the tone and content of the response message based on the user's emotional state.

[0567] "LINE message format" refers to the message format used in the LINE application.

[0568] The present invention provides a system for improving the efficiency of alarm responses during base station construction work, and is particularly equipped with a function for recognizing a user's emotions and optimizing responses. Specific embodiments will be described below.

[0569] Hardware and software used

[0570] The hardware used includes devices such as smartphones and tablets, as well as servers equipped with high-performance CPUs and GPUs, while the software used includes the LINE messaging app, an emotion recognition engine (e.g., emotion recognition API), a generative AI model (e.g., language generation model), and a translation model (e.g., automatic translation API).

[0571] Explanation of program processing

[0572] Alarm Input Acquisition

[0573] The user inputs the English alarm information displayed on the radio as a LINE message on a smartphone or other device. The device then acquires the alarm information. At this time, the user opens the chat screen of the LINE app and inputs the English alarm message as text.

[0574] User Emotion Recognition

[0575] The device activates an emotion engine to recognize emotions from the user's input, facial expressions, and voice. The device uses data acquired from the smartphone's camera and microphone and executes emotion recognition algorithms. For example, the emotion engine detects if the user looks anxious or if their voice is trembling.

[0576] Alarm details transmission

[0577] The device converts the acquired alarm information and user emotion data into JSON format and sends it to the server as an HTTP request. The server receives this request. Specifically, the device sends the data using the "POST" method, and the server parses the data using a function such as "JSON.parse()".

[0578] Alarm Analysis

[0579] The server adds the received alarm information to the analysis queue, then calls the generative AI model to begin analysis. The server then removes the alarm information from the queue and passes it to the AI ​​model as input data. When the generative AI model analyzes the input "Power supply error detected," it finds abnormal patterns from past data.

[0580] Alarm translation and correction method suggestions

[0581] The server calls up the translation model and translates the alarm information into Japanese. It then refers to the past database and knowledge base to search for the appropriate corrective action. For example, the corrective action for a "Power supply error" might be to "Check the power supply connection status."

[0582] Emotion-Based Response Modulation

[0583] The server adjusts the tone and content of the response message based on the user's emotional state. For example, if the user is feeling anxious, the server uses more reassuring and polite language. The server generates a message like, "Don't worry. Stay calm and check the steps."

[0584] Send results

[0585] The server sends the translation results, correction methods, and responses adjusted based on emotions to the device. The server sends the data as an HTTP response, which the device receives. The device then converts the received data into LINE message format.

[0586] Result confirmation and processing

[0587] The device displays the translation result and correction methods on the LINE message screen along with the adjusted response. The user can review and understand the content. The device may also record the message display timestamp and the user's reaction data.

[0588] Implementing specific correction work

[0589] The user follows the suggested corrective action and performs the necessary corrective action, such as reconnecting the power or checking the cables. The user follows the detailed steps, including arrows and diagrams.

[0590] Examples of concrete examples and prompts

[0591] For example, if a user inputs the alarm "Power supply error detected. Please check the power connection" into the LINE app and unconsciously shows signs of restlessness, the emotion engine will recognize this as anxiety. The server will receive this and generate a response such as "A power supply error has been detected. Please stay calm and check the power connection and reconnect if necessary," and send it as a LINE message.

[0592] An example prompt is:

[0593] "Please enter the alarm displayed on your radio. Also, briefly describe the emotions you felt as you typed."

[0594] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0595] Step 1:

[0596] The user inputs the English alarm information displayed on the radio as a LINE message on a smartphone or other device. The input alarm information is then acquired by the device. Specifically, the user opens the LINE app and inputs alarm information such as "Power supply error detected. Please check the power connection" into the chat screen. The input data is saved in text format in the device's memory.

[0597] Step 2:

[0598] The device launches an emotion recognition engine to recognize emotions from the user's input, facial expressions, voice, etc. Input data includes the user's input text, camera footage, and voice. The emotion recognition engine analyzes this data and detects the emotion the user is feeling (e.g., anxiety, impatience). The output data is generated in JSON format, listing the type of emotion recognized and its intensity.

[0599] Step 3:

[0600] The device converts the acquired alarm information and user emotion data into JSON format and sends it to the server as an HTTP request. Specifically, the device combines the alarm information and emotion data into a single JSON object and sends it to the server using a "POST" request. The input data is the alarm information and emotion data, and the output data is a status indicating that the transmission was successful.

[0601] Step 4:

[0602] The server adds the received alarm information to the analysis queue and calls the generative AI model to begin analysis. The input data includes the JSON object sent from the client. Specifically, the server adds this data to the analysis queue and passes it to the generative AI model in the appropriate order. The generative AI model understands the content of the alarm from the alarm statement and generates specific countermeasures. The output data is the type of alarm and the corresponding countermeasures.

[0603] Step 5:

[0604] The server calls the translation model and translates the alarm information into Japanese. The input data includes the alarm text from the analysis results. Specifically, the server calls the translation API and translates from English to Japanese. The output data is the translated Japanese alarm text.

[0605] Step 6:

[0606] The server references historical databases and knowledge bases to search for appropriate corrective measures based on the analysis results. Input data includes alarm information translated into Japanese and analysis results. Specifically, the server executes a database query to retrieve relevant corrective measures. The output data is detailed instructions for the corrective measures.

[0607] Step 7:

[0608] The server adjusts the tone and content of the response message based on the user's emotional state. The input data includes the user's emotional data and corrective action instructions. Specifically, the server analyzes the emotional data and generates an emotion-sensitive message, such as "Don't worry. Please stay calm and review the steps." The output data is the adjusted response message.

[0609] Step 8:

[0610] The server generates a translation result, provides corrective measures, and sends a response adjusted based on the emotion to the device. The input data includes the translated alarm information, corrective measures, and an adjusted response message. Specifically, the server compiles this information into a single JSON object and sends it to the device as an "HTTP response." The output data is a status indicating successful transmission.

[0611] Step 9:

[0612] The device displays the translation result and correction method on the LINE message screen along with an adjusted response. The input data includes a JSON object received from the server. Specifically, the device parses the JSON data, converts it into a LINE message format, and displays it to the user. The output is when the user checks it and understands the content.

[0613] Step 10:

[0614] The user follows the presented corrective measures and performs the necessary corrective work. The input data includes the corrective measures displayed in the LINE message. As specific actions, the user performs specific steps such as reconnecting the power and checking the cables. The output is that the work has been completed.

[0615] (Application example 2)

[0616] 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."

[0617] Conventional alarm response systems respond uniformly without considering the user's emotional state, which can delay appropriate responses and increase stress, especially when the user is feeling anxious or impatient. Furthermore, the translation of alarm information and the presentation of corrective measures are also uniform, making it difficult to provide individualized responses tailored to the user's situation. Furthermore, there was no way to recognize the user's emotions and optimize the response based on them. This resulted in problems with reduced accuracy and speed of responses.

[0618] 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 inputting alarm information, means for transmitting the input alarm information and emotion data to the server, means for analyzing the alarm information and emotion data and generating an analysis result, means for translating the analysis result and presenting a corrective measure, means for adjusting the presented corrective measure based on the emotion and transmitting it to the terminal, and means for recognizing the user's emotion. This enables individual responses that take the user's emotion into consideration, improving the accuracy and speed of alarm responses. It also makes it possible to reduce user stress and provide more effective support.

[0619] "Alarm information" refers to warning or error information issued by a system or device, which alerts the user to a specific problem or alerts the user to a particular problem.

[0620] "Emotion data" is data that indicates the emotional state of a user analyzed from facial expressions, voice, and text input.

[0621] A "server" is a central control unit that receives, analyzes, and processes data sent by users.

[0622] The "analysis result" is the result information obtained by the server analyzing the alarm information and emotion data.

[0623] "Corrective measures" indicate specific procedures and methods for dealing with alarm information.

[0624] "Translation" refers to the process of converting analysis results and corrective measures into a language that is easy for users to understand.

[0625] A "terminal" is a connected device used by a user, such as a smartphone or smart glasses.

[0626] "Means for recognizing emotions" refers to technology that identifies emotions from a user's facial expressions, voice, and text input.

[0627] "Adjustment" refers to the process of optimizing the corrective measures and response content based on the user's emotional data.

[0628] A specific example of the present invention is a system called "Security Emotion Manager," the details of which are given below.

[0629] First, a user inputs alarm information from a security system using a smartphone or smart glasses. This alarm information is input by the user, and the specific content of the alarm is obtained in text format.

[0630] The device then uses its built-in camera and microphone to recognize the user's emotional state. It then uses DeepFace facial recognition software and other voice emotion recognition engines to extract emotional data from the user's facial expressions and voice. This emotional data is then sent to the server along with the alarm information. The device then converts this data into JSON format and sends it as an HTTP request.

[0631] The server analyzes the received alarm information and emotion data and generates an analysis result. It uses natural language processing technology to understand the content of the alarm information. Furthermore, it supplements the analysis result with a generative AI model and suggests the optimal corrective measures by referencing past databases and knowledge bases.

[0632] Once the analysis and corrective measures are ready, the server can adjust this information based on the user's emotions—for example, by providing more polite and specific instructions if the user is feeling anxious—using a generative AI model.

[0633] Finally, the adjusted instructions and corrective measures are sent to the terminal and displayed on the user's device, allowing the user to review them and take specific corrective actions, enabling the user to respond appropriately and promptly.

[0634] As a concrete example, consider a case where a user inputs alarm text information such as "Unauthorized access detected. Please verify the security status." and provides an image path as "user_image.jpg" and an audio path as "user_voice.wav." The server generates an optimal corrective action based on this information and provides a response tailored to the user's emotions. For example, if the user expresses impatience, a specific instruction such as "Unauthorized access detected. Please remain calm. Please verify the security status." is returned.

[0635] The system recognizes the user's emotions and takes them into consideration when providing assistance, improving the accuracy and speed of responses and reducing user stress. It also utilizes cutting-edge technologies such as DeepFace and generative AI models to improve the overall user experience.

[0636] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0637] Step 1:

[0638] A user inputs alarm information from a security system using a smartphone or smart glasses. For example, the user inputs text such as "Unauthorized access detected. Please verify the security status." and sends it to an application on the device. The input of this procedure is the alarm information in text format, and the output is the alarm information received by the device.

[0639] Step 2:

[0640] The device recognizes the user's emotions. The device's built-in camera takes a photo of the user's face and a microphone records their voice. Then, using facial recognition software "DeepFace" and a voice emotion recognition engine, these data are analyzed to extract emotional data. The input for this procedure is the user's facial image and voice data, and the output is emotional data that indicates the user's emotional state.

[0641] Step 3:

[0642] The alarm information and emotion data acquired by the device are converted into JSON format and sent to the server as an HTTP request. The input for this data transmission is the alarm information and emotion data, and the output is a transmission completion notification to the server.

[0643] Step 4:

[0644] The server analyzes the received alarm information and emotional data. First, it uses natural language processing technology to analyze the alarm information and understand its content. Next, it uses a generative AI model to supplement the analysis results and perform a deeper analysis of the meaning and impact of the alarm information. The input to this process is the alarm information and emotional data received by the server, and the output is the analysis results.

[0645] Step 5:

[0646] Based on the analysis results, the server searches for corrective measures by referring to a past database or knowledge base. For example, it refers to how similar alarms have been handled in the past and proposes the optimal corrective measures. The input to this procedure is the analysis results, and the output is the corrective measures.

[0647] Step 6:

[0648] The server adjusts the corrective measures and response messages based on the user's emotional data. For example, if the user feels anxious, the server adjusts the response messages to include polite and specific instructions. The inputs to this procedure are the corrective measures and the user's emotional data, and the output is the adjusted response message.

[0649] Step 7:

[0650] The server sends the adjusted response message and the correction method to the terminal. The input of this data transmission is the adjusted response message and the correction method, and the output is a transmission completion notification to the terminal.

[0651] Step 8:

[0652] The terminal displays the received response message and corrective action to the user. The user confirms it and performs specific corrective action. The input of this procedure is the message and corrective action received by the terminal, and the output is the specific operation or response by the user.

[0653] This allows the user to deal with the alarm quickly and appropriately, and receive emotional support.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] [Third embodiment]

[0658] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0659] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0660] 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).

[0661] 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.

[0662] 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.

[0663] 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).

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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."

[0670] The present invention provides a system for improving the efficiency of alarm response during base station construction work. Specific embodiments for carrying out the present invention will be described below.

[0671] 1. Alarm input acquisition

[0672] The user inputs the English alarm message displayed on the radio into the LINE message screen using a smartphone or other device, and the alarm information is then acquired by the device.

[0673] 2. Alarm details transmission

[0674] The alarm information acquired by the device is sent to the server. Specifically, the input alarm information is converted into JSON format and sent to the server as an HTTP request. The server receives this request and prepares for analysis.

[0675] 3. Alarm Analysis

[0676] The server adds the received alarm information to an analysis queue. It then calls the generative AI model, which extracts the alarm information from the queue and begins analysis. The generative AI model uses natural language processing technology to analyze the meaning of the alarm information and identify causes and countermeasures.

[0677] 4. Alarm translation and correction method provided

[0678] Once the server receives the analysis results, it calls up a translation model to translate the alarm information into Japanese. Once translation is complete, it references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will present corrective measures, including steps to check the power supply connection status.

[0679] 5. Send results

[0680] The server sends the translation results and correction instructions to the device. The sent content is received by the device as an HTTP response and converted into a LINE message format.

[0681] 6. Results confirmation and processing

[0682] The device will display the translation results and corrective measures on the LINE message screen. The user can check this and take the necessary corrective measures as instructed. For example, if the message "A power error has been detected. Please check the power connection" is displayed, the user should check the power connection to the BBU (baseband unit) and reconnect it.

[0683] As a concrete example, consider the following scenario: A user inputs an alarm saying, "Power supply error detected. Please check the power connection." The device sends this alarm information to a server, which analyzes it using a generative AI model. The analysis results are translated into Japanese and displayed as, "A power supply error has been detected. Please check the power connection." Furthermore, the server refers to a database and presents a specific corrective measure: "Check the BBU's power connection and reconnect if necessary." Ultimately, the user follows this procedure and takes the appropriate action, quickly resolving the problem.

[0684] This system will enable even engineers without specialized knowledge to respond quickly and accurately when an alarm occurs, which is expected to improve work efficiency and quality.

[0685] The processing flow will be explained below.

[0686] Step 1:

[0687] The user enters the English alarm message displayed on the radio into the LINE message screen. The device receives this input and prepares for the next process.

[0688] Step 2:

[0689] The device converts the input alarm message into JSON format and sends it as an HTTP request to the server, which receives the request.

[0690] Step 3:

[0691] The server adds the received alarm message to the analysis queue, then invokes the generative AI model to take the alarm message from the queue and start analyzing it.

[0692] Step 4:

[0693] The generative AI model uses natural language processing technology to semantically analyze the alarm message, specifically analyzing the structure and content of the message to identify the type and cause of the error.

[0694] Step 5:

[0695] The server receives the analysis results and calls the appropriate translation model based on the results. The translation model translates the English alarm content into Japanese.

[0696] Step 6:

[0697] The server compares the translated analysis results with historical and knowledge bases to find the appropriate corrective action, for example, if a power error is detected, it may include steps to check the power connection.

[0698] Step 7:

[0699] The server combines the translation results with specific corrective actions to generate a response message, which is presented to the user in a format that is easy to understand.

[0700] Step 8:

[0701] The server generates a response message and sends it to the device as an HTTP response. The device receives this response and converts it into a LINE message format based on the analysis and translation results.

[0702] Step 9:

[0703] The device displays the translation result and correction instructions on the LINE message screen, and the user can check the message and understand the content.

[0704] Step 10:

[0705] The user follows the suggested corrective measures and takes the necessary corrective action, for example, by performing specific steps such as reconnecting the power or checking the cables.

[0706] This processing step enables a quick and accurate response when an alarm occurs, improving the efficiency and quality of work.

[0707] Example 1

[0708] 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."

[0709] Responding to alarms during base station construction work requires a high level of specialized knowledge, making it difficult to respond quickly. Furthermore, the lack of a way to effectively utilize case studies from other sites and past data makes it difficult to solve problems efficiently. A system that can resolve this situation and enable even non-experts to respond quickly and accurately is needed.

[0710] 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.

[0711] In this invention, the server includes a means for adding alarm information to an analysis queue, a means for analyzing the alarm information using a generative AI model to generate an analysis result, and a means for translating the analysis result and presenting a corrective measure. This allows even non-experts to respond to alarms quickly and accurately. Furthermore, by utilizing a past database and knowledge base, it is possible to efficiently present appropriate corrective measures.

[0712] "Alarm information" refers to warnings and error messages that are generated by radios and other equipment during base station construction work.

[0713] A "terminal" is a device, such as a smartphone or tablet, that a user uses to input and display alarm information.

[0714] "JSON format" is an abbreviation for JavaScript Object Notation, and is a data format for sending alarm information to a server.

[0715] "Server" refers to a computer system that receives alarm information, analyzes, translates, and suggests corrective measures.

[0716] The "analysis queue" is a data queue that stores alarm information received within the server and analyzes it sequentially.

[0717] A "generative AI model" is an artificial intelligence model used to analyze alarm information and understand its meaning.

[0718] "Natural language processing technology" is a technology used by generative AI models to analyze the text of alarm information and understand its meaning.

[0719] A "translation model" is an artificial intelligence model used to translate analysis results into a language that the user can understand.

[0720] "Corrective measures" are specific steps and measures for resolving alarm problems that the server presents based on the analysis results and past databases and knowledge bases.

[0721] "LINE message format" refers to the format of a message application that a device uses to notify a user of alarm analysis results and corrective measures.

[0722] A "database" is a system that maintains records of past alarm information and corrective measures.

[0723] A "knowledge base" is an information aggregation system that accumulates expert knowledge and past experience.

[0724] The present invention is a system for improving the efficiency of alarm response during base station construction work. The program processing procedure of this system is described in detail below.

[0725] Alarm Input Acquisition

[0726] The user inputs the English alarm message displayed on the radio into the LINE message screen on a smartphone, tablet, or other device. This causes the alarm information to be acquired by the device. For example, the user can input the alarm message "Power supply error detected. Please check the power connection." into their device.

[0727] Alarm details transmission

[0728] The device converts the acquired alarm information into JSON format. The converted alarm information is sent to the server as an HTTP POST request. For example, the device sends data to the server in the format "{"alarm_message": "Power supply error detected. Please check the power connection."}". The server receives this request and prepares it for analysis.

[0729] Alarm Analysis

[0730] The server adds the received alarm information to the analysis queue. It then calls the generative AI model, which retrieves the alarm information from the analysis queue and begins analysis. The generative AI model uses natural language processing technology to analyze the meaning of the alarm information and identify the cause and countermeasures. For example, the generative AI model understands the meaning of "Power supply error detected. Please check the power connection." and realizes that it is a power-related problem.

[0731] Alarm translation and correction method suggestions

[0732] Once the server obtains the analysis results, it calls the translation model to translate the alarm information into Japanese. For example, the server translates "Power supply error detected. Please check the power connection." into "A power supply error has been detected. Please check the power connection." It then references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will suggest the corrective measure, "Check the BBU's power connection and reconnect if necessary."

[0733] Send results

[0734] The server sends the generated translation result and corrective measures to the device. The sent content is received by the device as an HTTP response, which the device converts into a LINE message format. For example, the response from the server is sent in the following format: {"translated_message": "A power supply error has been detected. Please check the power connection.", "corrective_action": "Check the BBU power connection and reconnect if necessary."}.

[0735] Result confirmation and processing

[0736] The device will display the translation results and corrective measures on the LINE message screen. The user will check this message and follow the instructions to take the necessary corrective measures. For example, if the message "A power error has been detected. Please check the power connection," is displayed, the user should check the power connection to the BBU (baseband unit) and reconnect it.

[0737] Specific examples

[0738] As a concrete example, consider the case where a user inputs an alarm saying, "Power supply error detected. Please check the power connection." The device sends this alarm information to the server, which analyzes it using a generative AI model. The analysis results are translated into Japanese and displayed as, "A power supply error has been detected. Please check the power connection." Furthermore, by referencing the database, the server presents a specific corrective measure: "Check the BBU power connection and reconnect if necessary." Ultimately, the problem is resolved quickly when the user follows this procedure and takes the appropriate action.

[0739] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0740] Step 1:

[0741] Alarm Input Acquisition

[0742] The alarm information is acquired by the user by entering the alarm message displayed on the radio into the LINE message screen of their smartphone or tablet. Specifically, the user enters the alarm message "Power supply error detected. Please check the power connection." The entered alarm information is saved in the device's internal memory.

[0743] Input: Alarm message displayed on the radio

[0744] Output: Alarm information entered on the LINE message screen

[0745] Step 2:

[0746] Alarm details transmission

[0747] The alarm information acquired by the device is converted into JSON format and sent to the server. When converting the message, it is converted into a JSON format such as "{"alarm_message": "Power supply error detected. Please check the power connection."}". The converted alarm information is sent as an HTTP POST request. The server receives this request and saves the log in a database.

[0748] Input: Alarm information entered on the LINE message screen

[0749] Output: Alarm information in JSON format sent to the server as an HTTP POST request

[0750] Step 3:

[0751] Alarm Analysis

[0752] The server adds the received alarm information to an analysis queue. The generative AI model extracts the alarm information from the queue and analyzes it using natural language processing techniques. Specifically, it understands the alarm information through processes such as tokenization, semantic analysis, and context understanding. For example, it understands that the message "Power supply error detected. Please check the power connection" is a power-related problem.

[0753] Input: Alarm information in JSON format sent to the server

[0754] Output: Analysis results from the generative AI model

[0755] Step 4:

[0756] Alarm translation and correction method suggestions

[0757] The server obtains the analysis results obtained from the generative AI model and calls the translation model to translate the alarm information into Japanese. For example, it translates "Power supply error detected. Please check the power connection." into "A power supply error has been detected. Please check the power connection." The server then refers to its past database and knowledge base to search for an appropriate corrective measure. For example, it identifies the corrective measure as "Check the power connection of the BBU and reconnect if necessary."

[0758] Input: Analysis results from generative AI model

[0759] Output: Japanese translation by translation model and correction method

[0760] Step 5:

[0761] Send results

[0762] The server generates an HTTP response that sends the translation result and corrective actions to the device. The response is received by the device and converted into a LINE message format. For example, the following format is sent to the device: {"translated_message": "A power supply error has been detected. Please check the power connection.", "corrective_action": "Check the BBU power connection and reconnect if necessary."}.

[0763] Input: Japanese translation by translation model and correction method

[0764] Output: Translation results converted into LINE message format and correction methods

[0765] Step 6:

[0766] Result confirmation and processing

[0767] The device displays the translation result and corrective measures on the LINE message screen. The user can check the result and follow the instructions to take the necessary corrective measures. For example, if a user sees the message "A power supply error has been detected. Please check the power supply connection," they can check the power supply connection of the BBU and reconnect it if necessary.

[0768] Input: Translation results converted to LINE message format and correction methods

[0769] Output: User takes corrective action

[0770] (Application example 1)

[0771] 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."

[0772] One challenge is the difficulty of quickly and accurately analyzing alarm information generated by robots in factories and presenting appropriate corrective measures. In particular, when non-expert engineers respond to alarms, it can be difficult to quickly find appropriate countermeasures, which can reduce work efficiency and delay problem resolution.

[0773] 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.

[0774] In this invention, the server includes means for inputting alarm information, means for transmitting the input alarm information to the server, means for analyzing the alarm information and generating an analysis result, means for translating the analysis result and presenting a corrective procedure, means for transmitting the presented corrective procedure to a terminal, and means for displaying the corrective procedure via a smart device based on the alarm information, thereby enabling a prompt and accurate response to alarms issued by robots in a factory.

[0775] "Alarm information" is information about errors and warning messages generated by robots in the factory.

[0776] "Input means" refers to a means for inputting alarm information using a smart device or terminal.

[0777] The "transmission means" is a means for transmitting input alarm information to the server.

[0778] The "analysis means" is a means by which the server analyzes alarm information and generates an analysis result.

[0779] The "translation means" is a means for translating the generated analysis results and presenting corrective measures.

[0780] The "presentation means" is a means for transmitting the translated analysis results and corrective measures to the terminal.

[0781] The "means for displaying via a smart device" refers to a means for displaying corrective procedures on a smart device based on alarm information.

[0782] "Corrective measures" are specific procedures or measures to resolve a problem that are identified based on alarm information.

[0783] This invention is a system for quickly and accurately managing alarm information generated by robots in factories and suggesting appropriate corrective measures. Specifically, it implements a series of processes: inputting and transmitting alarm information, analyzing it, translating it, and suggesting corrective measures.

[0784] First, to input alarm information, a smart device (e.g., smart glasses or a smartphone) is used. The user inputs alarm information into the terminal using this smart device. For example, if the robot issues an "emergency stop error" alarm, the user can voice-input "Emergency stop error detected. Please check the emergency stop button." into the smart glasses.

[0785] Next, the terminal converts the input alarm information into JSON format and sends it as an HTTP request to the server, which receives the request and adds the alarm information to the analysis queue.

[0786] The server uses the generative AI model to analyze the alarm information. It uses natural language processing technology to analyze the content of the alarm information and identify the cause and countermeasures. For example, in the case of the alarm information "Emergency stop error detected," the generative AI model determines that the status of the emergency stop button needs to be checked.

[0787] The analysis results are translated into Japanese, and the server refers to a past database and knowledge base to search for appropriate corrective measures. For example, a corrective measure such as "Check the emergency stop button" is presented.

[0788] The server sends the translation results and correction instructions to the device, which receives them, converts them into a LINE message format, and displays them to the user. The user can then check the correction instructions on their smart device and take action according to the instructions.

[0789] For example, if the message "A power error has been detected. Please check the power connection" appears, the user can quickly resolve the issue by checking the robot's power connection and reconnecting it if necessary.

[0790] An example of a prompt is as follows:

[0791] Smart glasses display: "Please speak alarm information:"

[0792] User speaks: "Emergency stop error detected. Please check the emergency stop button."

[0793] This system will enable even engineers without specialized knowledge to respond to alarms quickly and accurately, and is expected to improve work efficiency and quality within the factory.

[0794] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0795] Step 1:

[0796] A user inputs alarm information using a smart device. For example, the user inputs alarm information by voice using smart glasses. The input is converted into text and stored in the terminal as text alarm information.

[0797] Input: Alarm information (audio)

[0798] Output: Alarm information (text format)

[0799] Step 2:

[0800] The device converts the input alarm information into JSON format and sends it as an HTTP request to the server. The server receives this request and adds the alarm information to a queue.

[0801] Input: Alarm information (text format)

[0802] Output: Alarm information (JSON format)

[0803] Step 3:

[0804] The server calls the generative AI model, retrieves the alarm information from the queue, and begins analysis. The generative AI model uses natural language processing technology to analyze the content of the alarm information and identify the cause and countermeasures.

[0805] Input: Alarm information (JSON format)

[0806] Data processing: Analysis using natural language processing technology

[0807] Output: Analysis results (text format)

[0808] Step 4:

[0809] The server retrieves the analysis results and translates them into Japanese using a translation model. It then searches for appropriate corrective measures by referencing past databases and knowledge bases, and identifies specific corrective steps.

[0810] Input: Analysis results (text format)

[0811] Data processing: Translation and database reference to find corrective procedures

[0812] Output: Translation results and correction methods (text format)

[0813] Step 5:

[0814] The server then sends the translated analysis results and corrective measures to the device, which then receives them, converts them into LINE message format, and displays them to the user.

[0815] Input: Translation results and correction methods (text format)

[0816] Data processing: conversion to message format

[0817] Output: LINE message

[0818] Step 6:

[0819] The user checks the translation results and corrective measures displayed in the LINE message and follows the instructions to respond to the alarm. For example, if the message says "Please check the emergency stop button," the user should actually check the emergency stop button and take the necessary steps.

[0820] Input: LINE message (displayed corrective action)

[0821] Output: Physical alarm response WeChat, for example, button confirmation and appropriate operation

[0822] 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.

[0823] The present invention is a system for improving the efficiency of alarm responses during base station construction work, and is equipped with a function that recognizes the user's emotions and optimizes the response. Below, we will explain in detail how the system can be combined with an emotion engine.

[0824] 1. Alarm input acquisition

[0825] The user inputs the English alarm message displayed on the radio into the LINE message screen using a smartphone or other device, and the alarm information is then acquired by the device.

[0826] 2. User Emotion Recognition

[0827] The device activates an emotion engine that recognizes emotions from the user's input, facial expressions, voice, etc. For example, it analyzes whether the user is feeling anxious or impatient when inputting.

[0828] 3. Alarm details transmission

[0829] The alarm information and user emotion data acquired by the device are sent to the server. Specifically, this information is converted into JSON format and sent to the server as an HTTP request. The server receives this request.

[0830] 4. Alarm Analysis

[0831] The server adds the received alarm information to the analysis queue. Then, it calls the generative AI model, which extracts the alarm information from the queue and begins analyzing it. By analyzing the information while also referring to emotional data, it fine-tunes the response to the user.

[0832] 5. Alarm translation and correction method provided

[0833] Once the server receives the analysis results, it calls up a translation model to translate the alarm information into Japanese. Once translation is complete, it references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will present corrective measures, including steps to check the power supply connection status.

[0834] 6. Emotion-Based Response Modulation

[0835] The server adjusts the tone and content of the response message based on the user's emotional state, for example providing more polite and detailed instructions if the user is impatient.

[0836] 7. Send results

[0837] The server generates a translation result, provides corrections, and sends a response adjusted based on the emotion to the device. The content is received by the device as an HTTP response and converted into a LINE message format.

[0838] 8. Results confirmation and processing

[0839] The device will display the translation results and correction methods on the LINE message screen along with the adjusted response. The user can review and understand the content. If necessary, additional support and help will be provided.

[0840] 9. Implementation of specific correction work

[0841] The user follows the suggested corrective measures and takes the necessary corrective action, for example, by performing specific steps such as reconnecting the power or checking the cables.

[0842] As a concrete example, consider the following scenario: If a user inputs an alarm saying "Power supply error detected. Please check the power connection." and the emotion engine recognizes that the user is feeling anxious, the server will generate a response such as "A power supply error has been detected. Please do not worry. Please stay calm and check the power connection and reconnect if necessary." In this way, instructions that take the user's emotions into consideration can be provided, enabling faster and more accurate responses.

[0843] This system not only enables a quick and accurate response when an alarm occurs, but also provides support that takes the user's emotions into consideration, thereby improving work efficiency and quality and helping to reduce user stress.

[0844] The processing flow will be explained below.

[0845] Step 1:

[0846] The user types the English alarm message displayed on the radio into the LINE message screen. The device receives this message.

[0847] Step 2:

[0848] As soon as the device receives the user's input, it starts the emotion engine, which analyzes the user's facial expressions and voice tone to recognize the user's emotional state.

[0849] Step 3:

[0850] The alarm information and recognized emotion data acquired by the device are converted into JSON format and sent as an HTTP request to the server, which receives the request.

[0851] Step 4:

[0852] The server adds the received alarm information to the analysis queue. Then it calls the generative AI model, which retrieves the alarm information from the queue and begins analysis. In parallel, it also references emotion data and adjusts the analysis results.

[0853] Step 5:

[0854] The generative AI model uses natural language processing technology to perform semantic analysis of the alarm message, specifically analyzing the content of the error message and identifying its type and cause.

[0855] Step 6:

[0856] The server retrieves the analysis results, calls up a translation model, and translates the alarm information into Japanese. Based on the translated content, it references past databases and knowledge bases to search for appropriate corrective measures.

[0857] Step 7:

[0858] The server combines the translation results with the correction methods and adjusts the response message based on the emotional data provided by the emotion engine. For example, if the user is feeling anxious, the response message will be changed to a calming tone.

[0859] Step 8:

[0860] The server sends the adjusted response message to the device as an HTTP response. The device receives this response and converts it into a LINE message format.

[0861] Step 9:

[0862] The device displays the translation results and corrections on the LINE message screen, and the displayed content is tailored to the user's emotional state.

[0863] Step 10:

[0864] The user takes appropriate corrective action according to the suggested corrective measures. For example, if the user checks the power connection status and tries to reconnect it, a message will be displayed stating, "A power error has been detected. Please stay calm and check the power connection and reconnect if necessary."

[0865] These specific processing steps enable a quick and accurate response when an alarm occurs, and since the user's emotions are taken into consideration, stress is reduced and work efficiency is improved. In addition, the emotion recognition function provides support so that the user can continue working with peace of mind.

[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] Alarm responses during base station construction work require rapid and accurate responses, but user stress and frustration can reduce work efficiency. Alarm information is often displayed in different languages, often resulting in delays in translation and presentation of corrective measures. Conventional systems lack optimal support that combines emotion recognition and natural language processing, increasing the burden on users and resulting in reduced work quality. Therefore, a system that optimizes responses based on user emotions and provides rapid and accurate responses is needed.

[0869] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0870] In this invention, the server includes means for adding alarm information to an analysis queue and calling a generative AI model for analysis, means for translating the analysis results and presenting corrective measures, and means for adjusting a response message based on the user's emotional state. This enables prompt and accurate support while taking the user's emotions into consideration when an alarm occurs, improving work efficiency and quality and reducing user stress.

[0871] "Alarm information" is a message indicating an abnormality or warning that occurs during base station construction work.

[0872] The "means for inputting" is an interface that allows a user to input alarm information into the system using a smartphone or other terminal.

[0873] A "terminal" is a device for acquiring and transmitting alarm information and user emotion data, and includes smartphones, tablets, etc.

[0874] An "emotion recognition engine" is software or an algorithm that analyzes emotions from user input, facial expressions, voice, etc.

[0875] The JSON format is a text-based data exchange format that structures data and facilitates communication between systems.

[0876] A "server" is a computer system that receives alarm information and emotion data, analyzes them, and generates responses.

[0877] An "analysis queue" is a data structure for processing alarm information awaiting analysis in order.

[0878] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze alarm information and generate appropriate responses or corrective measures.

[0879] "Translation" is the process of converting the analysis results from the original text into another language (for example, Japanese).

[0880] "Corrective measures" refer to specific procedures and measures to resolve problems based on alarm information.

[0881] The "means for adjusting the response message" is a process for changing the tone and content of the response message based on the user's emotional state.

[0882] "LINE message format" refers to the message format used in the LINE application.

[0883] The present invention provides a system for improving the efficiency of alarm responses during base station construction work, and is particularly equipped with a function for recognizing a user's emotions and optimizing responses. Specific embodiments will be described below.

[0884] Hardware and software used

[0885] The hardware used includes devices such as smartphones and tablets, as well as servers equipped with high-performance CPUs and GPUs, while the software used includes the LINE messaging app, an emotion recognition engine (e.g., emotion recognition API), a generative AI model (e.g., language generation model), and a translation model (e.g., automatic translation API).

[0886] Explanation of program processing

[0887] Alarm Input Acquisition

[0888] The user inputs the English alarm information displayed on the radio as a LINE message on a smartphone or other device. The device then acquires the alarm information. At this time, the user opens the chat screen of the LINE app and inputs the English alarm message as text.

[0889] User Emotion Recognition

[0890] The device activates an emotion engine to recognize emotions from the user's input, facial expressions, and voice. The device uses data acquired from the smartphone's camera and microphone and executes emotion recognition algorithms. For example, the emotion engine detects if the user looks anxious or if their voice is trembling.

[0891] Alarm details transmission

[0892] The device converts the acquired alarm information and user emotion data into JSON format and sends it to the server as an HTTP request. The server receives this request. Specifically, the device sends the data using the "POST" method, and the server parses the data using a function such as "JSON.parse()".

[0893] Alarm Analysis

[0894] The server adds the received alarm information to the analysis queue, then calls the generative AI model to begin analysis. The server then removes the alarm information from the queue and passes it to the AI ​​model as input data. When the generative AI model analyzes the input "Power supply error detected," it finds abnormal patterns from past data.

[0895] Alarm translation and correction method suggestions

[0896] The server calls up the translation model and translates the alarm information into Japanese. It then refers to the past database and knowledge base to search for the appropriate corrective action. For example, the corrective action for a "Power supply error" might be to "Check the power supply connection status."

[0897] Emotion-Based Response Modulation

[0898] The server adjusts the tone and content of the response message based on the user's emotional state. For example, if the user is feeling anxious, the server uses more reassuring and polite language. The server generates a message like, "Don't worry. Stay calm and check the steps."

[0899] Send results

[0900] The server sends the translation results, correction methods, and responses adjusted based on emotions to the device. The server sends the data as an HTTP response, which the device receives. The device then converts the received data into LINE message format.

[0901] Result confirmation and processing

[0902] The device displays the translation result and correction methods on the LINE message screen along with the adjusted response. The user can review and understand the content. The device may also record the message display timestamp and the user's reaction data.

[0903] Implementing specific correction work

[0904] The user follows the suggested corrective action and performs the necessary corrective action, such as reconnecting the power or checking the cables. The user follows the detailed steps, including arrows and diagrams.

[0905] Examples of concrete examples and prompts

[0906] For example, if a user inputs the alarm "Power supply error detected. Please check the power connection" into the LINE app and unconsciously shows signs of restlessness, the emotion engine will recognize this as anxiety. The server will receive this and generate a response such as "A power supply error has been detected. Please stay calm and check the power connection and reconnect if necessary," and send it as a LINE message.

[0907] An example prompt is:

[0908] "Please enter the alarm displayed on your radio. Also, briefly describe the emotions you felt as you typed."

[0909] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0910] Step 1:

[0911] The user inputs the English alarm information displayed on the radio as a LINE message on a smartphone or other device. The input alarm information is then acquired by the device. Specifically, the user opens the LINE app and inputs alarm information such as "Power supply error detected. Please check the power connection" into the chat screen. The input data is saved in text format in the device's memory.

[0912] Step 2:

[0913] The device launches an emotion recognition engine to recognize emotions from the user's input, facial expressions, voice, etc. Input data includes the user's input text, camera footage, and voice. The emotion recognition engine analyzes this data and detects the emotion the user is feeling (e.g., anxiety, impatience). The output data is generated in JSON format, listing the type of emotion recognized and its intensity.

[0914] Step 3:

[0915] The device converts the acquired alarm information and user emotion data into JSON format and sends it to the server as an HTTP request. Specifically, the device combines the alarm information and emotion data into a single JSON object and sends it to the server using a "POST" request. The input data is the alarm information and emotion data, and the output data is a status indicating that the transmission was successful.

[0916] Step 4:

[0917] The server adds the received alarm information to the analysis queue and calls the generative AI model to begin analysis. The input data includes the JSON object sent from the client. Specifically, the server adds this data to the analysis queue and passes it to the generative AI model in the appropriate order. The generative AI model understands the content of the alarm from the alarm statement and generates specific countermeasures. The output data is the type of alarm and the corresponding countermeasures.

[0918] Step 5:

[0919] The server calls the translation model and translates the alarm information into Japanese. The input data includes the alarm text from the analysis results. Specifically, the server calls the translation API and translates from English to Japanese. The output data is the translated Japanese alarm text.

[0920] Step 6:

[0921] The server references historical databases and knowledge bases to search for appropriate corrective measures based on the analysis results. Input data includes alarm information translated into Japanese and analysis results. Specifically, the server executes a database query to retrieve relevant corrective measures. The output data is detailed instructions for the corrective measures.

[0922] Step 7:

[0923] The server adjusts the tone and content of the response message based on the user's emotional state. The input data includes the user's emotional data and corrective action instructions. Specifically, the server analyzes the emotional data and generates an emotion-sensitive message, such as "Don't worry. Please stay calm and review the steps." The output data is the adjusted response message.

[0924] Step 8:

[0925] The server generates a translation result, provides corrective measures, and sends a response adjusted based on the emotion to the device. The input data includes the translated alarm information, corrective measures, and an adjusted response message. Specifically, the server compiles this information into a single JSON object and sends it to the device as an "HTTP response." The output data is a status indicating successful transmission.

[0926] Step 9:

[0927] The device displays the translation result and correction method on the LINE message screen along with an adjusted response. The input data includes a JSON object received from the server. Specifically, the device parses the JSON data, converts it into a LINE message format, and displays it to the user. The output is when the user checks it and understands the content.

[0928] Step 10:

[0929] The user follows the presented corrective measures and performs the necessary corrective work. The input data includes the corrective measures displayed in the LINE message. As specific actions, the user performs specific steps such as reconnecting the power and checking the cables. The output is that the work has been completed.

[0930] (Application example 2)

[0931] 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."

[0932] Conventional alarm response systems respond uniformly without considering the user's emotional state, which can delay appropriate responses and increase stress, especially when the user is feeling anxious or impatient. Furthermore, the translation of alarm information and the presentation of corrective measures are also uniform, making it difficult to provide individualized responses tailored to the user's situation. Furthermore, there was no way to recognize the user's emotions and optimize the response based on them. This resulted in problems with reduced accuracy and speed of responses.

[0933] 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 inputting alarm information, means for transmitting the input alarm information and emotion data to the server, means for analyzing the alarm information and emotion data and generating an analysis result, means for translating the analysis result and presenting a corrective measure, means for adjusting the presented corrective measure based on the emotion and transmitting it to the terminal, and means for recognizing the user's emotion. This enables individual responses that take the user's emotion into consideration, improving the accuracy and speed of alarm responses. It also makes it possible to reduce user stress and provide more effective support.

[0934] "Alarm information" refers to warning or error information issued by a system or device, which alerts the user to a specific problem or alerts the user to a particular problem.

[0935] "Emotion data" is data that indicates the emotional state of a user analyzed from facial expressions, voice, and text input.

[0936] A "server" is a central control unit that receives, analyzes, and processes data sent by users.

[0937] The "analysis result" is the result information obtained by the server analyzing the alarm information and emotion data.

[0938] "Corrective measures" indicate specific procedures and methods for dealing with alarm information.

[0939] "Translation" refers to the process of converting analysis results and corrective measures into a language that is easy for users to understand.

[0940] A "terminal" is a connected device used by a user, such as a smartphone or smart glasses.

[0941] "Means for recognizing emotions" refers to technology that identifies emotions from a user's facial expressions, voice, and text input.

[0942] "Adjustment" refers to the process of optimizing the corrective measures and response content based on the user's emotional data.

[0943] A specific example of the present invention is a system called "Security Emotion Manager," the details of which are given below.

[0944] First, a user inputs alarm information from a security system using a smartphone or smart glasses. This alarm information is input by the user, and the specific content of the alarm is obtained in text format.

[0945] The device then uses its built-in camera and microphone to recognize the user's emotional state. It then uses DeepFace facial recognition software and other voice emotion recognition engines to extract emotional data from the user's facial expressions and voice. This emotional data is then sent to the server along with the alarm information. The device then converts this data into JSON format and sends it as an HTTP request.

[0946] The server analyzes the received alarm information and emotion data and generates an analysis result. It uses natural language processing technology to understand the content of the alarm information. Furthermore, it supplements the analysis result with a generative AI model and suggests the optimal corrective measures by referencing past databases and knowledge bases.

[0947] Once the analysis and corrective measures are ready, the server can adjust this information based on the user's emotions—for example, by providing more polite and specific instructions if the user is feeling anxious—using a generative AI model.

[0948] Finally, the adjusted instructions and corrective measures are sent to the terminal and displayed on the user's device, allowing the user to review them and take specific corrective actions, enabling the user to respond appropriately and promptly.

[0949] As a concrete example, consider a case where a user inputs alarm text information such as "Unauthorized access detected. Please verify the security status." and provides an image path as "user_image.jpg" and an audio path as "user_voice.wav." The server generates an optimal corrective action based on this information and provides a response tailored to the user's emotions. For example, if the user expresses impatience, a specific instruction such as "Unauthorized access detected. Please remain calm. Please verify the security status." is returned.

[0950] The system recognizes the user's emotions and takes them into consideration when providing assistance, improving the accuracy and speed of responses and reducing user stress. It also utilizes cutting-edge technologies such as DeepFace and generative AI models to improve the overall user experience.

[0951] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0952] Step 1:

[0953] A user inputs alarm information from a security system using a smartphone or smart glasses. For example, the user inputs text such as "Unauthorized access detected. Please verify the security status." and sends it to an application on the device. The input of this procedure is the alarm information in text format, and the output is the alarm information received by the device.

[0954] Step 2:

[0955] The device recognizes the user's emotions. The device's built-in camera takes a photo of the user's face and a microphone records their voice. Then, using facial recognition software "DeepFace" and a voice emotion recognition engine, these data are analyzed to extract emotional data. The input for this procedure is the user's facial image and voice data, and the output is emotional data that indicates the user's emotional state.

[0956] Step 3:

[0957] The alarm information and emotion data acquired by the device are converted into JSON format and sent to the server as an HTTP request. The input for this data transmission is the alarm information and emotion data, and the output is a transmission completion notification to the server.

[0958] Step 4:

[0959] The server analyzes the received alarm information and emotional data. First, it uses natural language processing technology to analyze the alarm information and understand its content. Next, it uses a generative AI model to supplement the analysis results and perform a deeper analysis of the meaning and impact of the alarm information. The input to this process is the alarm information and emotional data received by the server, and the output is the analysis results.

[0960] Step 5:

[0961] Based on the analysis results, the server searches for corrective measures by referring to a past database or knowledge base. For example, it refers to how similar alarms have been handled in the past and proposes the optimal corrective measures. The input to this procedure is the analysis results, and the output is the corrective measures.

[0962] Step 6:

[0963] The server adjusts the corrective measures and response messages based on the user's emotional data. For example, if the user feels anxious, the server adjusts the response messages to include polite and specific instructions. The inputs to this procedure are the corrective measures and the user's emotional data, and the output is the adjusted response message.

[0964] Step 7:

[0965] The server sends the adjusted response message and the correction method to the terminal. The input of this data transmission is the adjusted response message and the correction method, and the output is a transmission completion notification to the terminal.

[0966] Step 8:

[0967] The terminal displays the received response message and corrective action to the user. The user confirms it and performs specific corrective action. The input of this procedure is the message and corrective action received by the terminal, and the output is the specific operation or response by the user.

[0968] This allows the user to deal with the alarm quickly and appropriately, and receive emotional support.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] [Fourth embodiment]

[0973] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0974] 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.

[0975] 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).

[0976] 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.

[0977] 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.

[0978] 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).

[0979] 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.

[0980] 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.

[0981] 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.

[0982] 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.

[0983] 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.

[0984] 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.

[0985] 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."

[0986] The present invention provides a system for improving the efficiency of alarm response during base station construction work. Specific embodiments for carrying out the present invention will be described below.

[0987] 1. Alarm input acquisition

[0988] The user inputs the English alarm message displayed on the radio into the LINE message screen using a smartphone or other device, and the alarm information is then acquired by the device.

[0989] 2. Alarm details transmission

[0990] The alarm information acquired by the device is sent to the server. Specifically, the input alarm information is converted into JSON format and sent to the server as an HTTP request. The server receives this request and prepares for analysis.

[0991] 3. Alarm Analysis

[0992] The server adds the received alarm information to an analysis queue. It then calls the generative AI model, which extracts the alarm information from the queue and begins analysis. The generative AI model uses natural language processing technology to analyze the meaning of the alarm information and identify causes and countermeasures.

[0993] 4. Alarm translation and correction method provided

[0994] Once the server receives the analysis results, it calls up a translation model to translate the alarm information into Japanese. Once translation is complete, it references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will present corrective measures, including steps to check the power supply connection status.

[0995] 5. Send results

[0996] The server sends the translation results and correction instructions to the device. The sent content is received by the device as an HTTP response and converted into a LINE message format.

[0997] 6. Results confirmation and processing

[0998] The device will display the translation results and corrective measures on the LINE message screen. The user can check this and take the necessary corrective measures as instructed. For example, if the message "A power error has been detected. Please check the power connection" is displayed, the user should check the power connection to the BBU (baseband unit) and reconnect it.

[0999] As a concrete example, consider the following scenario: A user inputs an alarm saying, "Power supply error detected. Please check the power connection." The device sends this alarm information to a server, which analyzes it using a generative AI model. The analysis results are translated into Japanese and displayed as, "A power supply error has been detected. Please check the power connection." Furthermore, the server refers to a database and presents a specific corrective measure: "Check the BBU's power connection and reconnect if necessary." Ultimately, the user follows this procedure and takes the appropriate action, quickly resolving the problem.

[1000] This system will enable even engineers without specialized knowledge to respond quickly and accurately when an alarm occurs, which is expected to improve work efficiency and quality.

[1001] The processing flow will be explained below.

[1002] Step 1:

[1003] The user enters the English alarm message displayed on the radio into the LINE message screen. The device receives this input and prepares for the next process.

[1004] Step 2:

[1005] The device converts the input alarm message into JSON format and sends it as an HTTP request to the server, which receives the request.

[1006] Step 3:

[1007] The server adds the received alarm message to the analysis queue, then invokes the generative AI model to take the alarm message from the queue and start analyzing it.

[1008] Step 4:

[1009] The generative AI model uses natural language processing technology to semantically analyze the alarm message, specifically analyzing the structure and content of the message to identify the type and cause of the error.

[1010] Step 5:

[1011] The server receives the analysis results and calls the appropriate translation model based on the results. The translation model translates the English alarm content into Japanese.

[1012] Step 6:

[1013] The server compares the translated analysis results with historical and knowledge bases to find the appropriate corrective action, for example, if a power error is detected, it may include steps to check the power connection.

[1014] Step 7:

[1015] The server combines the translation results with specific corrective actions to generate a response message, which is presented to the user in a format that is easy to understand.

[1016] Step 8:

[1017] The server generates a response message and sends it to the device as an HTTP response. The device receives this response and converts it into a LINE message format based on the analysis and translation results.

[1018] Step 9:

[1019] The device displays the translation result and correction instructions on the LINE message screen, and the user can check the message and understand the content.

[1020] Step 10:

[1021] The user follows the suggested corrective measures and takes the necessary corrective action, for example, by performing specific steps such as reconnecting the power or checking the cables.

[1022] This processing step enables a quick and accurate response when an alarm occurs, improving the efficiency and quality of work.

[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] Responding to alarms during base station construction work requires a high level of specialized knowledge, making it difficult to respond quickly. Furthermore, the lack of a way to effectively utilize case studies from other sites and past data makes it difficult to solve problems efficiently. A system that can resolve this situation and enable even non-experts to respond quickly and accurately is needed.

[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 a means for adding alarm information to an analysis queue, a means for analyzing the alarm information using a generative AI model to generate an analysis result, and a means for translating the analysis result and presenting a corrective measure. This allows even non-experts to respond to alarms quickly and accurately. Furthermore, by utilizing a past database and knowledge base, it is possible to efficiently present appropriate corrective measures.

[1028] "Alarm information" refers to warnings and error messages that are generated by radios and other equipment during base station construction work.

[1029] A "terminal" is a device, such as a smartphone or tablet, that a user uses to input and display alarm information.

[1030] "JSON format" is an abbreviation for JavaScript Object Notation, and is a data format for sending alarm information to a server.

[1031] "Server" refers to a computer system that receives alarm information, analyzes, translates, and suggests corrective measures.

[1032] The "analysis queue" is a data queue that stores alarm information received within the server and analyzes it sequentially.

[1033] A "generative AI model" is an artificial intelligence model used to analyze alarm information and understand its meaning.

[1034] "Natural language processing technology" is a technology used by generative AI models to analyze the text of alarm information and understand its meaning.

[1035] A "translation model" is an artificial intelligence model used to translate analysis results into a language that the user can understand.

[1036] "Corrective measures" are specific steps and measures for resolving alarm problems that the server presents based on the analysis results and past databases and knowledge bases.

[1037] "LINE message format" refers to the format of a message application that a device uses to notify a user of alarm analysis results and corrective measures.

[1038] A "database" is a system that maintains records of past alarm information and corrective measures.

[1039] A "knowledge base" is an information aggregation system that accumulates expert knowledge and past experience.

[1040] The present invention is a system for improving the efficiency of alarm response during base station construction work. The program processing procedure of this system is described in detail below.

[1041] Alarm Input Acquisition

[1042] The user inputs the English alarm message displayed on the radio into the LINE message screen on a smartphone, tablet, or other device. This causes the alarm information to be acquired by the device. For example, the user can input the alarm message "Power supply error detected. Please check the power connection." into their device.

[1043] Alarm details transmission

[1044] The device converts the acquired alarm information into JSON format. The converted alarm information is sent to the server as an HTTP POST request. For example, the device sends data to the server in the format "{"alarm_message": "Power supply error detected. Please check the power connection."}". The server receives this request and prepares it for analysis.

[1045] Alarm Analysis

[1046] The server adds the received alarm information to the analysis queue. It then calls the generative AI model, which retrieves the alarm information from the analysis queue and begins analysis. The generative AI model uses natural language processing technology to analyze the meaning of the alarm information and identify the cause and countermeasures. For example, the generative AI model understands the meaning of "Power supply error detected. Please check the power connection." and realizes that it is a power-related problem.

[1047] Alarm translation and correction method suggestions

[1048] Once the server obtains the analysis results, it calls the translation model to translate the alarm information into Japanese. For example, the server translates "Power supply error detected. Please check the power connection." into "A power supply error has been detected. Please check the power connection." It then references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will suggest the corrective measure, "Check the BBU's power connection and reconnect if necessary."

[1049] Send results

[1050] The server sends the generated translation result and corrective measures to the device. The sent content is received by the device as an HTTP response, which the device converts into a LINE message format. For example, the response from the server is sent in the following format: {"translated_message": "A power supply error has been detected. Please check the power connection.", "corrective_action": "Check the BBU power connection and reconnect if necessary."}.

[1051] Result confirmation and processing

[1052] The device will display the translation results and corrective measures on the LINE message screen. The user will check this message and follow the instructions to take the necessary corrective measures. For example, if the message "A power error has been detected. Please check the power connection," is displayed, the user should check the power connection to the BBU (baseband unit) and reconnect it.

[1053] Specific examples

[1054] As a concrete example, consider the case where a user inputs an alarm saying, "Power supply error detected. Please check the power connection." The device sends this alarm information to the server, which analyzes it using a generative AI model. The analysis results are translated into Japanese and displayed as, "A power supply error has been detected. Please check the power connection." Furthermore, by referencing the database, the server presents a specific corrective measure: "Check the BBU power connection and reconnect if necessary." Ultimately, the problem is resolved quickly when the user follows this procedure and takes the appropriate action.

[1055] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1056] Step 1:

[1057] Alarm Input Acquisition

[1058] The alarm information is acquired by the user by entering the alarm message displayed on the radio into the LINE message screen of their smartphone or tablet. Specifically, the user enters the alarm message "Power supply error detected. Please check the power connection." The entered alarm information is saved in the device's internal memory.

[1059] Input: Alarm message displayed on the radio

[1060] Output: Alarm information entered on the LINE message screen

[1061] Step 2:

[1062] Alarm details transmission

[1063] The alarm information acquired by the device is converted into JSON format and sent to the server. When converting the message, it is converted into a JSON format such as "{"alarm_message": "Power supply error detected. Please check the power connection."}". The converted alarm information is sent as an HTTP POST request. The server receives this request and saves the log in a database.

[1064] Input: Alarm information entered on the LINE message screen

[1065] Output: Alarm information in JSON format sent to the server as an HTTP POST request

[1066] Step 3:

[1067] Alarm Analysis

[1068] The server adds the received alarm information to an analysis queue. The generative AI model extracts the alarm information from the queue and analyzes it using natural language processing techniques. Specifically, it understands the alarm information through processes such as tokenization, semantic analysis, and context understanding. For example, it understands that the message "Power supply error detected. Please check the power connection" is a power-related problem.

[1069] Input: Alarm information in JSON format sent to the server

[1070] Output: Analysis results from the generative AI model

[1071] Step 4:

[1072] Alarm translation and correction method suggestions

[1073] The server obtains the analysis results obtained from the generative AI model and calls the translation model to translate the alarm information into Japanese. For example, it translates "Power supply error detected. Please check the power connection." into "A power supply error has been detected. Please check the power connection." The server then refers to its past database and knowledge base to search for an appropriate corrective measure. For example, it identifies the corrective measure as "Check the power connection of the BBU and reconnect if necessary."

[1074] Input: Analysis results from generative AI model

[1075] Output: Japanese translation by translation model and correction method

[1076] Step 5:

[1077] Send results

[1078] The server generates an HTTP response that sends the translation result and corrective actions to the device. The response is received by the device and converted into a LINE message format. For example, the following format is sent to the device: {"translated_message": "A power supply error has been detected. Please check the power connection.", "corrective_action": "Check the BBU power connection and reconnect if necessary."}.

[1079] Input: Japanese translation by translation model and correction method

[1080] Output: Translation results converted into LINE message format and correction methods

[1081] Step 6:

[1082] Result confirmation and processing

[1083] The device displays the translation result and corrective measures on the LINE message screen. The user can check the result and follow the instructions to take the necessary corrective measures. For example, if a user sees the message "A power supply error has been detected. Please check the power supply connection," they can check the power supply connection of the BBU and reconnect it if necessary.

[1084] Input: Translation results converted to LINE message format and correction methods

[1085] Output: User takes corrective action

[1086] (Application example 1)

[1087] 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."

[1088] One challenge is the difficulty of quickly and accurately analyzing alarm information generated by robots in factories and presenting appropriate corrective measures. In particular, when non-expert engineers respond to alarms, it can be difficult to quickly find appropriate countermeasures, which can reduce work efficiency and delay problem resolution.

[1089] 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.

[1090] In this invention, the server includes means for inputting alarm information, means for transmitting the input alarm information to the server, means for analyzing the alarm information and generating an analysis result, means for translating the analysis result and presenting a corrective procedure, means for transmitting the presented corrective procedure to a terminal, and means for displaying the corrective procedure via a smart device based on the alarm information, thereby enabling a prompt and accurate response to alarms issued by robots in a factory.

[1091] "Alarm information" is information about errors and warning messages generated by robots in the factory.

[1092] "Input means" refers to a means for inputting alarm information using a smart device or terminal.

[1093] The "transmission means" is a means for transmitting input alarm information to the server.

[1094] The "analysis means" is a means by which the server analyzes alarm information and generates an analysis result.

[1095] The "translation means" is a means for translating the generated analysis results and presenting corrective measures.

[1096] The "presentation means" is a means for transmitting the translated analysis results and corrective measures to the terminal.

[1097] The "means for displaying via a smart device" refers to a means for displaying corrective procedures on a smart device based on alarm information.

[1098] "Corrective measures" are specific procedures or measures to resolve a problem that are identified based on alarm information.

[1099] This invention is a system for quickly and accurately managing alarm information generated by robots in factories and suggesting appropriate corrective measures. Specifically, it implements a series of processes: inputting and transmitting alarm information, analyzing it, translating it, and suggesting corrective measures.

[1100] First, to input alarm information, a smart device (e.g., smart glasses or a smartphone) is used. The user inputs alarm information into the terminal using this smart device. For example, if the robot issues an "emergency stop error" alarm, the user can voice-input "Emergency stop error detected. Please check the emergency stop button." into the smart glasses.

[1101] Next, the terminal converts the input alarm information into JSON format and sends it as an HTTP request to the server, which receives the request and adds the alarm information to the analysis queue.

[1102] The server uses the generative AI model to analyze the alarm information. It uses natural language processing technology to analyze the content of the alarm information and identify the cause and countermeasures. For example, in the case of the alarm information "Emergency stop error detected," the generative AI model determines that the status of the emergency stop button needs to be checked.

[1103] The analysis results are translated into Japanese, and the server refers to a past database and knowledge base to search for appropriate corrective measures. For example, a corrective measure such as "Check the emergency stop button" is presented.

[1104] The server sends the translation results and correction instructions to the device, which receives them, converts them into a LINE message format, and displays them to the user. The user can then check the correction instructions on their smart device and take action according to the instructions.

[1105] For example, if the message "A power error has been detected. Please check the power connection" appears, the user can quickly resolve the issue by checking the robot's power connection and reconnecting it if necessary.

[1106] An example of a prompt is as follows:

[1107] Smart glasses display: "Please speak alarm information:"

[1108] User speaks: "Emergency stop error detected. Please check the emergency stop button."

[1109] This system will enable even engineers without specialized knowledge to respond to alarms quickly and accurately, and is expected to improve work efficiency and quality within the factory.

[1110] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1111] Step 1:

[1112] A user inputs alarm information using a smart device. For example, the user inputs alarm information by voice using smart glasses. The input is converted into text and stored in the terminal as text alarm information.

[1113] Input: Alarm information (audio)

[1114] Output: Alarm information (text format)

[1115] Step 2:

[1116] The device converts the input alarm information into JSON format and sends it as an HTTP request to the server. The server receives this request and adds the alarm information to a queue.

[1117] Input: Alarm information (text format)

[1118] Output: Alarm information (JSON format)

[1119] Step 3:

[1120] The server calls the generative AI model, retrieves the alarm information from the queue, and begins analysis. The generative AI model uses natural language processing technology to analyze the content of the alarm information and identify the cause and countermeasures.

[1121] Input: Alarm information (JSON format)

[1122] Data processing: Analysis using natural language processing technology

[1123] Output: Analysis results (text format)

[1124] Step 4:

[1125] The server retrieves the analysis results and translates them into Japanese using a translation model. It then searches for appropriate corrective measures by referencing past databases and knowledge bases, and identifies specific corrective steps.

[1126] Input: Analysis results (text format)

[1127] Data processing: Translation and database reference to find corrective procedures

[1128] Output: Translation results and correction methods (text format)

[1129] Step 5:

[1130] The server then sends the translated analysis results and corrective measures to the device, which then receives them, converts them into LINE message format, and displays them to the user.

[1131] Input: Translation results and correction methods (text format)

[1132] Data processing: conversion to message format

[1133] Output: LINE message

[1134] Step 6:

[1135] The user checks the translation results and corrective measures displayed in the LINE message and follows the instructions to respond to the alarm. For example, if the message says "Please check the emergency stop button," the user should actually check the emergency stop button and take the necessary steps.

[1136] Input: LINE message (displayed corrective action)

[1137] Output: Physical alarm response WeChat, for example, button confirmation and appropriate operation

[1138] 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.

[1139] The present invention is a system for improving the efficiency of alarm responses during base station construction work, and is equipped with a function that recognizes the user's emotions and optimizes the response. Below, we will explain in detail how the system can be combined with an emotion engine.

[1140] 1. Alarm input acquisition

[1141] The user inputs the English alarm message displayed on the radio into the LINE message screen using a smartphone or other device, and the alarm information is then acquired by the device.

[1142] 2. User Emotion Recognition

[1143] The device activates an emotion engine that recognizes emotions from the user's input, facial expressions, voice, etc. For example, it analyzes whether the user is feeling anxious or impatient when inputting.

[1144] 3. Alarm details transmission

[1145] The alarm information and user emotion data acquired by the device are sent to the server. Specifically, this information is converted into JSON format and sent to the server as an HTTP request. The server receives this request.

[1146] 4. Alarm Analysis

[1147] The server adds the received alarm information to the analysis queue. Then, it calls the generative AI model, which extracts the alarm information from the queue and begins analyzing it. By analyzing the information while also referring to emotional data, it fine-tunes the response to the user.

[1148] 5. Alarm translation and correction method provided

[1149] Once the server receives the analysis results, it calls up a translation model to translate the alarm information into Japanese. Once translation is complete, it references past databases and knowledge bases to search for appropriate corrective measures. For example, if an alarm about a power supply error occurs, the server will present corrective measures, including steps to check the power supply connection status.

[1150] 6. Emotion-Based Response Modulation

[1151] The server adjusts the tone and content of the response message based on the user's emotional state, for example providing more polite and detailed instructions if the user is impatient.

[1152] 7. Send results

[1153] The server generates a translation result, provides corrections, and sends a response adjusted based on the emotion to the device. The content is received by the device as an HTTP response and converted into a LINE message format.

[1154] 8. Results confirmation and processing

[1155] The device will display the translation results and correction methods on the LINE message screen along with the adjusted response. The user can review and understand the content. If necessary, additional support and help will be provided.

[1156] 9. Implementation of specific correction work

[1157] The user follows the suggested corrective measures and takes the necessary corrective action, for example, by performing specific steps such as reconnecting the power or checking the cables.

[1158] As a concrete example, consider the following scenario: If a user inputs an alarm saying "Power supply error detected. Please check the power connection." and the emotion engine recognizes that the user is feeling anxious, the server will generate a response such as "A power supply error has been detected. Please do not worry. Please stay calm and check the power connection and reconnect if necessary." In this way, instructions that take the user's emotions into consideration can be provided, enabling faster and more accurate responses.

[1159] This system not only enables a quick and accurate response when an alarm occurs, but also provides support that takes the user's emotions into consideration, thereby improving work efficiency and quality and helping to reduce user stress.

[1160] The processing flow will be explained below.

[1161] Step 1:

[1162] The user types the English alarm message displayed on the radio into the LINE message screen. The device receives this message.

[1163] Step 2:

[1164] As soon as the device receives the user's input, it starts the emotion engine, which analyzes the user's facial expressions and voice tone to recognize the user's emotional state.

[1165] Step 3:

[1166] The alarm information and recognized emotion data acquired by the device are converted into JSON format and sent as an HTTP request to the server, which receives the request.

[1167] Step 4:

[1168] The server adds the received alarm information to the analysis queue. Then it calls the generative AI model, which retrieves the alarm information from the queue and begins analysis. In parallel, it also references emotion data and adjusts the analysis results.

[1169] Step 5:

[1170] The generative AI model uses natural language processing technology to perform semantic analysis of the alarm message, specifically analyzing the content of the error message and identifying its type and cause.

[1171] Step 6:

[1172] The server retrieves the analysis results, calls up a translation model, and translates the alarm information into Japanese. Based on the translated content, it references past databases and knowledge bases to search for appropriate corrective measures.

[1173] Step 7:

[1174] The server combines the translation results with the correction methods and adjusts the response message based on the emotional data provided by the emotion engine. For example, if the user is feeling anxious, the response message will be changed to a calming tone.

[1175] Step 8:

[1176] The server sends the adjusted response message to the device as an HTTP response. The device receives this response and converts it into a LINE message format.

[1177] Step 9:

[1178] The device displays the translation results and corrections on the LINE message screen, and the displayed content is tailored to the user's emotional state.

[1179] Step 10:

[1180] The user takes appropriate corrective action according to the suggested corrective measures. For example, if the user checks the power connection status and tries to reconnect it, a message will be displayed stating, "A power error has been detected. Please stay calm and check the power connection and reconnect if necessary."

[1181] These specific processing steps enable a quick and accurate response when an alarm occurs, and since the user's emotions are taken into consideration, stress is reduced and work efficiency is improved. In addition, the emotion recognition function provides support so that the user can continue working with peace of mind.

[1182] Example 2

[1183] 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."

[1184] Alarm responses during base station construction work require rapid and accurate responses, but user stress and frustration can reduce work efficiency. Alarm information is often displayed in different languages, often resulting in delays in translation and presentation of corrective measures. Conventional systems lack optimal support that combines emotion recognition and natural language processing, increasing the burden on users and resulting in reduced work quality. Therefore, a system that optimizes responses based on user emotions and provides rapid and accurate responses is needed.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1186] In this invention, the server includes means for adding alarm information to an analysis queue and calling a generative AI model for analysis, means for translating the analysis results and presenting corrective measures, and means for adjusting a response message based on the user's emotional state. This enables prompt and accurate support while taking the user's emotions into consideration when an alarm occurs, improving work efficiency and quality and reducing user stress.

[1187] "Alarm information" is a message indicating an abnormality or warning that occurs during base station construction work.

[1188] The "means for inputting" is an interface that allows a user to input alarm information into the system using a smartphone or other terminal.

[1189] A "terminal" is a device for acquiring and transmitting alarm information and user emotion data, and includes smartphones, tablets, etc.

[1190] An "emotion recognition engine" is software or an algorithm that analyzes emotions from user input, facial expressions, voice, etc.

[1191] The JSON format is a text-based data exchange format that structures data and facilitates communication between systems.

[1192] A "server" is a computer system that receives alarm information and emotion data, analyzes them, and generates responses.

[1193] An "analysis queue" is a data structure for processing alarm information awaiting analysis in order.

[1194] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze alarm information and generate appropriate responses or corrective measures.

[1195] "Translation" is the process of converting the analysis results from the original text into another language (for example, Japanese).

[1196] "Corrective measures" refer to specific procedures and measures to resolve problems based on alarm information.

[1197] The "means for adjusting the response message" is a process for changing the tone and content of the response message based on the user's emotional state.

[1198] "LINE message format" refers to the message format used in the LINE application.

[1199] The present invention provides a system for improving the efficiency of alarm responses during base station construction work, and is particularly equipped with a function for recognizing a user's emotions and optimizing responses. Specific embodiments will be described below.

[1200] Hardware and software used

[1201] The hardware used includes devices such as smartphones and tablets, as well as servers equipped with high-performance CPUs and GPUs, while the software used includes the LINE messaging app, an emotion recognition engine (e.g., emotion recognition API), a generative AI model (e.g., language generation model), and a translation model (e.g., automatic translation API).

[1202] Explanation of program processing

[1203] Alarm Input Acquisition

[1204] The user inputs the English alarm information displayed on the radio as a LINE message on a smartphone or other device. The device then acquires the alarm information. At this time, the user opens the chat screen of the LINE app and inputs the English alarm message as text.

[1205] User Emotion Recognition

[1206] The device activates an emotion engine to recognize emotions from the user's input, facial expressions, and voice. The device uses data acquired from the smartphone's camera and microphone and executes emotion recognition algorithms. For example, the emotion engine detects if the user looks anxious or if their voice is trembling.

[1207] Alarm details transmission

[1208] The device converts the acquired alarm information and user emotion data into JSON format and sends it to the server as an HTTP request. The server receives this request. Specifically, the device sends the data using the "POST" method, and the server parses the data using a function such as "JSON.parse()".

[1209] Alarm Analysis

[1210] The server adds the received alarm information to the analysis queue, then calls the generative AI model to begin analysis. The server then removes the alarm information from the queue and passes it to the AI ​​model as input data. When the generative AI model analyzes the input "Power supply error detected," it finds abnormal patterns from past data.

[1211] Alarm translation and correction method suggestions

[1212] The server calls up the translation model and translates the alarm information into Japanese. It then refers to the past database and knowledge base to search for the appropriate corrective action. For example, the corrective action for a "Power supply error" might be to "Check the power supply connection status."

[1213] Emotion-Based Response Modulation

[1214] The server adjusts the tone and content of the response message based on the user's emotional state. For example, if the user is feeling anxious, the server uses more reassuring and polite language. The server generates a message like, "Don't worry. Stay calm and check the steps."

[1215] Send results

[1216] The server sends the translation results, correction methods, and responses adjusted based on emotions to the device. The server sends the data as an HTTP response, which the device receives. The device then converts the received data into LINE message format.

[1217] Result confirmation and processing

[1218] The device displays the translation result and correction methods on the LINE message screen along with the adjusted response. The user can review and understand the content. The device may also record the message display timestamp and the user's reaction data.

[1219] Implementing specific correction work

[1220] The user follows the suggested corrective action and performs the necessary corrective action, such as reconnecting the power or checking the cables. The user follows the detailed steps, including arrows and diagrams.

[1221] Examples of concrete examples and prompts

[1222] For example, if a user inputs the alarm "Power supply error detected. Please check the power connection" into the LINE app and unconsciously shows signs of restlessness, the emotion engine will recognize this as anxiety. The server will receive this and generate a response such as "A power supply error has been detected. Please stay calm and check the power connection and reconnect if necessary," and send it as a LINE message.

[1223] An example prompt is:

[1224] "Please enter the alarm displayed on your radio. Also, briefly describe the emotions you felt as you typed."

[1225] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1226] Step 1:

[1227] The user inputs the English alarm information displayed on the radio as a LINE message on a smartphone or other device. The input alarm information is then acquired by the device. Specifically, the user opens the LINE app and inputs alarm information such as "Power supply error detected. Please check the power connection" into the chat screen. The input data is saved in text format in the device's memory.

[1228] Step 2:

[1229] The device launches an emotion recognition engine to recognize emotions from the user's input, facial expressions, voice, etc. Input data includes the user's input text, camera footage, and voice. The emotion recognition engine analyzes this data and detects the emotion the user is feeling (e.g., anxiety, impatience). The output data is generated in JSON format, listing the type of emotion recognized and its intensity.

[1230] Step 3:

[1231] The device converts the acquired alarm information and user emotion data into JSON format and sends it to the server as an HTTP request. Specifically, the device combines the alarm information and emotion data into a single JSON object and sends it to the server using a "POST" request. The input data is the alarm information and emotion data, and the output data is a status indicating that the transmission was successful.

[1232] Step 4:

[1233] The server adds the received alarm information to the analysis queue and calls the generative AI model to begin analysis. The input data includes the JSON object sent from the client. Specifically, the server adds this data to the analysis queue and passes it to the generative AI model in the appropriate order. The generative AI model understands the content of the alarm from the alarm statement and generates specific countermeasures. The output data is the type of alarm and the corresponding countermeasures.

[1234] Step 5:

[1235] The server calls the translation model and translates the alarm information into Japanese. The input data includes the alarm text from the analysis results. Specifically, the server calls the translation API and translates from English to Japanese. The output data is the translated Japanese alarm text.

[1236] Step 6:

[1237] The server references historical databases and knowledge bases to search for appropriate corrective measures based on the analysis results. Input data includes alarm information translated into Japanese and analysis results. Specifically, the server executes a database query to retrieve relevant corrective measures. The output data is detailed instructions for the corrective measures.

[1238] Step 7:

[1239] The server adjusts the tone and content of the response message based on the user's emotional state. The input data includes the user's emotional data and corrective action instructions. Specifically, the server analyzes the emotional data and generates an emotion-sensitive message, such as "Don't worry. Please stay calm and review the steps." The output data is the adjusted response message.

[1240] Step 8:

[1241] The server generates a translation result, provides corrective measures, and sends a response adjusted based on the emotion to the device. The input data includes the translated alarm information, corrective measures, and an adjusted response message. Specifically, the server compiles this information into a single JSON object and sends it to the device as an "HTTP response." The output data is a status indicating successful transmission.

[1242] Step 9:

[1243] The device displays the translation result and correction method on the LINE message screen along with an adjusted response. The input data includes a JSON object received from the server. Specifically, the device parses the JSON data, converts it into a LINE message format, and displays it to the user. The output is when the user checks it and understands the content.

[1244] Step 10:

[1245] The user follows the presented corrective measures and performs the necessary corrective work. The input data includes the corrective measures displayed in the LINE message. As specific actions, the user performs specific steps such as reconnecting the power and checking the cables. The output is that the work has been completed.

[1246] (Application example 2)

[1247] 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."

[1248] Conventional alarm response systems respond uniformly without considering the user's emotional state, which can delay appropriate responses and increase stress, especially when the user is feeling anxious or impatient. Furthermore, the translation of alarm information and the presentation of corrective measures are also uniform, making it difficult to provide individualized responses tailored to the user's situation. Furthermore, there was no way to recognize the user's emotions and optimize the response based on them. This resulted in problems with reduced accuracy and speed of responses.

[1249] 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 inputting alarm information, means for transmitting the input alarm information and emotion data to the server, means for analyzing the alarm information and emotion data and generating an analysis result, means for translating the analysis result and presenting a corrective measure, means for adjusting the presented corrective measure based on the emotion and transmitting it to the terminal, and means for recognizing the user's emotion. This enables individual responses that take the user's emotion into consideration, improving the accuracy and speed of alarm responses. It also makes it possible to reduce user stress and provide more effective support.

[1250] "Alarm information" refers to warning or error information issued by a system or device, which alerts the user to a specific problem or alerts the user to a particular problem.

[1251] "Emotion data" is data that indicates the emotional state of a user analyzed from facial expressions, voice, and text input.

[1252] A "server" is a central control unit that receives, analyzes, and processes data sent by users.

[1253] The "analysis result" is the result information obtained by the server analyzing the alarm information and emotion data.

[1254] "Corrective measures" indicate specific procedures and methods for dealing with alarm information.

[1255] "Translation" refers to the process of converting analysis results and corrective measures into a language that is easy for users to understand.

[1256] A "terminal" is a connected device used by a user, such as a smartphone or smart glasses.

[1257] "Means for recognizing emotions" refers to technology that identifies emotions from a user's facial expressions, voice, and text input.

[1258] "Adjustment" refers to the process of optimizing the corrective measures and response content based on the user's emotional data.

[1259] A specific example of the present invention is a system called "Security Emotion Manager," the details of which are given below.

[1260] First, a user inputs alarm information from a security system using a smartphone or smart glasses. This alarm information is input by the user, and the specific content of the alarm is obtained in text format.

[1261] The device then uses its built-in camera and microphone to recognize the user's emotional state. It then uses DeepFace facial recognition software and other voice emotion recognition engines to extract emotional data from the user's facial expressions and voice. This emotional data is then sent to the server along with the alarm information. The device then converts this data into JSON format and sends it as an HTTP request.

[1262] The server analyzes the received alarm information and emotion data and generates an analysis result. It uses natural language processing technology to understand the content of the alarm information. Furthermore, it supplements the analysis result with a generative AI model and suggests the optimal corrective measures by referencing past databases and knowledge bases.

[1263] Once the analysis and corrective measures are ready, the server can adjust this information based on the user's emotions—for example, by providing more polite and specific instructions if the user is feeling anxious—using a generative AI model.

[1264] Finally, the adjusted instructions and corrective measures are sent to the terminal and displayed on the user's device, allowing the user to review them and take specific corrective actions, enabling the user to respond appropriately and promptly.

[1265] As a concrete example, consider a case where a user inputs alarm text information such as "Unauthorized access detected. Please verify the security status." and provides an image path as "user_image.jpg" and an audio path as "user_voice.wav." The server generates an optimal corrective action based on this information and provides a response tailored to the user's emotions. For example, if the user expresses impatience, a specific instruction such as "Unauthorized access detected. Please remain calm. Please verify the security status." is returned.

[1266] The system recognizes the user's emotions and takes them into consideration when providing assistance, improving the accuracy and speed of responses and reducing user stress. It also utilizes cutting-edge technologies such as DeepFace and generative AI models to improve the overall user experience.

[1267] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1268] Step 1:

[1269] A user inputs alarm information from a security system using a smartphone or smart glasses. For example, the user inputs text such as "Unauthorized access detected. Please verify the security status." and sends it to an application on the device. The input of this procedure is the alarm information in text format, and the output is the alarm information received by the device.

[1270] Step 2:

[1271] The device recognizes the user's emotions. The device's built-in camera takes a photo of the user's face and a microphone records their voice. Then, using facial recognition software "DeepFace" and a voice emotion recognition engine, these data are analyzed to extract emotional data. The input for this procedure is the user's facial image and voice data, and the output is emotional data that indicates the user's emotional state.

[1272] Step 3:

[1273] The alarm information and emotion data acquired by the device are converted into JSON format and sent to the server as an HTTP request. The input for this data transmission is the alarm information and emotion data, and the output is a transmission completion notification to the server.

[1274] Step 4:

[1275] The server analyzes the received alarm information and emotional data. First, it uses natural language processing technology to analyze the alarm information and understand its content. Next, it uses a generative AI model to supplement the analysis results and perform a deeper analysis of the meaning and impact of the alarm information. The input to this process is the alarm information and emotional data received by the server, and the output is the analysis results.

[1276] Step 5:

[1277] Based on the analysis results, the server searches for corrective measures by referring to a past database or knowledge base. For example, it refers to how similar alarms have been handled in the past and proposes the optimal corrective measures. The input to this procedure is the analysis results, and the output is the corrective measures.

[1278] Step 6:

[1279] The server adjusts the corrective measures and response messages based on the user's emotional data. For example, if the user feels anxious, the server adjusts the response messages to include polite and specific instructions. The inputs to this procedure are the corrective measures and the user's emotional data, and the output is the adjusted response message.

[1280] Step 7:

[1281] The server sends the adjusted response message and the correction method to the terminal. The input of this data transmission is the adjusted response message and the correction method, and the output is a transmission completion notification to the terminal.

[1282] Step 8:

[1283] The terminal displays the received response message and corrective action to the user. The user confirms it and performs specific corrective action. The input of this procedure is the message and corrective action received by the terminal, and the output is the specific operation or response by the user.

[1284] This allows the user to deal with the alarm quickly and appropriately, and receive emotional support.

[1285] 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.

[1286] 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.

[1287] 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.

[1288] 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.

[1289] 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.

[1290] 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.

[1291] 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).

[1292] 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.

[1293] 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."

[1294] 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.

[1295] 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).

[1296] 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.

[1297] 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.

[1298] 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.

[1299] 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.

[1300] 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.

[1301] 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.

[1302] 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.

[1303] 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.

[1304] 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.

[1305] 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.

[1306] The following is further disclosed regarding the above embodiment.

[1307] (Claim 1)

[1308] a means for inputting alarm information;

[1309] means for transmitting the input alarm information to a server;

[1310] means for analyzing alarm information and generating an analysis result;

[1311] A means of translating the analysis results and suggesting corrective measures;

[1312] means for transmitting the proposed corrective measures to the terminal;

[1313] A system including:

[1314] (Claim 2)

[1315] 10. The system of claim 1, further comprising means for analyzing the alarm information using natural language processing techniques.

[1316] (Claim 3)

[1317] 2. The system according to claim 1, further comprising means for referencing a past database or knowledge base based on the analysis results to obtain corrective measures.

[1318] "Example 1"

[1319] (Claim 1)

[1320] A means for acquiring alarm information to a terminal;

[1321] A means to convert the acquired alarm information into JSON format and send it to the server;

[1322] a means for adding the transmitted alarm information to an analysis queue;

[1323] A means for analyzing alarm information using a generative AI model and generating an analysis result;

[1324] A means of translating the analysis results and suggesting corrective measures;

[1325] A means for sending the proposed corrective measures to the device and converting them into a LINE message format;

[1326] A system including:

[1327] (Claim 2)

[1328] 10. The system of claim 1, further comprising means for analyzing the alarm information using natural language processing techniques.

[1329] (Claim 3)

[1330] 2. The system according to claim 1, further comprising means for referencing a past database or knowledge base based on the analysis results to obtain corrective measures.

[1331] "Application Example 1"

[1332] (Claim 1)

[1333] a means for inputting alarm information;

[1334] means for transmitting the input alarm information to a server;

[1335] means for analyzing alarm information and generating an analysis result;

[1336] A means of translating the analysis results and suggesting corrective measures;

[1337] means for transmitting the proposed corrective measures to the terminal;

[1338] A means for displaying corrective procedures via a smart device based on the alarm information;

[1339] A system including:

[1340] (Claim 2)

[1341] 10. The system of claim 1, further comprising means for analyzing the alarm information using natural language processing techniques.

[1342] (Claim 3)

[1343] 2. The system according to claim 1, further comprising means for referencing a past database or knowledge base based on the analysis results to obtain corrective measures.

[1344] "Example 2: Combining Emotion Engines"

[1345] (Claim 1)

[1346] a means for inputting alarm information;

[1347] means for acquiring input alarm information into a terminal;

[1348] A means for recognizing user emotions using an emotion recognition engine in the terminal;

[1349] means for converting the alarm information and the user's emotion data into JSON format and transmitting the same to a server;

[1350] A means for adding alarm information to an analysis queue and calling a generative AI model for analysis;

[1351] A means of translating the analysis results and suggesting corrective measures;

[1352] means for adjusting a response message based on the emotional state of the user;

[1353] means for transmitting the results to a terminal;

[1354] A method for the device to convert the message into a LINE message format and display it.

[1355] A system including:

[1356] (Claim 2)

[1357] 10. The system of claim 1, further comprising means for analyzing the alarm information using natural language processing techniques.

[1358] (Claim 3)

[1359] 2. The system according to claim 1, further comprising means for referencing a past database or knowledge base based on the analysis results to obtain corrective measures.

[1360] "Application example 2 when combining emotion engines"

[1361] (Claim 1)

[1362] a means for inputting alarm information;

[1363] means for transmitting the input alarm information and emotion data to a server;

[1364] means for analyzing alarm information and emotion data and generating an analysis result;

[1365] A means of translating the analysis results and suggesting corrective measures;

[1366] a means for adjusting the proposed corrective measures based on the emotion and transmitting the adjusted corrective measures to the terminal;

[1367] means for recognizing a user's emotion;

[1368] A system including:

[1369] (Claim 2)

[1370] 10. The system of claim 1, further comprising means for analyzing the alarm information using natural language processing techniques.

[1371] (Claim 3)

[1372] 2. The system according to claim 1, further comprising means for referencing a past database or knowledge base based on the analysis results to obtain corrective measures. [Explanation of symbols]

[1373] 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 inputting alarm information; means for transmitting the input alarm information to a server; means for analyzing alarm information and generating an analysis result; A means of translating the analysis results and suggesting corrective measures; means for transmitting the proposed corrective measures to the terminal; A system including:

2. 2. The system of claim 1, further comprising means for analyzing the alarm information using natural language processing techniques.

3. The system according to claim 1, further comprising means for referencing a past database or knowledge base based on the analysis results to obtain a corrective method.

Images