System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a problem reported by a user; means for analyzing the received problem and generating a solution by a generative AI; and means for notifying the solution to a building manager.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] When a malfunction occurs in the facilities of a building or hotel, users are forced to spend their time in an uncomfortable environment. Furthermore, building managers often contact the equipment manufacturer because they do not know the cause of the malfunction, and even when the problem can be solved with a simple operation, the equipment manufacturer may have to rush to the scene. It is necessary to improve this inefficiency of response and achieve quick and efficient problem resolution. [Means for solving the problem]

[0005] The system includes a means for receiving problems reported by users, a means for a generative AI to analyze the received problems and generate solutions, and a means for notifying the building manager of the solutions. The system also includes a means for the building manager to try the generated solutions and report the results, and a means for determining the next step based on the reported results. If the generated solutions do not resolve the problem, the system also includes a means for notifying the equipment manufacturer of the problem, a means for coordinating a repair schedule with the equipment manufacturer, and a means for notifying the building manager and users of the adjusted repair schedule, thereby enabling the prompt and efficient resolution of equipment malfunctions.

[0006] "User" refers to an individual or group that uses a facility such as a building or hotel.

[0007] A "report" is an action by a user or building manager to notify the system of a specific problem or malfunction.

[0008] A "problem" is a functional malfunction or failure that occurs in the facilities of a building or hotel.

[0009] "Reception" is the process by which the system receives and records reports from the outside.

[0010] "Generative AI" is an artificial intelligence system that analyzes input data and automatically generates appropriate solutions.

[0011] "Analysis" is the information processing that allows the generative AI to understand the reported problem and derive appropriate countermeasures.

[0012] A "solution" is a specific procedure or method for resolving a reported problem.

[0013] "Notification" refers to the system communicating analysis results and solutions to users and building managers.

[0014] A "building manager" is an individual or organization responsible for the operation and facility management of a building or hotel.

[0015] "Equipment manufacturers" are companies and engineers that manufacture or provide equipment for buildings and hotels.

[0016] "Schedule adjustment" refers to the act of the equipment manufacturer organizing on-site repair response and notifying the building manager and users of the schedule. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention relates to a system for quickly and efficiently resolving problems when malfunctions occur in facilities of buildings, hotels, etc. Specific embodiments for carrying out the present invention are described below.

[0039] This system provides a platform for users, building managers, and equipment manufacturers to efficiently handle everything from reporting problems to resolving them. Its main components are a user terminal, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI.

[0040] System Operation

[0041] Receiving problem reports

[0042] Terminal (user):

[0043] If a user experiences a problem with a building or hotel facility, they can report the issue through a smartphone app or web portal. For example, if the air conditioner in their office isn't working, they can enter a message like "The air conditioner isn't working" into the app and attach photos and videos to send it.

[0044] server:

[0045] The server receives reports from users, records the details in a database, and simultaneously instructs the generative AI to analyze the problem.

[0046] Analyzing problems and generating solutions

[0047] server:

[0048] The generative AI analyzes the received report and identifies the cause of the problem by comparing it with a database of past problems. For example, if a problem with an air conditioner is reported, the AI ​​will generate a basic solution such as "Try turning the power off and on."

[0049] Notification and Implementation of Solutions

[0050] server:

[0051] The generated solution is sent to the building manager's terminal, who then checks the proposed solution and attempts to address the problem.

[0052] Terminal (Building Manager):

[0053] The building manager reports the results of his attempts to turn the air conditioner on and off to the server. If the problem is resolved, this is fed back to the system.

[0054] Escalation and cooperation with equipment manufacturers

[0055] server:

[0056] If the problem persists despite the solutions attempted by the building manager, the generative AI will notify the equipment manufacturer of the situation.

[0057] Terminal (equipment manufacturer):

[0058] An engineer from the equipment manufacturer will confirm the problem and, if necessary, schedule an on-site visit.

[0059] Schedule Notifications

[0060] server:

[0061] The set repair schedule is notified to the building manager and users, allowing users to know in advance about the planned repairs and make preparations.

[0062] Specific examples

[0063] Example 1: Air conditioner malfunction

[0064] 1. Terminal (User):

[0065] A user reported through the app that the air conditioner was not working.

[0066] Attach photos and submit a report.

[0067] 2. Server:

[0068] Receives problem reports and instructs generative AI to analyze them.

[0069] The AI ​​generates a solution such as "Try turning the power off and on" and notifies the building manager.

[0070] 3. Terminal (Building Manager):

[0071] The building manager attempts to turn the air conditioner on and off.

[0072] After the operation, the server reported that the problem persisted.

[0073] 4. Server:

[0074] Escalate issues to equipment manufacturers and schedule repairs.

[0075] 5. Terminal (equipment manufacturer):

[0076] The technician sets the schedule, and the server notifies the building manager and users of the information.

[0077] In this way, the present invention makes it possible to quickly and efficiently resolve equipment problems in buildings and hotels.

[0078] The processing flow will be explained below.

[0079] Step 1:

[0080] Device (user): The user opens the app or web portal and fills in the problem report form with details of the problem, such as "The air conditioner is not working." If necessary, they attach photos and videos.

[0081] Step 2:

[0082] Terminal: The user enters the details of the problem and presses the "Send" button. The problem report is sent to the server.

[0083] Step 3:

[0084] Server: The server receives the problem report from the user and records the details in the database, including the details of the reported problem, the date and time, and any attached files.

[0085] Step 4:

[0086] Server: The generative AI retrieves new defect reports from the database and analyzes the problem by comparing them with past trouble data.

[0087] Step 5:

[0088] Server: The generative AI generates a solution based on the analysis results. For example, it generates a solution such as "Try turning the power off and on."

[0089] Step 6:

[0090] Server: Notifies the generated solution to the building manager's terminal.

[0091] Step 7:

[0092] Device (Building Manager): The building manager receives a notification, checks the solution via the app or web portal, and turns the air conditioner off / on according to the solution.

[0093] Step 8:

[0094] Device (Building Manager): The building manager enters the results of the operation into the app and reports them to the server. For example, they may report, "I tried turning the power off and on, but the problem persists."

[0095] Step 9:

[0096] Server: Receives reports from building managers and the generative AI determines the next steps. If the problem is not resolved, it must be escalated to the equipment manufacturer.

[0097] Step 10:

[0098] Server: The generative AI notifies the equipment manufacturer of the details of the problem and the results of the building manager's trial.

[0099] Step 11:

[0100] Terminal (equipment manufacturer): The equipment manufacturer's engineer checks the report and arranges the date for the on-site visit. Once the schedule is decided, he / she contacts the server.

[0101] Step 12:

[0102] Server: Notifies the building manager and users of the adjusted repair schedule.

[0103] Step 13:

[0104] Terminals (building managers and users): Check the repair schedule and make the necessary preparations.

[0105] This series of processing steps allows building and hotel equipment problems to be resolved quickly and efficiently.

[0106] Example 1

[0107] 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."

[0108] In large facilities such as buildings and hotels, when equipment malfunctions occur, efficient information sharing and problem resolution among users, building managers, and equipment manufacturers is essential for rapid and appropriate response. However, currently, the process from reporting a problem to providing notification of a solution, responding, and providing feedback on the results is often done manually, which takes time and effort. Furthermore, if an appropriate solution is not adopted, the problem may be prolonged, resulting in further costs and a decline in reliability.

[0109] 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.

[0110] In this invention, the server includes means for receiving problems reported by users, means for the generative AI to analyze the received problems and generate solutions, means for notifying the building manager of the solutions, means for registering the problem reports in a database, means for the generative AI to identify the cause of the problem, and means for the generative AI to refer to a database of past troubles. This makes it possible to quickly and appropriately solve equipment malfunctions in buildings and hotels.

[0111] "User" refers to the individual or entity who discovers and reports a problem while using the Equipment.

[0112] "Means for receiving problems" refers to the function of receiving data on problems reported by users regarding equipment.

[0113] "Generative AI" refers to artificial intelligence that analyzes received data and automatically generates appropriate solutions.

[0114] "Means of analyzing problems and generating solutions" refers to the function of using generative AI to analyze the causes of problems and create solutions by referring to past data.

[0115] "Building manager" refers to the individual or organization responsible for managing the facilities of a building or facility and for implementing the solutions communicated by the generative AI.

[0116] "Means for notifying solutions" refers to a function for communicating the generated solutions to the building manager.

[0117] "Means for registering in a database" refers to the function of saving problems reported by users in a database with a unique ID.

[0118] "Means for identifying the cause of the problem" refers to the function of the generative AI to refer to past trouble data to identify the cause of the reported problem.

[0119] A "past trouble database" refers to a collection of information that stores detailed records of troubles that have occurred in the past and the solutions to those troubles.

[0120] "Equipment manufacturer" refers to the company or organization that manufactures the equipment and provides technical support.

[0121] "Means to adjust repair schedules" refers to the function of setting specific repair dates and times with the equipment manufacturer to resolve the problem.

[0122] "Means for notifying repair schedules" refers to a function for communicating the adjusted repair schedule to building managers and users.

[0123] The present invention provides a system for quickly and appropriately responding to equipment malfunctions in large facilities such as buildings and hotels. Specific embodiments for carrying out the present invention are described below.

[0124] System configuration

[0125] This system provides a platform for users, building managers, and equipment manufacturers to efficiently handle everything from reporting problems to resolving them. Its main components are a user terminal, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI.

[0126] Hardware and software used

[0127] User device: A device such as a smartphone, tablet, or computer.

[0128] Building manager's terminal: Devices such as PCs, tablets, and smartphones.

[0129] Equipment manufacturer terminal: Devices such as computers, tablets, and smartphones.

[0130] Server: A high-performance computer server equipped with generative AI that analyzes problems and generates solutions.

[0131] System operation explanation

[0132] Accepting problem reports

[0133] Terminal (user)

[0134] If a user experiences a problem with a building or hotel facility, they can report the problem through a smartphone app or web portal. For example, to report a problem like "The air conditioner in my office isn't working," they simply type "The air conditioner isn't working" into the app and attach photos or videos as needed. When the user presses the "Submit" button, the report is sent to the server.

[0135] Problem Report Database Registration

[0136] server

[0137] The server receives problem reports sent by users and records their contents in a database. At this time, details of the reported problem and attached photos and videos are saved together. A unique ID is also assigned to the report contents for management.

[0138] Problem analysis using generative AI models

[0139] server

[0140] Based on problem reports registered in the database, the generative AI model is instructed to perform an analysis. The generative AI model refers to past trouble data and performs an analysis to identify the cause of the problem. For example, in response to a report that "the air conditioner is not working," it will list possible causes, such as a power failure or a clogged filter.

[0141] Solution Generation

[0142] server

[0143] The generative AI model generates optimal solutions based on the analysis results. For example, the AI ​​might suggest basic solutions such as "Try turning the power off and on." If necessary, it also includes detailed instructions and precautions.

[0144] Solution Notification

[0145] server

[0146] The generated solution is sent to the building manager's terminal, and the notification includes a summary of the report along with the details of the solution.

[0147] Building manager's response

[0148] Terminal (Building Manager)

[0149] The building manager receives the notification and takes action according to the proposed solution, for example, turning the air conditioner off and on, and then reports the result to the server.

[0150] Reporting results and feedback

[0151] server

[0152] Receive reports from building managers to see if the problem has been resolved. If the problem has been resolved, record the information in a database and notify the user.

[0153] Escalation and cooperation with equipment manufacturers

[0154] server

[0155] If the problem cannot be resolved by the building manager, the generative AI model escalates the issue to the equipment manufacturer, who sends a detailed report and dispatches a technician to handle the issue as needed.

[0156] Response by equipment manufacturers

[0157] Terminal (equipment manufacturer)

[0158] An engineer from the equipment manufacturer will identify the problem and schedule a site visit or repair. This information is sent to the server.

[0159] Repair schedule notification

[0160] server

[0161] The set repair schedule is notified to the building manager and users, allowing users to know about the planned repairs in advance and make preparations.

[0162] Specific examples

[0163] For example, if a problem is reported that "the air conditioner in the office is not working," the following actions will be taken:

[0164] 1. Terminal (User)

[0165] A user reports "the air conditioner is not working" in the app and sends it with a photo attached.

[0166] 2. Server

[0167] Receives problem reports, stores them in a database, and directs the generative AI model to analyze them.

[0168] 3. Server

[0169] The AI ​​generates a solution such as "Try turning the power off and on" and notifies the building manager.

[0170] 4. Terminal (Building Manager)

[0171] The building manager attempts to operate the power supply, but the problem persists, so he reports the results to the server.

[0172] 5. Server

[0173] Escalate the issue to the equipment manufacturer and schedule a repair response.

[0174] 6. Terminal (equipment manufacturer)

[0175] The technician sets the schedule and the server notifies the building manager and users.

[0176] This makes it possible for the system of the present invention to quickly and efficiently resolve equipment problems in buildings and hotels.

[0177] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0178] Step 1:

[0179] User (Device):

[0180] Users report equipment problems through a smartphone app or web portal. They enter specific prompt text (e.g., "The air conditioner isn't working") into the app and attach photos and videos as needed. A problem report (text, photos, and videos) is generated based on the input data. When the user presses the "Submit" button, the entered problem report is sent to the server.

[0181] Step 2:

[0182] server:

[0183] The server records the problem reports received from users in a database. At this time, it receives the report content data (text, photos, videos) and records it with a unique ID. The input data is the problem report data from the user, and the output is the problem report stored in the database.

[0184] Step 3:

[0185] server:

[0186] Based on the problem reports registered in the database, the generative AI model is instructed to perform analysis. The generative AI model receives the details of the problem report as input data and searches for related information from a database of past troubles. Data processing involves analysis to identify the cause of the problem, and a list of possible causes is generated as output.

[0187] Step 4:

[0188] server:

[0189] The generative AI model generates an appropriate solution from the analysis results. The input data is the analysis results and past trouble data, and the solution is generated as a data calculation. The output is a specific solution (e.g., "Try turning the power off and on").

[0190] Step 5:

[0191] server:

[0192] The generated solution is notified to the building manager's terminal. The input data is the generated solution, and the output data is a solution notification message sent to the building manager. The server sends a notification to the building manager's terminal.

[0193] Step 6:

[0194] Building manager (terminal):

[0195] The building manager receives the solution notification and takes action according to the proposed solution. The input data is the solution notification sent from the server, and the output data is the result of the action taken by the building manager. The building manager actually operates the equipment (e.g., turning the power off / on).

[0196] Step 7:

[0197] server:

[0198] Receives a report from the building manager and verifies whether the problem has been resolved. The input data is the action taken by the building manager, and the data calculation verifies the resolution of the problem. The output data is the resolution status recorded in the database and a feedback message generated as needed.

[0199] Step 8:

[0200] server:

[0201] If the problem cannot be resolved by the building manager's actions, the server escalates the problem to the equipment manufacturer based on the instructions of the generated AI model. The input data are the building manager's actions and analysis results, and the output data is an escalation notification sent to the equipment manufacturer.

[0202] Step 9:

[0203] Equipment manufacturer (terminal):

[0204] The equipment manufacturer's technician receives the escalation notification, checks the problem, and arranges a site visit or repair schedule as necessary. The input data is the escalation notification, and the output data is the adjusted repair schedule.

[0205] Step 10:

[0206] server:

[0207] The set repair schedule is notified to the building manager and users. The input data is the adjusted repair schedule, and the output data is a schedule notification message sent to the building manager and users. By sending the notification from the server, users and building managers can know the repair schedule in advance.

[0208] (Application example 1)

[0209] 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."

[0210] The present invention aims to quickly and efficiently resolve problems that occur in equipment used in factories and other facilities. It also aims to reduce the burden on managers and engineers and improve productivity. In particular, it aims to improve the speed and accuracy of responses in factory equipment management by automating the entire process from reporting problems to implementing countermeasures and escalation.

[0211] 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.

[0212] In this invention, the server includes a means for receiving problems reported by users, a means for the generative AI to analyze the received problems and generate solutions, a means for notifying the administrator of the solutions, a means for the administrator to confirm the solutions and issue instructions to the equipment, and a means for the equipment to execute the instructed solutions. This allows for a smooth process from reporting problems to generating and executing solutions. It also reduces the burden on administrators and engineers and improves response speed.

[0213] 1. "User" refers to the employee or staff member who reports the issue within the factory or facility.

[0214] 2. "Generative AI" refers to an artificial intelligence system that analyzes incoming problems and generates solutions.

[0215] 3. "Manager" refers to a person in charge of managing equipment within a factory or facility.

[0216] 4. "Means for receiving problems" refers to the methods and tools by which problems reported by users are captured by the system.

[0217] 5. “Means of problem analysis” refers to the methods and tools that generative AI uses to understand the content of a problem and identify its causes.

[0218] 6. "Solution generation means" refers to methods or tools that propose solutions to problems analyzed by generative AI.

[0219] 7. "Solution notification means" refers to the methods and tools used to communicate generated solutions to management.

[0220] 8. "Means for verifying solutions and issuing instructions to equipment" refers to the methods and tools by which managers verify proposed solutions and issue instructions to equipment based on their content.

[0221] 9. "Equipment" refers to machinery and devices used within a factory or facility.

[0222] 10. "Means for implementing directed solutions" refers to the methods and tools by which the facility implements solutions as directed by management.

[0223] 11. "Technical Specialist" refers to a technical expert who will provide additional support if the generated solution does not resolve the issue.

[0224] 12. "Measures for coordinating response scheduling" refers to methods and tools for scheduling technical personnel to conduct on-site visits and follow-up responses.

[0225] 13. "Means for notifying adjusted response schedules" refers to methods and tools for notifying administrators and users of the set response schedules.

[0226] The present invention is a system that automates the process from reporting problems in facility management in factories and other facilities to generating and implementing solutions. The system is composed of a user terminal, an administrator terminal, facilities, and a server equipped with generative AI. Specific embodiments for implementing the present invention are described below.

[0227] User-reported problems

[0228] Users report equipment malfunctions using smartphones or robotics control terminals. The report is sent to the server in the form of text, photos, videos, etc. Consider the example where a user reports that "Machine A is not working" and attaches a photo to the report.

[0229] Server-based problem analysis and solution generation

[0230] The server analyzes the received problem report and generates a solution using generative AI. For example, a solution such as "Please restart machine A" may be generated. This generative AI compares the solution with a past database to select the optimal solution.

[0231] Notify administrator of solution

[0232] The generated solution is sent to the administrator's terminal. The administrator checks the solution and issues instructions to the equipment based on its contents. For example, the administrator sends an instruction to restart a factory robot.

[0233] Implementation of solutions by equipment

[0234] The factory robot follows instructions from the administrator and executes a solution. For example, it restarts machine A and reports the results to the server. If the solution is executed and the problem is solved, the process ends there, but if it is not solved, it moves on to the next step.

[0235] Escalation and Scheduling

[0236] If the generated solution does not resolve the problem, the server notifies a specialist engineer, who then schedules a response and notifies the administrator and user. This allows for a smooth response, such as an on-site visit.

[0237] The hardware used includes smartphones, robotics control terminals, factory robots, and servers, while the software includes smartphone apps for Android (registered trademark) and iOS, robotics control software, generative AI, and a database management system.

[0238] Specific examples

[0239] 1. User device: A factory employee reports on their smartphone that "Machine A is not working" and attaches a photo.

[0240] 2. Server: The generative AI analyzes the problem and generates a solution: "Please restart machine A."

[0241] 3. Administrator terminal: The administrator checks the solution and sends a restart instruction to the factory robot.

[0242] 4. Equipment: The factory robot restarts Machine A and reports the results.

[0243] 5. Server: If the issue persists, escalate to a technician and schedule an on-site visit.

[0244] Prompt Sentence Examples

[0245] Analyze a problem report for a specific machine in the factory and generate and issue the optimal solution. Please use the following information:

[0246] Problem details: {Problem details text}

[0247] Additional information: {URL of photo or video}

[0248] In this way, the system can be used to quickly and efficiently solve facility management problems within a factory.

[0249] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0250] Step 1:

[0251] Entering a Problem Report

[0252] Users report equipment malfunctions using a smartphone app or robotics control terminal. Input includes text (e.g., "Machine A is not working"), photos, and videos. The user enters this information into the app and sends it to the server, which records the received report in a database.

[0253] Step 2:

[0254] Analyzing problems and generating solutions

[0255] The server passes the received report content to the generative AI. The generative AI analyzes the report content (text, photos, videos) and identifies the cause of the problem by comparing it with a database of past troubles. Based on this analysis, the generative AI generates a solution such as "Please restart machine A." The server records the generated solution in a database.

[0256] Step 3:

[0257] Solution Notification

[0258] The server notifies the generated solution to the administrator terminal. The administrator terminal receives the notification and displays the solution. For example, the administrator sees a message saying "Please restart machine A."

[0259] Step 4:

[0260] Instructions for implementing solutions

[0261] The manager checks the received solution and issues instructions to the factory robot based on the content. A reboot instruction is sent from the manager's terminal to the factory robot control system. For example, the manager presses the "reboot" button on the terminal, and the instruction is transmitted to the robot.

[0262] Step 5:

[0263] Implementing the solution

[0264] The factory robot restarts machine A based on instructions from the administrator. The robot actually performs the restart operation and sends the results to the administrator's terminal. The server records the results reported by the robot in a database.

[0265] Step 6:

[0266] Verify the problem is resolved

[0267] The administrator terminal receives the report from the robot and checks whether the problem has been resolved. If it has been resolved, it sends feedback to the server. If it has not been resolved, it proceeds to the next step. The server records this feedback in a database.

[0268] Step 7:

[0269] Escalation and Scheduling

[0270] If the generated solution does not solve the problem, the server notifies the specialist engineer of the problem. The engineer's terminal receives the notification from the server. The engineer adjusts a response schedule, such as a facility visit, and reports it to the server. The server notifies the administrator and user of the adjusted schedule.

[0271] Step 8:

[0272] Schedule Notifications

[0273] Users and administrators receive schedule notifications from the server and prepare for the response. The server records the notification content in a database. This completes the entire process, ensuring a smooth process from reporting the problem to responding to it.

[0274] 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.

[0275] The present invention is a system for analyzing problems reported by users and their emotions at the time, and for solving the problems quickly and accurately. A specific embodiment of the present invention combined with an emotion engine is shown below.

[0276] This system consists of a user terminal equipped with an emotion engine, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI. By using the emotion engine, it is possible to analyze the emotional state of the user when reporting a problem and provide a more effective solution.

[0277] System Operation

[0278] Receiving problem reports and analyzing sentiment

[0279] Terminal (user):

[0280] When a user opens the app or web portal and enters details of a problem, such as "my air conditioner isn't working," into a problem report form, the emotion engine analyzes the user's input and voice (in the case of voice input) to determine emotions, such as frustration, anger, or worry.

[0281] Device:

[0282] The user enters the details of the problem and presses the "Submit" button. The emotion data is sent to the server along with the problem report.

[0283] Analyzing problems and generating solutions

[0284] server:

[0285] The server receives user reports of problems, records their content and emotional data in a database, and simultaneously instructs the generative AI to analyze the problem.

[0286] server:

[0287] The generative AI analyzes the received report and emotional data, and identifies the cause of the problem by comparing it with a database of past problems. When generating solutions based on the analysis results, it takes into account emotional data to suggest high-priority solutions that reduce the user's frustration. For example, a solution might be generated such as, "Try turning the power off and on. If the problem persists, please contact us again."

[0288] Notification and Implementation of Solutions

[0289] server:

[0290] The generated solution is notified to the building manager's terminal, who then checks the proposed solution and attempts to address the equipment.

[0291] Terminal (Building Manager):

[0292] The building manager receives a notification, checks for a solution via the app or web portal, and then turns the air conditioner off and on according to the solution.

[0293] Applications of the Emotion Engine:

[0294] The terminal (building manager) inputs the results of the operation into the server, and generates a report that takes into account the user's emotional state through an emotion engine. For example, a follow-up message such as "We apologize for the inconvenience, but we tried turning the power off and on again, but that did not resolve the problem. We will try another method."

[0295] Escalation and cooperation with equipment manufacturers

[0296] server:

[0297] If the problem persists despite the solutions attempted by the building manager, the generative AI will notify the equipment manufacturer of the situation.

[0298] Terminal (equipment manufacturer):

[0299] An engineer from the equipment manufacturer will review the report and the sentiment data, and schedule a site visit. Once the schedule is decided, it will be notified to the server.

[0300] Schedule Notifications

[0301] server:

[0302] The adjusted repair schedule is then communicated to building managers and users, allowing users to be aware of upcoming repairs and make preparations in advance.

[0303] Specific examples

[0304] Example 1: Air conditioner malfunction

[0305] 1. Terminal (User):

[0306] A user reports in the app that the air conditioner isn't working, expressing extreme frustration.

[0307] The emotion engine analyzes frustration and sends the emotional data to the server.

[0308] 2. Server:

[0309] Receives problem reports and emotional data and instructs generative AI to analyze them.

[0310] The AI ​​generates a solution, such as "Try turning the power off and on. If the problem persists, please contact us again," and notifies the building manager.

[0311] 3. Terminal (Building Manager):

[0312] The building manager reported that he tried turning the air conditioner on and off but was unable to resolve the issue.

[0313] The emotion engine generates follow-up messages to ease user frustration.

[0314] 4. Server:

[0315] Escalate issues to equipment manufacturers and schedule repairs.

[0316] 5. Terminal (equipment manufacturer):

[0317] The technician sets the schedule, and the server notifies the building manager and users of the information.

[0318] In this way, the present invention makes it possible to quickly and efficiently resolve facility problems in buildings and hotels while also taking into consideration the feelings of users.

[0319] The processing flow will be explained below.

[0320] Step 1:

[0321] Device (user): The user opens the app or web portal and enters details of the problem into the problem report form, such as "my air conditioner isn't working." At the same time, the emotion engine analyzes the user's input (text or voice) to identify emotions, such as frustration, anger, or worry.

[0322] Step 2:

[0323] Terminal: The user enters details of the problem and emotional data and presses the "Send" button. The problem report and emotional data are sent to the server.

[0324] Step 3:

[0325] Server: The server receives the defect report and emotion data from the user and records the details in a database. The record contents include details of the reported defect, date and time, emotion data, and attached files.

[0326] Step 4:

[0327] Server: The generative AI retrieves new defect reports from the database, analyzes the report content and emotional data, and identifies the cause of the problem by comparing it with a database of past problems.

[0328] Step 5:

[0329] Server: The generative AI generates solutions based on the analysis results. It takes into account emotional data and suggests high-priority solutions that reduce the user's frustration. For example, it generates a solution such as "Try turning the power off and on. If the problem persists, please contact us again."

[0330] Step 6:

[0331] Server: Notifies the generated solution to the building manager's terminal.

[0332] Step 7:

[0333] Device (Building Manager): The building manager receives a notification, checks the solution via the app or web portal, and turns the air conditioner off / on according to the solution.

[0334] Step 8:

[0335] Terminal (Building Manager): The building manager enters the results of the operation into the app and reports them to the server. If the problem is resolved, this is fed back to the system.

[0336] Step 9:

[0337] Server: Receives reports from building managers and the generative AI determines the next steps. If the problem is not resolved, it escalates to the equipment manufacturer.

[0338] Step 10:

[0339] Server: The generative AI notifies the equipment manufacturer of the details of the problem and the results of the building manager's trial.

[0340] Step 11:

[0341] Terminal (Equipment Manufacturer): The equipment manufacturer's engineer checks the report and emotion data, and arranges the date for the on-site visit. Once the schedule is decided, the engineer contacts the server.

[0342] Step 12:

[0343] Server: Notifies the building manager and users of the adjusted repair schedule.

[0344] Step 13:

[0345] Terminals (building managers and users): Check the repair schedule and make the necessary preparations.

[0346] Step 14:

[0347] Terminal (Building Manager): The building manager sends a follow-up message generated by the emotion engine to the user along with the results of the operation. For example, "We apologize for the inconvenience, but the problem was not resolved after power cycling. We will try another method."

[0348] This series of processing steps allows building and hotel equipment problems to be resolved quickly and efficiently, while also properly managing the emotions of users.

[0349] Example 2

[0350] 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."

[0351] Conventional building and facility management systems handle problems reported by users without considering their emotional state, which has prevented them from fully increasing user satisfaction. Furthermore, they are unable to properly analyze and utilize emotional data, resulting in problems that are not resolved quickly or accurately. Therefore, there is a need for a system that can resolve problems quickly and accurately while taking into account the emotions of users.

[0352] 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.

[0353] In this invention, the server includes a means for receiving a problem reported by a user and analyzing the emotional state of the user at the time, a means for the generative AI model to analyze the received problem and emotional data and generate a solution, and a means for notifying the building manager of the generated solution, which enables the problem to be solved quickly and accurately while taking the user's emotions into consideration.

[0354] "User" means a person who uses the system to report a problem.

[0355] "Emotional state" refers to the emotional state that a user exhibits when reporting a problem, such as frustration, anger, or worry.

[0356] "Generative AI model" refers to an artificial intelligence system that analyzes received problem and emotion data and automatically generates solutions.

[0357] A "building manager" is a person who manages and repairs facilities based on reported problems and generated solutions.

[0358] "Means of notification" refers to a mechanism for transmitting information from the server to building managers and users, and includes, for example, sending messages via email or an application.

[0359] "Equipment manufacturer" refers to the manufacturer of the equipment, and is the party to which you should contact if the problem cannot be resolved.

[0360] "Repair Schedule" means the dates for carrying out repair work on equipment.

[0361] "Means for analysis" refers to the techniques and processes used to analyze received data, identify causes of problems, and generate solutions.

[0362] "Means of receiving" refers to the mechanism for obtaining data from users and building managers.

[0363] "Means for reporting" refers to a system that allows the building manager to communicate the results of attempting the generated solutions to the server.

[0364] "Means of escalation" refers to the method of communicating information to the equipment manufacturer when a specific issue requires a more advanced response.

[0365] This invention uses a system that combines an emotion engine to analyze problems reported by users and their emotions at the time, and solves the problems quickly and accurately. The system is composed of a user terminal equipped with an emotion engine, a building manager terminal, an equipment manufacturer terminal, and a server equipped with a generative AI model.

[0366] System configuration

[0367] The system consists of the following main components:

[0368] 1. User terminal: Enter and send problem reports and emotional data.

[0369] 2. Emotion engine: Analyzes the user's emotional state from their input and voice.

[0370] 3. Server: Analyzes the received data and generates solutions.

[0371] 4. Generative AI models: Analyze problem and emotion data and automatically generate solutions.

[0372] 5. Building manager terminal: Receives solutions and reports implementation results.

[0373] 6. Equipment Manufacturer Terminal: Escalates issues and coordinates repair schedules.

[0374] The role of each element

[0375] User terminal

[0376] The user terminal is provided in the form of an application or web portal, and is used by the user to enter details of the problem into a problem report form. If voice input is possible, it also has an interface for analyzing emotions from the user's voice. For example, when a user reports that "the air conditioner is not working," the emotion engine detects frustration.

[0377] Emotion Engine

[0378] The emotion engine uses natural language processing and speech analysis technologies to extract the user's emotions. For example, it identifies emotions such as frustration, anger, and worry from the input text and sends the analysis results to the server.

[0379] server

[0380] The server records the received report and emotional data in a database and instructs the generative AI to analyze it. Based on the analysis results, it generates a solution that takes the user's emotions into consideration. For example, the generative AI might suggest a solution such as, "Try turning the power off and on. If the problem persists, please contact us again."

[0381] Generative AI Models

[0382] The generative AI model identifies the cause of the problem and generates a solution by comparing it with a huge database of problems. Taking into account emotional measurement data, it is able to provide high-priority solutions that reduce the user's frustration. An example of a specific prompt is, "The air conditioner is not working. Frustration has been detected from the user's input. Please generate a solution that takes into account the emotional data."

[0383] Building manager terminal

[0384] The building manager's terminal receives the solution notified by the server, attempts to deal with the equipment, reports the results to the server, and generates a follow-up message if necessary.

[0385] Equipment manufacturer terminal

[0386] The equipment manufacturer's terminal receives notification of problem escalation and adjusts the repair schedule, which allows for efficient scheduling of on-site visits.

[0387] Specific scenarios

[0388] For example, when a user reports that the air conditioner is not working, the emotion engine detects the user's frustration. This data is received by the server, and the generative AI generates a solution such as "Please try turning the power off and on. If the problem persists, please contact us again." The building manager is then notified, and if the problem is not resolved, it is escalated to the equipment manufacturer. The equipment manufacturer adjusts the repair schedule and notifies the user.

[0389] In this way, the present invention provides a system that takes into account the user's feelings and solves problems quickly and accurately.

[0390] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0391] Step 1:

[0392] User-entered problem report

[0393] Terminal (user):

[0394] A user opens an application or web portal on their device and enters details of the problem into a problem report form. The input can be in text or voice format, for example, "The air conditioner is not working." The input text or voice is then saved on the device (output).

[0395] Step 2:

[0396] Emotion analysis using an emotion engine

[0397] Terminal (user):

[0398] The emotion engine analyzes input text and voice to extract the user's emotional state. Using natural language processing technology, emotions such as "I feel very frustrated" are analyzed (input). As a result of the analysis, emotional data is generated and stored on the device (output).

[0399] Step 3:

[0400] Receiving report content and emotion data on the server

[0401] server:

[0402] The system receives the defect report and emotion data sent from the device. The problem details and emotion data entered by the user are recorded in the server's database (input). This makes the report details and emotion data stored in the database available on the server side (output).

[0403] Step 4:

[0404] Analyzing problems and generating solutions using generative AI

[0405] server:

[0406] Based on the received data, the server instructs the generative AI to analyze the problem. The generative AI compares the report with a database of past problems to identify the cause of the problem (input). Based on the analysis results, a specific solution is generated (output), such as "Try turning the power off and on. If the problem persists, please contact us again."

[0407] Step 5:

[0408] Server notification of solution

[0409] server:

[0410] The generated solution is notified to the building manager's terminal. The generated solution and emotion data are sent from the server to the building manager's terminal (input). A notification is displayed on the building manager's terminal so that the building manager can check it (output).

[0411] Step 6:

[0412] Building manager implements solutions and reports results

[0413] Terminal (Building Manager):

[0414] The building manager receives the notification and checks for a solution via the app or web portal. The building manager then performs the power off / on operation on the air conditioner (input). The device then reports the results of the operation to the server, sending a report such as "I tried the operation but it did not resolve the problem" (output).

[0415] Step 7:

[0416] Server-driven escalation and repair schedule notifications

[0417] server:

[0418] If the problem persists despite the attempted solutions, the generative AI escalates the issue to the equipment manufacturer (input). An engineer at the equipment manufacturer reviews the problem report and emotion data, arranges a date for an on-site visit, and notifies the server of the schedule (output).

[0419] Step 8:

[0420] Repair schedule notification

[0421] server:

[0422] The adjusted repair schedule is notified to the building manager and users (input), allowing users and building managers to be aware of the planned repairs in advance and make preparations (output).

[0423] The above are the specific processing steps of the system. This is a flow that includes the input and output of data, as well as the specific operations performed at each step.

[0424] (Application example 2)

[0425] 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."

[0426] While conventional troubleshooting systems were able to receive and analyze problems reported by users, they were unable to generate solutions that took into account the user's emotional state. As a result, it was difficult to alleviate users' frustration, especially in high-stress environments. Furthermore, when the problem persisted even after factory managers implemented solutions, it was often difficult to provide appropriate follow-up or coordinate smoothly with the equipment manufacturer.

[0427] 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 a means for receiving a problem reported by a user, a means for a generative AI to analyze the received problem and generate a solution, a means for using an emotion engine to analyze the user's emotional state, and a means for notifying the factory manager of the solution. This enables a prompt and accurate solution to be provided while taking the user's emotional state into consideration. Furthermore, by providing a means for the factory manager to try the generated solution and report the results, and a means for determining the next step based on the reported results and emotion data, the efficiency of problem solving is improved. Furthermore, by providing a means for notifying the manufacturing equipment manufacturer of the problem if the generated solution does not solve the problem, a means for coordinating a repair schedule with the manufacturing equipment manufacturer, and a means for notifying the factory manager and the user of the adjusted repair schedule, follow-up for problem resolution can be carried out smoothly.

[0428] "User" means any person or entity that uses the System to report a Problem.

[0429] A "means for receiving problems" is an interface or device for receiving problems reported by users.

[0430] "Generative AI" is a system or algorithm that uses artificial intelligence techniques to analyze incoming problems and generate optimal solutions.

[0431] An "emotion engine" is software or hardware that analyzes emotions from a user's input data (text or voice) and extracts their emotional state.

[0432] A "factory manager" is an employee or staff member in charge of managing production lines and equipment within a factory.

[0433] "Means for notification" refers to the communications infrastructure or devices used to transmit generated solutions and status information to designated recipients.

[0434] The "means for analyzing the problem" refers to a processing device or software for analyzing the content of the received problem.

[0435] A "means for generating solutions" is a system or program that has the function of proposing appropriate solutions based on the analysis results.

[0436] "Emotional state" refers to the psychological state, such as frustration, anger, or worry, that a user feels when reporting a problem.

[0437] A "next step decision method" is a system or algorithm that determines the next action to take based on the reported solution results and sentiment data.

[0438] A "manufacturing equipment manufacturer" is a company that designs, manufactures, sells, and maintains manufacturing equipment used in factories.

[0439] "Means for coordinating repair schedules" means the systems and procedures for scheduling equipment repairs and inspections and communicating with relevant parties.

[0440] "Means of notifying users" are the means of communication or devices used to communicate schedules and resolution results to users.

[0441] This invention includes a troubleshooting support system installed in a robot operating on a factory production line. The specific configuration and operation will be described below.

[0442] First, a factory worker who will be the user uses a device such as a smartphone or tablet to report a problem with a robot on the production line. For example, a problem might be that the robot's arm has stopped mid-operation. Reports can be made using text input or voice input, and the emotion engine analyzes the user's emotional state (frustration, anger, worry, etc.) from this input data.

[0443] The emotion engine uses natural language processing technology to analyze input text and voice data and extract the user's emotional state. This emotional data is sent to the server along with the problem report data and recorded in a database.

[0444] The server analyzes the problem using a generative AI model based on the received problem report and emotional data. The generative AI model compares the results with a database of past problems and generates the optimal solution. The model also takes into account the emotional data and proposes high-priority solutions that reduce user frustration.

[0445] The generated solution is sent to the factory manager's device via the notification system. The factory manager receives the notification, checks the solution through an application or web portal, and implements it. For example, specific actions such as "Please restart the power supply of the arm. Also, please check the contact sensor" are displayed.

[0446] When the factory manager reports the results of the solution attempt to the server, the emotion engine also generates a follow-up message based on the user's emotional state, such as "We apologize for the inconvenience, but we tried cycling the power but it did not resolve the problem. We will try another method."

[0447] If the generated solution does not resolve the problem, the server automatically escalates the issue to the manufacturing equipment manufacturer. The manufacturer's technicians review the report and sentiment data and schedule an on-site visit. The adjusted repair schedule is then notified to the factory manager and users via the server.

[0448] This makes it possible to quickly and efficiently resolve problems with manufacturing robots in factories, and to provide courteous support that takes into account the emotional state of the user.

[0449] Prompt Sentence Examples

[0450] "Analyze problem report text entered from a smartphone, extract sentiment data, and generate solutions based on generative AI models."

[0451] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0452] Step 1:

[0453] Users use a smartphone or tablet to report a problem with a robot on a manufacturing line. They can enter text or voice input, and the input includes details of the problem, such as "The robot's arm is stuck mid-way." This is the input data. The output is the problem report data.

[0454] Step 2:

[0455] The device receives the problem report data and performs emotion analysis using an emotion engine. The emotion engine uses natural language processing technology to extract the user's emotional state (frustration, anger, worry, etc.) from the text and voice data. The input data is text and voice input, and the output data is the analysis result including the emotional state.

[0456] Step 3:

[0457] The device sends the analyzed emotion data and problem report data to the server, which records these data in a database. In this step, the input data is converted into a database format and processed for storage. As an output, confirmation information of the recorded data is generated.

[0458] Step 4:

[0459] The server analyzes the problem using a generative AI model based on the received problem report and emotion data. The generative AI model compares the results with a database of past problems and generates the optimal solution. Here, the problem is analyzed using a matching algorithm with the problem database. The input data is the problem report and emotion data, and the output is the generated solution.

[0460] Step 5:

[0461] The server notifies the generated solution to the factory manager's terminal through the notification system. The factory manager checks and implements the solution through an application or web portal. In this step, the solution is used as input data and a notification message is generated as output data.

[0462] Step 6:

[0463] The factory manager attempts the generated solution and reports the results to the server. The terminal also generates a follow-up message based on the user's emotional state using an emotion engine. The input data is the trial result data and emotion data, and the output data is the follow-up message.

[0464] Step 7:

[0465] If the generated solution does not resolve the problem, the server automatically escalates the problem to the manufacturing equipment manufacturer. The server checks the report content and sentiment data and schedules an on-site visit. The input data is the unresolved problem report, and the output data is the escalation notification.

[0466] Step 8:

[0467] The adjusted repair schedule is then sent back to the server to be notified to the factory manager and user terminals. The server processes the schedule information and generates a notification message in an appropriate format. The input data is the repair schedule, and the output data is the notification message.

[0468] 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.

[0469] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0470] 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.

[0471] [Second embodiment]

[0472] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0473] 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.

[0474] 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).

[0475] 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.

[0476] 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.

[0477] 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).

[0478] 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. 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.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] In the smart glasses 214, 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.

[0483] 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."

[0484] The present invention relates to a system for quickly and efficiently resolving problems when malfunctions occur in facilities of buildings, hotels, etc. Specific embodiments for carrying out the present invention are described below.

[0485] This system provides a platform for users, building managers, and equipment manufacturers to efficiently handle everything from reporting problems to resolving them. Its main components are a user terminal, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI.

[0486] System Operation

[0487] Receiving problem reports

[0488] Terminal (user):

[0489] If a user experiences a problem with a building or hotel facility, they can report the issue through a smartphone app or web portal. For example, if the air conditioner in their office isn't working, they can enter a message like "The air conditioner isn't working" into the app and attach photos and videos to send it.

[0490] server:

[0491] The server receives reports from users, records the details in a database, and simultaneously instructs the generative AI to analyze the problem.

[0492] Analyzing problems and generating solutions

[0493] server:

[0494] The generative AI analyzes the received report and identifies the cause of the problem by comparing it with a database of past problems. For example, if a problem with an air conditioner is reported, the AI ​​will generate a basic solution such as "Try turning the power off and on."

[0495] Notification and Implementation of Solutions

[0496] server:

[0497] The generated solution is sent to the building manager's terminal, who then checks the proposed solution and attempts to address the problem.

[0498] Terminal (Building Manager):

[0499] The building manager reports the results of his attempts to turn the air conditioner on and off to the server. If the problem is resolved, this is fed back to the system.

[0500] Escalation and cooperation with equipment manufacturers

[0501] server:

[0502] If the problem persists despite the solutions attempted by the building manager, the generative AI will notify the equipment manufacturer of the situation.

[0503] Terminal (equipment manufacturer):

[0504] An engineer from the equipment manufacturer will confirm the problem and, if necessary, schedule an on-site visit.

[0505] Schedule Notifications

[0506] server:

[0507] The set repair schedule is notified to the building manager and users, allowing users to know in advance about the planned repairs and make preparations.

[0508] Specific examples

[0509] Example 1: Air conditioner malfunction

[0510] 1. Terminal (User):

[0511] A user reported through the app that the air conditioner was not working.

[0512] Attach photos and submit a report.

[0513] 2. Server:

[0514] Receives problem reports and instructs generative AI to analyze them.

[0515] The AI ​​generates a solution such as "Try turning the power off and on" and notifies the building manager.

[0516] 3. Terminal (Building Manager):

[0517] The building manager attempts to turn the air conditioner on and off.

[0518] After the operation, the server reported that the problem persisted.

[0519] 4. Server:

[0520] Escalate issues to equipment manufacturers and schedule repairs.

[0521] 5. Terminal (equipment manufacturer):

[0522] The technician sets the schedule, and the server notifies the building manager and users of the information.

[0523] In this way, the present invention makes it possible to quickly and efficiently resolve equipment problems in buildings and hotels.

[0524] The processing flow will be explained below.

[0525] Step 1:

[0526] Device (user): The user opens the app or web portal and fills in the problem report form with details of the problem, such as "The air conditioner is not working." If necessary, they attach photos and videos.

[0527] Step 2:

[0528] Terminal: The user enters the details of the problem and presses the "Send" button. The problem report is sent to the server.

[0529] Step 3:

[0530] Server: The server receives the problem report from the user and records the details in the database, including the details of the reported problem, the date and time, and any attached files.

[0531] Step 4:

[0532] Server: The generative AI retrieves new defect reports from the database and analyzes the problem by comparing them with past trouble data.

[0533] Step 5:

[0534] Server: The generative AI generates a solution based on the analysis results. For example, it generates a solution such as "Try turning the power off and on."

[0535] Step 6:

[0536] Server: Notifies the generated solution to the building manager's terminal.

[0537] Step 7:

[0538] Device (Building Manager): The building manager receives a notification, checks the solution via the app or web portal, and turns the air conditioner off / on according to the solution.

[0539] Step 8:

[0540] Device (Building Manager): The building manager enters the results of the operation into the app and reports them to the server. For example, they may report, "I tried turning the power off and on, but the problem persists."

[0541] Step 9:

[0542] Server: Receives reports from building managers and the generative AI determines the next steps. If the problem is not resolved, it must be escalated to the equipment manufacturer.

[0543] Step 10:

[0544] Server: The generative AI notifies the equipment manufacturer of the details of the problem and the results of the building manager's trial.

[0545] Step 11:

[0546] Terminal (equipment manufacturer): The equipment manufacturer's engineer checks the report and arranges the date for the on-site visit. Once the schedule is decided, he / she contacts the server.

[0547] Step 12:

[0548] Server: Notifies the building manager and users of the adjusted repair schedule.

[0549] Step 13:

[0550] Terminals (building managers and users): Check the repair schedule and make the necessary preparations.

[0551] This series of processing steps allows building and hotel equipment problems to be resolved quickly and efficiently.

[0552] Example 1

[0553] 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."

[0554] In large facilities such as buildings and hotels, when equipment malfunctions occur, efficient information sharing and problem resolution among users, building managers, and equipment manufacturers is essential for rapid and appropriate response. However, currently, the process from reporting a problem to providing notification of a solution, responding, and providing feedback on the results is often done manually, which takes time and effort. Furthermore, if an appropriate solution is not adopted, the problem may be prolonged, resulting in further costs and a decline in reliability.

[0555] 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.

[0556] In this invention, the server includes means for receiving problems reported by users, means for the generative AI to analyze the received problems and generate solutions, means for notifying the building manager of the solutions, means for registering the problem reports in a database, means for the generative AI to identify the cause of the problem, and means for the generative AI to refer to a database of past troubles. This makes it possible to quickly and appropriately solve equipment malfunctions in buildings and hotels.

[0557] "User" refers to the individual or entity who discovers and reports a problem while using the Equipment.

[0558] "Means for receiving problems" refers to the function of receiving data on problems reported by users regarding equipment.

[0559] "Generative AI" refers to artificial intelligence that analyzes received data and automatically generates appropriate solutions.

[0560] "Means of analyzing problems and generating solutions" refers to the function of using generative AI to analyze the causes of problems and create solutions by referring to past data.

[0561] "Building manager" refers to the individual or organization responsible for managing the facilities of a building or facility and for implementing the solutions communicated by the generative AI.

[0562] "Means for notifying solutions" refers to a function for communicating the generated solutions to the building manager.

[0563] "Means for registering in a database" refers to the function of saving problems reported by users in a database with a unique ID.

[0564] "Means for identifying the cause of the problem" refers to the function of the generative AI to refer to past trouble data to identify the cause of the reported problem.

[0565] A "past trouble database" refers to a collection of information that stores detailed records of troubles that have occurred in the past and the solutions to those troubles.

[0566] "Equipment manufacturer" refers to the company or organization that manufactures the equipment and provides technical support.

[0567] "Means to adjust repair schedules" refers to the function of setting specific repair dates and times with the equipment manufacturer to resolve the problem.

[0568] "Means for notifying repair schedules" refers to a function for communicating the adjusted repair schedule to building managers and users.

[0569] The present invention provides a system for quickly and appropriately responding to equipment malfunctions in large facilities such as buildings and hotels. Specific embodiments for carrying out the present invention are described below.

[0570] System configuration

[0571] This system provides a platform for users, building managers, and equipment manufacturers to efficiently handle everything from reporting problems to resolving them. Its main components are a user terminal, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI.

[0572] Hardware and software used

[0573] User device: A device such as a smartphone, tablet, or computer.

[0574] Building manager's terminal: Devices such as PCs, tablets, and smartphones.

[0575] Equipment manufacturer terminal: Devices such as computers, tablets, and smartphones.

[0576] Server: A high-performance computer server equipped with generative AI that analyzes problems and generates solutions.

[0577] System operation explanation

[0578] Accepting problem reports

[0579] Terminal (user)

[0580] If a user experiences a problem with a building or hotel facility, they can report the problem through a smartphone app or web portal. For example, to report a problem like "The air conditioner in my office isn't working," they simply type "The air conditioner isn't working" into the app and attach photos or videos as needed. When the user presses the "Submit" button, the report is sent to the server.

[0581] Problem Report Database Registration

[0582] server

[0583] The server receives problem reports sent by users and records their contents in a database. At this time, details of the reported problem and attached photos and videos are saved together. A unique ID is also assigned to the report contents for management.

[0584] Problem analysis using generative AI models

[0585] server

[0586] Based on problem reports registered in the database, the generative AI model is instructed to perform an analysis. The generative AI model refers to past trouble data and performs an analysis to identify the cause of the problem. For example, in response to a report that "the air conditioner is not working," it will list possible causes, such as a power failure or a clogged filter.

[0587] Solution Generation

[0588] server

[0589] The generative AI model generates optimal solutions based on the analysis results. For example, the AI ​​might suggest basic solutions such as "Try turning the power off and on." If necessary, it also includes detailed instructions and precautions.

[0590] Solution Notification

[0591] server

[0592] The generated solution is sent to the building manager's terminal, and the notification includes a summary of the report along with the details of the solution.

[0593] Building manager's response

[0594] Terminal (Building Manager)

[0595] The building manager receives the notification and takes action according to the proposed solution, for example, turning the air conditioner off and on, and then reports the result to the server.

[0596] Reporting results and feedback

[0597] server

[0598] Receive reports from building managers to see if the problem has been resolved. If the problem has been resolved, record the information in a database and notify the user.

[0599] Escalation and cooperation with equipment manufacturers

[0600] server

[0601] If the problem cannot be resolved by the building manager, the generative AI model escalates the issue to the equipment manufacturer, who sends a detailed report and dispatches a technician to handle the issue as needed.

[0602] Response by equipment manufacturers

[0603] Terminal (equipment manufacturer)

[0604] An engineer from the equipment manufacturer will identify the problem and schedule a site visit or repair. This information is sent to the server.

[0605] Repair schedule notification

[0606] server

[0607] The set repair schedule is notified to the building manager and users, allowing users to know about the planned repairs in advance and make preparations.

[0608] Specific examples

[0609] For example, if a problem is reported that "the air conditioner in the office is not working," the following actions will be taken:

[0610] 1. Terminal (User)

[0611] A user reports "the air conditioner is not working" in the app and sends it with a photo attached.

[0612] 2. Server

[0613] Receives problem reports, stores them in a database, and directs the generative AI model to analyze them.

[0614] 3. Server

[0615] The AI ​​generates a solution such as "Try turning the power off and on" and notifies the building manager.

[0616] 4. Terminal (Building Manager)

[0617] The building manager attempts to operate the power supply, but the problem persists, so he reports the results to the server.

[0618] 5. Server

[0619] Escalate the issue to the equipment manufacturer and schedule a repair response.

[0620] 6. Terminal (equipment manufacturer)

[0621] The technician sets the schedule and the server notifies the building manager and users.

[0622] This makes it possible for the system of the present invention to quickly and efficiently resolve equipment problems in buildings and hotels.

[0623] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0624] Step 1:

[0625] User (Device):

[0626] Users report equipment problems through a smartphone app or web portal. They enter specific prompt text (e.g., "The air conditioner isn't working") into the app and attach photos and videos as needed. A problem report (text, photos, and videos) is generated based on the input data. When the user presses the "Submit" button, the entered problem report is sent to the server.

[0627] Step 2:

[0628] server:

[0629] The server records the problem reports received from users in a database. At this time, it receives the report content data (text, photos, videos) and records it with a unique ID. The input data is the problem report data from the user, and the output is the problem report stored in the database.

[0630] Step 3:

[0631] server:

[0632] Based on the problem reports registered in the database, the generative AI model is instructed to perform analysis. The generative AI model receives the details of the problem report as input data and searches for related information from a database of past troubles. Data processing involves analysis to identify the cause of the problem, and a list of possible causes is generated as output.

[0633] Step 4:

[0634] server:

[0635] The generative AI model generates an appropriate solution from the analysis results. The input data is the analysis results and past trouble data, and the solution is generated as a data calculation. The output is a specific solution (e.g., "Try turning the power off and on").

[0636] Step 5:

[0637] server:

[0638] The generated solution is notified to the building manager's terminal. The input data is the generated solution, and the output data is a solution notification message sent to the building manager. The server sends a notification to the building manager's terminal.

[0639] Step 6:

[0640] Building manager (terminal):

[0641] The building manager receives the solution notification and takes action according to the proposed solution. The input data is the solution notification sent from the server, and the output data is the result of the action taken by the building manager. The building manager actually operates the equipment (e.g., turning the power off / on).

[0642] Step 7:

[0643] server:

[0644] Receives a report from the building manager and verifies whether the problem has been resolved. The input data is the action taken by the building manager, and the data calculation verifies the resolution of the problem. The output data is the resolution status recorded in the database and a feedback message generated as needed.

[0645] Step 8:

[0646] server:

[0647] If the problem cannot be resolved by the building manager's actions, the server escalates the problem to the equipment manufacturer based on the instructions of the generated AI model. The input data are the building manager's actions and analysis results, and the output data is an escalation notification sent to the equipment manufacturer.

[0648] Step 9:

[0649] Equipment manufacturer (terminal):

[0650] The equipment manufacturer's technician receives the escalation notification, checks the problem, and arranges a site visit or repair schedule as necessary. The input data is the escalation notification, and the output data is the adjusted repair schedule.

[0651] Step 10:

[0652] server:

[0653] The set repair schedule is notified to the building manager and users. The input data is the adjusted repair schedule, and the output data is a schedule notification message sent to the building manager and users. By sending the notification from the server, users and building managers can know the repair schedule in advance.

[0654] (Application example 1)

[0655] 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."

[0656] The present invention aims to quickly and efficiently resolve problems that occur in equipment used in factories and other facilities. It also aims to reduce the burden on managers and engineers and improve productivity. In particular, it aims to improve the speed and accuracy of responses in factory equipment management by automating the entire process from reporting problems to implementing countermeasures and escalation.

[0657] 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.

[0658] In this invention, the server includes a means for receiving problems reported by users, a means for the generative AI to analyze the received problems and generate solutions, a means for notifying the administrator of the solutions, a means for the administrator to confirm the solutions and issue instructions to the equipment, and a means for the equipment to execute the instructed solutions. This allows for a smooth process from reporting problems to generating and executing solutions. It also reduces the burden on administrators and engineers and improves response speed.

[0659] 1. "User" refers to the employee or staff member who reports the issue within the factory or facility.

[0660] 2. "Generative AI" refers to an artificial intelligence system that analyzes incoming problems and generates solutions.

[0661] 3. "Manager" refers to a person in charge of managing equipment within a factory or facility.

[0662] 4. "Means for receiving problems" refers to the methods and tools by which problems reported by users are captured by the system.

[0663] 5. “Means of problem analysis” refers to the methods and tools that generative AI uses to understand the content of a problem and identify its causes.

[0664] 6. "Solution generation means" refers to methods or tools that propose solutions to problems analyzed by generative AI.

[0665] 7. "Solution notification means" refers to the methods and tools used to communicate generated solutions to management.

[0666] 8. "Means for verifying solutions and issuing instructions to equipment" refers to the methods and tools by which managers verify proposed solutions and issue instructions to equipment based on their content.

[0667] 9. "Equipment" refers to machinery and devices used within a factory or facility.

[0668] 10. "Means for implementing directed solutions" refers to the methods and tools by which the facility implements solutions as directed by management.

[0669] 11. "Technical Specialist" refers to a technical expert who will provide additional support if the generated solution does not resolve the issue.

[0670] 12. "Measures for coordinating response scheduling" refers to methods and tools for scheduling technical personnel to conduct on-site visits and follow-up responses.

[0671] 13. "Means for notifying adjusted response schedules" refers to methods and tools for notifying administrators and users of the set response schedules.

[0672] The present invention is a system that automates the process from reporting problems in facility management in factories and other facilities to generating and implementing solutions. The system is composed of a user terminal, an administrator terminal, facilities, and a server equipped with generative AI. Specific embodiments for implementing the present invention are described below.

[0673] User-reported problems

[0674] Users report equipment malfunctions using smartphones or robotics control terminals. The report is sent to the server in the form of text, photos, videos, etc. Consider the example where a user reports that "Machine A is not working" and attaches a photo to the report.

[0675] Server-based problem analysis and solution generation

[0676] The server analyzes the received problem report and generates a solution using generative AI. For example, a solution such as "Please restart machine A" may be generated. This generative AI compares the solution with a past database to select the optimal solution.

[0677] Notify administrator of solution

[0678] The generated solution is sent to the administrator's terminal. The administrator checks the solution and issues instructions to the equipment based on its contents. For example, the administrator sends an instruction to restart a factory robot.

[0679] Implementation of solutions by equipment

[0680] The factory robot follows instructions from the administrator and executes a solution. For example, it restarts machine A and reports the results to the server. If the solution is executed and the problem is solved, the process ends there, but if it is not solved, it moves on to the next step.

[0681] Escalation and Scheduling

[0682] If the generated solution does not resolve the problem, the server notifies a specialist engineer, who then schedules a response and notifies the administrator and user. This allows for a smooth response, such as an on-site visit.

[0683] The hardware used includes smartphones, robotics control terminals, factory robots, and servers, while the software includes smartphone apps for Android / iOS, robotics control software, generative AI, and a database management system.

[0684] Specific examples

[0685] 1. User device: A factory employee reports on their smartphone that "Machine A is not working" and attaches a photo.

[0686] 2. Server: The generative AI analyzes the problem and generates a solution: "Please restart machine A."

[0687] 3. Administrator terminal: The administrator checks the solution and sends a restart instruction to the factory robot.

[0688] 4. Equipment: The factory robot restarts Machine A and reports the results.

[0689] 5. Server: If the issue persists, escalate to a technician and schedule an on-site visit.

[0690] Prompt Sentence Examples

[0691] Analyze a problem report for a specific machine in the factory and generate and issue the optimal solution. Please use the following information:

[0692] Problem details: {Problem details text}

[0693] Additional information: {URL of photo or video}

[0694] In this way, the system can be used to quickly and efficiently solve facility management problems within a factory.

[0695] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0696] Step 1:

[0697] Entering a Problem Report

[0698] Users report equipment malfunctions using a smartphone app or robotics control terminal. Input includes text (e.g., "Machine A is not working"), photos, and videos. The user enters this information into the app and sends it to the server, which records the received report in a database.

[0699] Step 2:

[0700] Analyzing problems and generating solutions

[0701] The server passes the received report content to the generative AI. The generative AI analyzes the report content (text, photos, videos) and identifies the cause of the problem by comparing it with a database of past troubles. Based on this analysis, the generative AI generates a solution such as "Please restart machine A." The server records the generated solution in a database.

[0702] Step 3:

[0703] Solution Notification

[0704] The server notifies the generated solution to the administrator terminal. The administrator terminal receives the notification and displays the solution. For example, the administrator sees a message saying "Please restart machine A."

[0705] Step 4:

[0706] Instructions for implementing solutions

[0707] The manager checks the received solution and issues instructions to the factory robot based on the content. A reboot instruction is sent from the manager's terminal to the factory robot control system. For example, the manager presses the "reboot" button on the terminal, and the instruction is transmitted to the robot.

[0708] Step 5:

[0709] Implementing the solution

[0710] The factory robot restarts machine A based on instructions from the administrator. The robot actually performs the restart operation and sends the results to the administrator's terminal. The server records the results reported by the robot in a database.

[0711] Step 6:

[0712] Verify the problem is resolved

[0713] The administrator terminal receives the report from the robot and checks whether the problem has been resolved. If it has been resolved, it sends feedback to the server. If it has not been resolved, it proceeds to the next step. The server records this feedback in a database.

[0714] Step 7:

[0715] Escalation and Scheduling

[0716] If the generated solution does not solve the problem, the server notifies the specialist engineer of the problem. The engineer's terminal receives the notification from the server. The engineer adjusts a response schedule, such as a facility visit, and reports it to the server. The server notifies the administrator and user of the adjusted schedule.

[0717] Step 8:

[0718] Schedule Notifications

[0719] Users and administrators receive schedule notifications from the server and prepare for the response. The server records the notification content in a database. This completes the entire process, ensuring a smooth process from reporting the problem to responding to it.

[0720] 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.

[0721] The present invention is a system for analyzing problems reported by users and their emotions at the time, and for solving the problems quickly and accurately. A specific embodiment of the present invention combined with an emotion engine is shown below.

[0722] This system consists of a user terminal equipped with an emotion engine, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI. By using the emotion engine, it is possible to analyze the emotional state of the user when reporting a problem and provide a more effective solution.

[0723] System Operation

[0724] Receiving problem reports and analyzing sentiment

[0725] Terminal (user):

[0726] When a user opens the app or web portal and enters details of a problem, such as "my air conditioner isn't working," into a problem report form, the emotion engine analyzes the user's input and voice (in the case of voice input) to determine emotions, such as frustration, anger, or worry.

[0727] Device:

[0728] The user enters the details of the problem and presses the "Submit" button. The emotion data is sent to the server along with the problem report.

[0729] Analyzing problems and generating solutions

[0730] server:

[0731] The server receives user reports of problems, records their content and emotional data in a database, and simultaneously instructs the generative AI to analyze the problem.

[0732] server:

[0733] The generative AI analyzes the received report and emotional data, and identifies the cause of the problem by comparing it with a database of past problems. When generating solutions based on the analysis results, it takes into account emotional data to suggest high-priority solutions that reduce the user's frustration. For example, a solution might be generated such as, "Try turning the power off and on. If the problem persists, please contact us again."

[0734] Notification and Implementation of Solutions

[0735] server:

[0736] The generated solution is notified to the building manager's terminal, who then checks the proposed solution and attempts to address the equipment.

[0737] Terminal (Building Manager):

[0738] The building manager receives a notification, checks for a solution via the app or web portal, and then turns the air conditioner off and on according to the solution.

[0739] Applications of the Emotion Engine:

[0740] The terminal (building manager) inputs the results of the operation into the server, and generates a report that takes into account the user's emotional state through an emotion engine. For example, a follow-up message such as "We apologize for the inconvenience, but we tried turning the power off and on again, but that did not resolve the problem. We will try another method."

[0741] Escalation and cooperation with equipment manufacturers

[0742] server:

[0743] If the problem persists despite the solutions attempted by the building manager, the generative AI will notify the equipment manufacturer of the situation.

[0744] Terminal (equipment manufacturer):

[0745] An engineer from the equipment manufacturer will review the report and the sentiment data, and schedule a site visit. Once the schedule is decided, it will be notified to the server.

[0746] Schedule Notifications

[0747] server:

[0748] The adjusted repair schedule is then communicated to building managers and users, allowing users to be aware of upcoming repairs and make preparations in advance.

[0749] Specific examples

[0750] Example 1: Air conditioner malfunction

[0751] 1. Terminal (User):

[0752] A user reports in the app that the air conditioner isn't working, expressing extreme frustration.

[0753] The emotion engine analyzes frustration and sends the emotional data to the server.

[0754] 2. Server:

[0755] Receives problem reports and emotional data and instructs generative AI to analyze them.

[0756] The AI ​​generates a solution, such as "Try turning the power off and on. If the problem persists, please contact us again," and notifies the building manager.

[0757] 3. Terminal (Building Manager):

[0758] The building manager reported that he tried turning the air conditioner on and off but was unable to resolve the issue.

[0759] The emotion engine generates follow-up messages to ease user frustration.

[0760] 4. Server:

[0761] Escalate issues to equipment manufacturers and schedule repairs.

[0762] 5. Terminal (equipment manufacturer):

[0763] The technician sets the schedule, and the server notifies the building manager and users of the information.

[0764] In this way, the present invention makes it possible to quickly and efficiently resolve facility problems in buildings and hotels while also taking into consideration the feelings of users.

[0765] The processing flow will be explained below.

[0766] Step 1:

[0767] Device (user): The user opens the app or web portal and enters details of the problem into the problem report form, such as "my air conditioner isn't working." At the same time, the emotion engine analyzes the user's input (text or voice) to identify emotions, such as frustration, anger, or worry.

[0768] Step 2:

[0769] Terminal: The user enters details of the problem and emotional data and presses the "Send" button. The problem report and emotional data are sent to the server.

[0770] Step 3:

[0771] Server: The server receives the defect report and emotion data from the user and records the details in a database. The record contents include details of the reported defect, date and time, emotion data, and attached files.

[0772] Step 4:

[0773] Server: The generative AI retrieves new defect reports from the database, analyzes the report content and emotional data, and identifies the cause of the problem by comparing it with a database of past problems.

[0774] Step 5:

[0775] Server: The generative AI generates solutions based on the analysis results. It takes into account emotional data and suggests high-priority solutions that reduce the user's frustration. For example, it generates a solution such as "Try turning the power off and on. If the problem persists, please contact us again."

[0776] Step 6:

[0777] Server: Notifies the generated solution to the building manager's terminal.

[0778] Step 7:

[0779] Device (Building Manager): The building manager receives a notification, checks the solution via the app or web portal, and turns the air conditioner off / on according to the solution.

[0780] Step 8:

[0781] Terminal (Building Manager): The building manager enters the results of the operation into the app and reports them to the server. If the problem is resolved, this is fed back to the system.

[0782] Step 9:

[0783] Server: Receives reports from building managers and the generative AI determines the next steps. If the problem is not resolved, it escalates to the equipment manufacturer.

[0784] Step 10:

[0785] Server: The generative AI notifies the equipment manufacturer of the details of the problem and the results of the building manager's trial.

[0786] Step 11:

[0787] Terminal (Equipment Manufacturer): The equipment manufacturer's engineer checks the report and emotion data, and arranges the date for the on-site visit. Once the schedule is decided, the engineer contacts the server.

[0788] Step 12:

[0789] Server: Notifies the building manager and users of the adjusted repair schedule.

[0790] Step 13:

[0791] Terminals (building managers and users): Check the repair schedule and make the necessary preparations.

[0792] Step 14:

[0793] Terminal (Building Manager): The building manager sends a follow-up message generated by the emotion engine to the user along with the results of the operation. For example, "We apologize for the inconvenience, but the problem was not resolved after power cycling. We will try another method."

[0794] This series of processing steps allows building and hotel equipment problems to be resolved quickly and efficiently, while also properly managing the emotions of users.

[0795] Example 2

[0796] 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."

[0797] Conventional building and facility management systems handle problems reported by users without considering their emotional state, which has prevented them from fully increasing user satisfaction. Furthermore, they are unable to properly analyze and utilize emotional data, resulting in problems that are not resolved quickly or accurately. Therefore, there is a need for a system that can resolve problems quickly and accurately while taking into account the emotions of users.

[0798] 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.

[0799] In this invention, the server includes a means for receiving a problem reported by a user and analyzing the emotional state of the user at the time, a means for the generative AI model to analyze the received problem and emotional data and generate a solution, and a means for notifying the building manager of the generated solution, which enables the problem to be solved quickly and accurately while taking the user's emotions into consideration.

[0800] "User" means a person who uses the system to report a problem.

[0801] "Emotional state" refers to the emotional state that a user exhibits when reporting a problem, such as frustration, anger, or worry.

[0802] "Generative AI model" refers to an artificial intelligence system that analyzes received problem and emotion data and automatically generates solutions.

[0803] A "building manager" is a person who manages and repairs facilities based on reported problems and generated solutions.

[0804] "Means of notification" refers to a mechanism for transmitting information from the server to building managers and users, and includes, for example, sending messages via email or an application.

[0805] "Equipment manufacturer" refers to the manufacturer of the equipment, and is the party to which you should contact if the problem cannot be resolved.

[0806] "Repair Schedule" means the dates for carrying out repair work on equipment.

[0807] "Means for analysis" refers to the techniques and processes used to analyze received data, identify causes of problems, and generate solutions.

[0808] "Means of receiving" refers to the mechanism for obtaining data from users and building managers.

[0809] "Means for reporting" refers to a system that allows the building manager to communicate the results of attempting the generated solutions to the server.

[0810] "Means of escalation" refers to the method of communicating information to the equipment manufacturer when a specific issue requires a more advanced response.

[0811] This invention uses a system that combines an emotion engine to analyze problems reported by users and their emotions at the time, and solves the problems quickly and accurately. The system is composed of a user terminal equipped with an emotion engine, a building manager terminal, an equipment manufacturer terminal, and a server equipped with a generative AI model.

[0812] System configuration

[0813] The system consists of the following main components:

[0814] 1. User terminal: Enter and send problem reports and emotional data.

[0815] 2. Emotion engine: Analyzes the user's emotional state from their input and voice.

[0816] 3. Server: Analyzes the received data and generates solutions.

[0817] 4. Generative AI models: Analyze problem and emotion data and automatically generate solutions.

[0818] 5. Building manager terminal: Receives solutions and reports implementation results.

[0819] 6. Equipment Manufacturer Terminal: Escalates issues and coordinates repair schedules.

[0820] The role of each element

[0821] User terminal

[0822] The user terminal is provided in the form of an application or web portal, and is used by the user to enter details of the problem into a problem report form. If voice input is possible, it also has an interface for analyzing emotions from the user's voice. For example, when a user reports that "the air conditioner is not working," the emotion engine detects frustration.

[0823] Emotion Engine

[0824] The emotion engine uses natural language processing and speech analysis technologies to extract the user's emotions. For example, it identifies emotions such as frustration, anger, and worry from the input text and sends the analysis results to the server.

[0825] server

[0826] The server records the received report and emotional data in a database and instructs the generative AI to analyze it. Based on the analysis results, it generates a solution that takes the user's emotions into consideration. For example, the generative AI might suggest a solution such as, "Try turning the power off and on. If the problem persists, please contact us again."

[0827] Generative AI Models

[0828] The generative AI model identifies the cause of the problem and generates a solution by comparing it with a huge database of problems. Taking into account emotional measurement data, it is able to provide high-priority solutions that reduce the user's frustration. An example of a specific prompt is, "The air conditioner is not working. Frustration has been detected from the user's input. Please generate a solution that takes into account the emotional data."

[0829] Building manager terminal

[0830] The building manager's terminal receives the solution notified by the server, attempts to deal with the equipment, reports the results to the server, and generates a follow-up message if necessary.

[0831] Equipment manufacturer terminal

[0832] The equipment manufacturer's terminal receives notification of problem escalation and adjusts the repair schedule, which allows for efficient scheduling of on-site visits.

[0833] Specific scenarios

[0834] For example, when a user reports that the air conditioner is not working, the emotion engine detects the user's frustration. This data is received by the server, and the generative AI generates a solution such as "Please try turning the power off and on. If the problem persists, please contact us again." The building manager is then notified, and if the problem is not resolved, it is escalated to the equipment manufacturer. The equipment manufacturer adjusts the repair schedule and notifies the user.

[0835] In this way, the present invention provides a system that takes into account the user's feelings and solves problems quickly and accurately.

[0836] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0837] Step 1:

[0838] User-entered problem report

[0839] Terminal (user):

[0840] A user opens an application or web portal on their device and enters details of the problem into a problem report form. The input can be in text or voice format, for example, "The air conditioner is not working." The input text or voice is then saved on the device (output).

[0841] Step 2:

[0842] Emotion analysis using an emotion engine

[0843] Terminal (user):

[0844] The emotion engine analyzes input text and voice to extract the user's emotional state. Using natural language processing technology, emotions such as "I feel very frustrated" are analyzed (input). As a result of the analysis, emotional data is generated and stored on the device (output).

[0845] Step 3:

[0846] Receiving report content and emotion data on the server

[0847] server:

[0848] The system receives the defect report and emotion data sent from the device. The problem details and emotion data entered by the user are recorded in the server's database (input). This makes the report details and emotion data stored in the database available on the server side (output).

[0849] Step 4:

[0850] Analyzing problems and generating solutions using generative AI

[0851] server:

[0852] Based on the received data, the server instructs the generative AI to analyze the problem. The generative AI compares the report with a database of past problems to identify the cause of the problem (input). Based on the analysis results, a specific solution is generated (output), such as "Try turning the power off and on. If the problem persists, please contact us again."

[0853] Step 5:

[0854] Server notification of solution

[0855] server:

[0856] The generated solution is notified to the building manager's terminal. The generated solution and emotion data are sent from the server to the building manager's terminal (input). A notification is displayed on the building manager's terminal so that the building manager can check it (output).

[0857] Step 6:

[0858] Building manager implements solutions and reports results

[0859] Terminal (Building Manager):

[0860] The building manager receives the notification and checks for a solution via the app or web portal. The building manager then performs the power off / on operation on the air conditioner (input). The device then reports the results of the operation to the server, sending a report such as "I tried the operation but it did not resolve the problem" (output).

[0861] Step 7:

[0862] Server-driven escalation and repair schedule notifications

[0863] server:

[0864] If the problem persists despite the attempted solutions, the generative AI escalates the issue to the equipment manufacturer (input). An engineer at the equipment manufacturer reviews the problem report and emotion data, arranges a date for an on-site visit, and notifies the server of the schedule (output).

[0865] Step 8:

[0866] Repair schedule notification

[0867] server:

[0868] The adjusted repair schedule is notified to the building manager and users (input), allowing users and building managers to be aware of the planned repairs in advance and make preparations (output).

[0869] The above are the specific processing steps of the system. This is a flow that includes the input and output of data, as well as the specific operations performed at each step.

[0870] (Application example 2)

[0871] 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."

[0872] While conventional troubleshooting systems were able to receive and analyze problems reported by users, they were unable to generate solutions that took into account the user's emotional state. As a result, it was difficult to alleviate users' frustration, especially in high-stress environments. Furthermore, when the problem persisted even after factory managers implemented solutions, it was often difficult to provide appropriate follow-up or coordinate smoothly with the equipment manufacturer.

[0873] 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 a means for receiving a problem reported by a user, a means for a generative AI to analyze the received problem and generate a solution, a means for using an emotion engine to analyze the user's emotional state, and a means for notifying the factory manager of the solution. This enables a prompt and accurate solution to be provided while taking the user's emotional state into consideration. Furthermore, by providing a means for the factory manager to try the generated solution and report the results, and a means for determining the next step based on the reported results and emotion data, the efficiency of problem solving is improved. Furthermore, by providing a means for notifying the manufacturing equipment manufacturer of the problem if the generated solution does not solve the problem, a means for coordinating a repair schedule with the manufacturing equipment manufacturer, and a means for notifying the factory manager and the user of the adjusted repair schedule, follow-up for problem resolution can be carried out smoothly.

[0874] "User" means any person or entity that uses the System to report a Problem.

[0875] A "means for receiving problems" is an interface or device for receiving problems reported by users.

[0876] "Generative AI" is a system or algorithm that uses artificial intelligence techniques to analyze incoming problems and generate optimal solutions.

[0877] An "emotion engine" is software or hardware that analyzes emotions from a user's input data (text or voice) and extracts their emotional state.

[0878] A "factory manager" is an employee or staff member in charge of managing production lines and equipment within a factory.

[0879] "Means for notification" refers to the communications infrastructure or devices used to transmit generated solutions and status information to designated recipients.

[0880] The "means for analyzing the problem" refers to a processing device or software for analyzing the content of the received problem.

[0881] A "means for generating solutions" is a system or program that has the function of proposing appropriate solutions based on the analysis results.

[0882] "Emotional state" refers to the psychological state, such as frustration, anger, or worry, that a user feels when reporting a problem.

[0883] A "next step decision method" is a system or algorithm that determines the next action to take based on the reported solution results and sentiment data.

[0884] A "manufacturing equipment manufacturer" is a company that designs, manufactures, sells, and maintains manufacturing equipment used in factories.

[0885] "Means for coordinating repair schedules" means the systems and procedures for scheduling equipment repairs and inspections and communicating with relevant parties.

[0886] "Means of notifying users" are the means of communication or devices used to communicate schedules and resolution results to users.

[0887] This invention includes a troubleshooting support system installed in a robot operating on a factory production line. The specific configuration and operation will be described below.

[0888] First, a factory worker who will be the user uses a device such as a smartphone or tablet to report a problem with a robot on the production line. For example, a problem might be that the robot's arm has stopped mid-operation. Reports can be made using text input or voice input, and the emotion engine analyzes the user's emotional state (frustration, anger, worry, etc.) from this input data.

[0889] The emotion engine uses natural language processing technology to analyze input text and voice data and extract the user's emotional state. This emotional data is sent to the server along with the problem report data and recorded in a database.

[0890] The server analyzes the problem using a generative AI model based on the received problem report and emotional data. The generative AI model compares the results with a database of past problems and generates the optimal solution. The model also takes into account the emotional data and proposes high-priority solutions that reduce user frustration.

[0891] The generated solution is sent to the factory manager's device via the notification system. The factory manager receives the notification, checks the solution through an application or web portal, and implements it. For example, specific actions such as "Please restart the power supply of the arm. Also, please check the contact sensor" are displayed.

[0892] When the factory manager reports the results of the solution attempt to the server, the emotion engine also generates a follow-up message based on the user's emotional state, such as "We apologize for the inconvenience, but we tried cycling the power but it did not resolve the problem. We will try another method."

[0893] If the generated solution does not resolve the problem, the server automatically escalates the issue to the manufacturing equipment manufacturer. The manufacturer's technicians review the report and sentiment data and schedule an on-site visit. The adjusted repair schedule is then notified to the factory manager and users via the server.

[0894] This makes it possible to quickly and efficiently resolve problems with manufacturing robots in factories, and to provide courteous support that takes into account the emotional state of the user.

[0895] Prompt Sentence Examples

[0896] "Analyze problem report text entered from a smartphone, extract sentiment data, and generate solutions based on generative AI models."

[0897] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0898] Step 1:

[0899] Users use a smartphone or tablet to report a problem with a robot on a manufacturing line. They can enter text or voice input, and the input includes details of the problem, such as "The robot's arm is stuck mid-way." This is the input data. The output is the problem report data.

[0900] Step 2:

[0901] The device receives the problem report data and performs emotion analysis using an emotion engine. The emotion engine uses natural language processing technology to extract the user's emotional state (frustration, anger, worry, etc.) from the text and voice data. The input data is text and voice input, and the output data is the analysis result including the emotional state.

[0902] Step 3:

[0903] The device sends the analyzed emotion data and problem report data to the server, which records these data in a database. In this step, the input data is converted into a database format and processed for storage. As an output, confirmation information of the recorded data is generated.

[0904] Step 4:

[0905] The server analyzes the problem using a generative AI model based on the received problem report and emotion data. The generative AI model compares the results with a database of past problems and generates the optimal solution. Here, the problem is analyzed using a matching algorithm with the problem database. The input data is the problem report and emotion data, and the output is the generated solution.

[0906] Step 5:

[0907] The server notifies the generated solution to the factory manager's terminal through the notification system. The factory manager checks and implements the solution through an application or web portal. In this step, the solution is used as input data and a notification message is generated as output data.

[0908] Step 6:

[0909] The factory manager attempts the generated solution and reports the results to the server. The terminal also generates a follow-up message based on the user's emotional state using an emotion engine. The input data is the trial result data and emotion data, and the output data is the follow-up message.

[0910] Step 7:

[0911] If the generated solution does not resolve the problem, the server automatically escalates the problem to the manufacturing equipment manufacturer. The server checks the report content and sentiment data and schedules an on-site visit. The input data is the unresolved problem report, and the output data is the escalation notification.

[0912] Step 8:

[0913] The adjusted repair schedule is then sent back to the server to be notified to the factory manager and user terminals. The server processes the schedule information and generates a notification message in an appropriate format. The input data is the repair schedule, and the output data is the notification message.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] [Third embodiment]

[0918] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0919] 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.

[0920] 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).

[0921] 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.

[0922] 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.

[0923] 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).

[0924] 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. 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.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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."

[0930] The present invention relates to a system for quickly and efficiently resolving problems when malfunctions occur in facilities of buildings, hotels, etc. Specific embodiments for carrying out the present invention are described below.

[0931] This system provides a platform for users, building managers, and equipment manufacturers to efficiently handle everything from reporting problems to resolving them. Its main components are a user terminal, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI.

[0932] System Operation

[0933] Receiving problem reports

[0934] Terminal (user):

[0935] If a user experiences a problem with a building or hotel facility, they can report the issue through a smartphone app or web portal. For example, if the air conditioner in their office isn't working, they can enter a message like "The air conditioner isn't working" into the app and attach photos and videos to send it.

[0936] server:

[0937] The server receives reports from users, records the details in a database, and simultaneously instructs the generative AI to analyze the problem.

[0938] Analyzing problems and generating solutions

[0939] server:

[0940] The generative AI analyzes the received report and identifies the cause of the problem by comparing it with a database of past problems. For example, if a problem with an air conditioner is reported, the AI ​​will generate a basic solution such as "Try turning the power off and on."

[0941] Notification and Implementation of Solutions

[0942] server:

[0943] The generated solution is sent to the building manager's terminal, who then checks the proposed solution and attempts to address the problem.

[0944] Terminal (Building Manager):

[0945] The building manager reports the results of his attempts to turn the air conditioner on and off to the server. If the problem is resolved, this is fed back to the system.

[0946] Escalation and cooperation with equipment manufacturers

[0947] server:

[0948] If the problem persists despite the solutions attempted by the building manager, the generative AI will notify the equipment manufacturer of the situation.

[0949] Terminal (equipment manufacturer):

[0950] An engineer from the equipment manufacturer will confirm the problem and, if necessary, schedule an on-site visit.

[0951] Schedule Notifications

[0952] server:

[0953] The set repair schedule is notified to the building manager and users, allowing users to know in advance about the planned repairs and make preparations.

[0954] Specific examples

[0955] Example 1: Air conditioner malfunction

[0956] 1. Terminal (User):

[0957] A user reported through the app that the air conditioner was not working.

[0958] Attach photos and submit a report.

[0959] 2. Server:

[0960] Receives problem reports and instructs generative AI to analyze them.

[0961] The AI ​​generates a solution such as "Try turning the power off and on" and notifies the building manager.

[0962] 3. Terminal (Building Manager):

[0963] The building manager attempts to turn the air conditioner on and off.

[0964] After the operation, the server reported that the problem persisted.

[0965] 4. Server:

[0966] Escalate issues to equipment manufacturers and schedule repairs.

[0967] 5. Terminal (equipment manufacturer):

[0968] The technician sets the schedule, and the server notifies the building manager and users of the information.

[0969] In this way, the present invention makes it possible to quickly and efficiently resolve equipment problems in buildings and hotels.

[0970] The processing flow will be explained below.

[0971] Step 1:

[0972] Device (user): The user opens the app or web portal and fills in the problem report form with details of the problem, such as "The air conditioner is not working." If necessary, they attach photos and videos.

[0973] Step 2:

[0974] Terminal: The user enters the details of the problem and presses the "Send" button. The problem report is sent to the server.

[0975] Step 3:

[0976] Server: The server receives the problem report from the user and records the details in the database, including the details of the reported problem, the date and time, and any attached files.

[0977] Step 4:

[0978] Server: The generative AI retrieves new defect reports from the database and analyzes the problem by comparing them with past trouble data.

[0979] Step 5:

[0980] Server: The generative AI generates a solution based on the analysis results. For example, it generates a solution such as "Try turning the power off and on."

[0981] Step 6:

[0982] Server: Notifies the generated solution to the building manager's terminal.

[0983] Step 7:

[0984] Device (Building Manager): The building manager receives a notification, checks the solution via the app or web portal, and turns the air conditioner off / on according to the solution.

[0985] Step 8:

[0986] Device (Building Manager): The building manager enters the results of the operation into the app and reports them to the server. For example, they may report, "I tried turning the power off and on, but the problem persists."

[0987] Step 9:

[0988] Server: Receives reports from building managers and the generative AI determines the next steps. If the problem is not resolved, it must be escalated to the equipment manufacturer.

[0989] Step 10:

[0990] Server: The generative AI notifies the equipment manufacturer of the details of the problem and the results of the building manager's trial.

[0991] Step 11:

[0992] Terminal (equipment manufacturer): The equipment manufacturer's engineer checks the report and arranges the date for the on-site visit. Once the schedule is decided, he / she contacts the server.

[0993] Step 12:

[0994] Server: Notifies the building manager and users of the adjusted repair schedule.

[0995] Step 13:

[0996] Terminals (building managers and users): Check the repair schedule and make the necessary preparations.

[0997] This series of processing steps allows building and hotel equipment problems to be resolved quickly and efficiently.

[0998] Example 1

[0999] 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."

[1000] In large facilities such as buildings and hotels, when equipment malfunctions occur, efficient information sharing and problem resolution among users, building managers, and equipment manufacturers is essential for rapid and appropriate response. However, currently, the process from reporting a problem to providing notification of a solution, responding, and providing feedback on the results is often done manually, which takes time and effort. Furthermore, if an appropriate solution is not adopted, the problem may be prolonged, resulting in further costs and a decline in reliability.

[1001] 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.

[1002] In this invention, the server includes means for receiving problems reported by users, means for the generative AI to analyze the received problems and generate solutions, means for notifying the building manager of the solutions, means for registering the problem reports in a database, means for the generative AI to identify the cause of the problem, and means for the generative AI to refer to a database of past troubles. This makes it possible to quickly and appropriately solve equipment malfunctions in buildings and hotels.

[1003] "User" refers to the individual or entity who discovers and reports a problem while using the Equipment.

[1004] "Means for receiving problems" refers to the function of receiving data on problems reported by users regarding equipment.

[1005] "Generative AI" refers to artificial intelligence that analyzes received data and automatically generates appropriate solutions.

[1006] "Means of analyzing problems and generating solutions" refers to the function of using generative AI to analyze the causes of problems and create solutions by referring to past data.

[1007] "Building manager" refers to the individual or organization responsible for managing the facilities of a building or facility and for implementing the solutions communicated by the generative AI.

[1008] "Means for notifying solutions" refers to a function for communicating the generated solutions to the building manager.

[1009] "Means for registering in a database" refers to the function of saving problems reported by users in a database with a unique ID.

[1010] "Means for identifying the cause of the problem" refers to the function of the generative AI to refer to past trouble data to identify the cause of the reported problem.

[1011] A "past trouble database" refers to a collection of information that stores detailed records of troubles that have occurred in the past and the solutions to those troubles.

[1012] "Equipment manufacturer" refers to the company or organization that manufactures the equipment and provides technical support.

[1013] "Means to adjust repair schedules" refers to the function of setting specific repair dates and times with the equipment manufacturer to resolve the problem.

[1014] "Means for notifying repair schedules" refers to a function for communicating the adjusted repair schedule to building managers and users.

[1015] The present invention provides a system for quickly and appropriately responding to equipment malfunctions in large facilities such as buildings and hotels. Specific embodiments for carrying out the present invention are described below.

[1016] System configuration

[1017] This system provides a platform for users, building managers, and equipment manufacturers to efficiently handle everything from reporting problems to resolving them. Its main components are a user terminal, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI.

[1018] Hardware and software used

[1019] User device: A device such as a smartphone, tablet, or computer.

[1020] Building manager's terminal: Devices such as PCs, tablets, and smartphones.

[1021] Equipment manufacturer terminal: Devices such as computers, tablets, and smartphones.

[1022] Server: A high-performance computer server equipped with generative AI that analyzes problems and generates solutions.

[1023] System operation explanation

[1024] Accepting problem reports

[1025] Terminal (user)

[1026] If a user experiences a problem with a building or hotel facility, they can report the problem through a smartphone app or web portal. For example, to report a problem like "The air conditioner in my office isn't working," they simply type "The air conditioner isn't working" into the app and attach photos or videos as needed. When the user presses the "Submit" button, the report is sent to the server.

[1027] Problem Report Database Registration

[1028] server

[1029] The server receives problem reports sent by users and records their contents in a database. At this time, details of the reported problem and attached photos and videos are saved together. A unique ID is also assigned to the report contents for management.

[1030] Problem analysis using generative AI models

[1031] server

[1032] Based on problem reports registered in the database, the generative AI model is instructed to perform an analysis. The generative AI model refers to past trouble data and performs an analysis to identify the cause of the problem. For example, in response to a report that "the air conditioner is not working," it will list possible causes, such as a power failure or a clogged filter.

[1033] Solution Generation

[1034] server

[1035] The generative AI model generates optimal solutions based on the analysis results. For example, the AI ​​might suggest basic solutions such as "Try turning the power off and on." If necessary, it also includes detailed instructions and precautions.

[1036] Solution Notification

[1037] server

[1038] The generated solution is sent to the building manager's terminal, and the notification includes a summary of the report along with the details of the solution.

[1039] Building manager's response

[1040] Terminal (Building Manager)

[1041] The building manager receives the notification and takes action according to the proposed solution, for example, turning the air conditioner off and on, and then reports the result to the server.

[1042] Reporting results and feedback

[1043] server

[1044] Receive reports from building managers to see if the problem has been resolved. If the problem has been resolved, record the information in a database and notify the user.

[1045] Escalation and cooperation with equipment manufacturers

[1046] server

[1047] If the problem cannot be resolved by the building manager, the generative AI model escalates the issue to the equipment manufacturer, who sends a detailed report and dispatches a technician to handle the issue as needed.

[1048] Response by equipment manufacturers

[1049] Terminal (equipment manufacturer)

[1050] An engineer from the equipment manufacturer will identify the problem and schedule a site visit or repair. This information is sent to the server.

[1051] Repair schedule notification

[1052] server

[1053] The set repair schedule is notified to the building manager and users, allowing users to know about the planned repairs in advance and make preparations.

[1054] Specific examples

[1055] For example, if a problem is reported that "the air conditioner in the office is not working," the following actions will be taken:

[1056] 1. Terminal (User)

[1057] A user reports "the air conditioner is not working" in the app and sends it with a photo attached.

[1058] 2. Server

[1059] Receives problem reports, stores them in a database, and directs the generative AI model to analyze them.

[1060] 3. Server

[1061] The AI ​​generates a solution such as "Try turning the power off and on" and notifies the building manager.

[1062] 4. Terminal (Building Manager)

[1063] The building manager attempts to operate the power supply, but the problem persists, so he reports the results to the server.

[1064] 5. Server

[1065] Escalate the issue to the equipment manufacturer and schedule a repair response.

[1066] 6. Terminal (equipment manufacturer)

[1067] The technician sets the schedule and the server notifies the building manager and users.

[1068] This makes it possible for the system of the present invention to quickly and efficiently resolve equipment problems in buildings and hotels.

[1069] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1070] Step 1:

[1071] User (Device):

[1072] Users report equipment problems through a smartphone app or web portal. They enter specific prompt text (e.g., "The air conditioner isn't working") into the app and attach photos and videos as needed. A problem report (text, photos, and videos) is generated based on the input data. When the user presses the "Submit" button, the entered problem report is sent to the server.

[1073] Step 2:

[1074] server:

[1075] The server records the problem reports received from users in a database. At this time, it receives the report content data (text, photos, videos) and records it with a unique ID. The input data is the problem report data from the user, and the output is the problem report stored in the database.

[1076] Step 3:

[1077] server:

[1078] Based on the problem reports registered in the database, the generative AI model is instructed to perform analysis. The generative AI model receives the details of the problem report as input data and searches for related information from a database of past troubles. Data processing involves analysis to identify the cause of the problem, and a list of possible causes is generated as output.

[1079] Step 4:

[1080] server:

[1081] The generative AI model generates an appropriate solution from the analysis results. The input data is the analysis results and past trouble data, and the solution is generated as a data calculation. The output is a specific solution (e.g., "Try turning the power off and on").

[1082] Step 5:

[1083] server:

[1084] The generated solution is notified to the building manager's terminal. The input data is the generated solution, and the output data is a solution notification message sent to the building manager. The server sends a notification to the building manager's terminal.

[1085] Step 6:

[1086] Building manager (terminal):

[1087] The building manager receives the solution notification and takes action according to the proposed solution. The input data is the solution notification sent from the server, and the output data is the result of the action taken by the building manager. The building manager actually operates the equipment (e.g., turning the power off / on).

[1088] Step 7:

[1089] server:

[1090] Receives a report from the building manager and verifies whether the problem has been resolved. The input data is the action taken by the building manager, and the data calculation verifies the resolution of the problem. The output data is the resolution status recorded in the database and a feedback message generated as needed.

[1091] Step 8:

[1092] server:

[1093] If the problem cannot be resolved by the building manager's actions, the server escalates the problem to the equipment manufacturer based on the instructions of the generated AI model. The input data are the building manager's actions and analysis results, and the output data is an escalation notification sent to the equipment manufacturer.

[1094] Step 9:

[1095] Equipment manufacturer (terminal):

[1096] The equipment manufacturer's technician receives the escalation notification, checks the problem, and arranges a site visit or repair schedule as necessary. The input data is the escalation notification, and the output data is the adjusted repair schedule.

[1097] Step 10:

[1098] server:

[1099] The set repair schedule is notified to the building manager and users. The input data is the adjusted repair schedule, and the output data is a schedule notification message sent to the building manager and users. By sending the notification from the server, users and building managers can know the repair schedule in advance.

[1100] (Application example 1)

[1101] 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."

[1102] The present invention aims to quickly and efficiently resolve problems that occur in equipment used in factories and other facilities. It also aims to reduce the burden on managers and engineers and improve productivity. In particular, it aims to improve the speed and accuracy of responses in factory equipment management by automating the entire process from reporting problems to implementing countermeasures and escalation.

[1103] 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.

[1104] In this invention, the server includes a means for receiving problems reported by users, a means for the generative AI to analyze the received problems and generate solutions, a means for notifying the administrator of the solutions, a means for the administrator to confirm the solutions and issue instructions to the equipment, and a means for the equipment to execute the instructed solutions. This allows for a smooth process from reporting problems to generating and executing solutions. It also reduces the burden on administrators and engineers and improves response speed.

[1105] 1. "User" refers to the employee or staff member who reports the issue within the factory or facility.

[1106] 2. "Generative AI" refers to an artificial intelligence system that analyzes incoming problems and generates solutions.

[1107] 3. "Manager" refers to a person in charge of managing equipment within a factory or facility.

[1108] 4. "Means for receiving problems" refers to the methods and tools by which problems reported by users are captured by the system.

[1109] 5. “Means of problem analysis” refers to the methods and tools that generative AI uses to understand the content of a problem and identify its causes.

[1110] 6. "Solution generation means" refers to methods or tools that propose solutions to problems analyzed by generative AI.

[1111] 7. "Solution notification means" refers to the methods and tools used to communicate generated solutions to management.

[1112] 8. "Means for verifying solutions and issuing instructions to equipment" refers to the methods and tools by which managers verify proposed solutions and issue instructions to equipment based on their content.

[1113] 9. "Equipment" refers to machinery and devices used within a factory or facility.

[1114] 10. "Means for implementing directed solutions" refers to the methods and tools by which the facility implements solutions as directed by management.

[1115] 11. "Technical Specialist" refers to a technical expert who will provide additional support if the generated solution does not resolve the issue.

[1116] 12. "Measures for coordinating response scheduling" refers to methods and tools for scheduling technical personnel to conduct on-site visits and follow-up responses.

[1117] 13. "Means for notifying adjusted response schedules" refers to methods and tools for notifying administrators and users of the set response schedules.

[1118] The present invention is a system that automates the process from reporting problems in facility management in factories and other facilities to generating and implementing solutions. The system is composed of a user terminal, an administrator terminal, facilities, and a server equipped with generative AI. Specific embodiments for implementing the present invention are described below.

[1119] User-reported problems

[1120] Users report equipment malfunctions using smartphones or robotics control terminals. The report is sent to the server in the form of text, photos, videos, etc. Consider the example where a user reports that "Machine A is not working" and attaches a photo to the report.

[1121] Server-based problem analysis and solution generation

[1122] The server analyzes the received problem report and generates a solution using generative AI. For example, a solution such as "Please restart machine A" may be generated. This generative AI compares the solution with a past database to select the optimal solution.

[1123] Notify administrator of solution

[1124] The generated solution is sent to the administrator's terminal. The administrator checks the solution and issues instructions to the equipment based on its contents. For example, the administrator sends an instruction to restart a factory robot.

[1125] Implementation of solutions by equipment

[1126] The factory robot follows instructions from the administrator and executes a solution. For example, it restarts machine A and reports the results to the server. If the solution is executed and the problem is solved, the process ends there, but if it is not solved, it moves on to the next step.

[1127] Escalation and Scheduling

[1128] If the generated solution does not resolve the problem, the server notifies a specialist engineer, who then schedules a response and notifies the administrator and user. This allows for a smooth response, such as an on-site visit.

[1129] The hardware used includes smartphones, robotics control terminals, factory robots, and servers, while the software includes smartphone apps for Android / iOS, robotics control software, generative AI, and a database management system.

[1130] Specific examples

[1131] 1. User device: A factory employee reports on their smartphone that "Machine A is not working" and attaches a photo.

[1132] 2. Server: The generative AI analyzes the problem and generates a solution: "Please restart machine A."

[1133] 3. Administrator terminal: The administrator checks the solution and sends a restart instruction to the factory robot.

[1134] 4. Equipment: The factory robot restarts Machine A and reports the results.

[1135] 5. Server: If the issue persists, escalate to a technician and schedule an on-site visit.

[1136] Prompt Sentence Examples

[1137] Analyze a problem report for a specific machine in the factory and generate and issue the optimal solution. Please use the following information:

[1138] Problem details: {Problem details text}

[1139] Additional information: {URL of photo or video}

[1140] In this way, the system can be used to quickly and efficiently solve facility management problems within a factory.

[1141] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1142] Step 1:

[1143] Entering a Problem Report

[1144] Users report equipment malfunctions using a smartphone app or robotics control terminal. Input includes text (e.g., "Machine A is not working"), photos, and videos. The user enters this information into the app and sends it to the server, which records the received report in a database.

[1145] Step 2:

[1146] Analyzing problems and generating solutions

[1147] The server passes the received report content to the generative AI. The generative AI analyzes the report content (text, photos, videos) and identifies the cause of the problem by comparing it with a database of past troubles. Based on this analysis, the generative AI generates a solution such as "Please restart machine A." The server records the generated solution in a database.

[1148] Step 3:

[1149] Solution Notification

[1150] The server notifies the generated solution to the administrator terminal. The administrator terminal receives the notification and displays the solution. For example, the administrator sees a message saying "Please restart machine A."

[1151] Step 4:

[1152] Instructions for implementing solutions

[1153] The manager checks the received solution and issues instructions to the factory robot based on the content. A reboot instruction is sent from the manager's terminal to the factory robot control system. For example, the manager presses the "reboot" button on the terminal, and the instruction is transmitted to the robot.

[1154] Step 5:

[1155] Implementing the solution

[1156] The factory robot restarts machine A based on instructions from the administrator. The robot actually performs the restart operation and sends the results to the administrator's terminal. The server records the results reported by the robot in a database.

[1157] Step 6:

[1158] Verify the problem is resolved

[1159] The administrator terminal receives the report from the robot and checks whether the problem has been resolved. If it has been resolved, it sends feedback to the server. If it has not been resolved, it proceeds to the next step. The server records this feedback in a database.

[1160] Step 7:

[1161] Escalation and Scheduling

[1162] If the generated solution does not solve the problem, the server notifies the specialist engineer of the problem. The engineer's terminal receives the notification from the server. The engineer adjusts a response schedule, such as a facility visit, and reports it to the server. The server notifies the administrator and user of the adjusted schedule.

[1163] Step 8:

[1164] Schedule Notifications

[1165] Users and administrators receive schedule notifications from the server and prepare for the response. The server records the notification content in a database. This completes the entire process, ensuring a smooth process from reporting the problem to responding to it.

[1166] 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.

[1167] The present invention is a system for analyzing problems reported by users and their emotions at the time, and for solving the problems quickly and accurately. A specific embodiment of the present invention combined with an emotion engine is shown below.

[1168] This system consists of a user terminal equipped with an emotion engine, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI. By using the emotion engine, it is possible to analyze the emotional state of the user when reporting a problem and provide a more effective solution.

[1169] System Operation

[1170] Receiving problem reports and analyzing sentiment

[1171] Terminal (user):

[1172] When a user opens the app or web portal and enters details of a problem, such as "my air conditioner isn't working," into a problem report form, the emotion engine analyzes the user's input and voice (in the case of voice input) to determine emotions, such as frustration, anger, or worry.

[1173] Device:

[1174] The user enters the details of the problem and presses the "Submit" button. The emotion data is sent to the server along with the problem report.

[1175] Analyzing problems and generating solutions

[1176] server:

[1177] The server receives user reports of problems, records their content and emotional data in a database, and simultaneously instructs the generative AI to analyze the problem.

[1178] server:

[1179] The generative AI analyzes the received report and emotional data, and identifies the cause of the problem by comparing it with a database of past problems. When generating solutions based on the analysis results, it takes into account emotional data to suggest high-priority solutions that reduce the user's frustration. For example, a solution might be generated such as, "Try turning the power off and on. If the problem persists, please contact us again."

[1180] Notification and Implementation of Solutions

[1181] server:

[1182] The generated solution is notified to the building manager's terminal, who then checks the proposed solution and attempts to address the equipment.

[1183] Terminal (Building Manager):

[1184] The building manager receives a notification, checks for a solution via the app or web portal, and then turns the air conditioner off and on according to the solution.

[1185] Applications of the Emotion Engine:

[1186] The terminal (building manager) inputs the results of the operation into the server, and generates a report that takes into account the user's emotional state through an emotion engine. For example, a follow-up message such as "We apologize for the inconvenience, but we tried turning the power off and on again, but that did not resolve the problem. We will try another method."

[1187] Escalation and cooperation with equipment manufacturers

[1188] server:

[1189] If the problem persists despite the solutions attempted by the building manager, the generative AI will notify the equipment manufacturer of the situation.

[1190] Terminal (equipment manufacturer):

[1191] An engineer from the equipment manufacturer will review the report and the sentiment data, and schedule a site visit. Once the schedule is decided, it will be notified to the server.

[1192] Schedule Notifications

[1193] server:

[1194] The adjusted repair schedule is then communicated to building managers and users, allowing users to be aware of upcoming repairs and make preparations in advance.

[1195] Specific examples

[1196] Example 1: Air conditioner malfunction

[1197] 1. Terminal (User):

[1198] A user reports in the app that the air conditioner isn't working, expressing extreme frustration.

[1199] The emotion engine analyzes frustration and sends the emotional data to the server.

[1200] 2. Server:

[1201] Receives problem reports and emotional data and instructs generative AI to analyze them.

[1202] The AI ​​generates a solution, such as "Try turning the power off and on. If the problem persists, please contact us again," and notifies the building manager.

[1203] 3. Terminal (Building Manager):

[1204] The building manager reported that he tried turning the air conditioner on and off but was unable to resolve the issue.

[1205] The emotion engine generates follow-up messages to ease user frustration.

[1206] 4. Server:

[1207] Escalate issues to equipment manufacturers and schedule repairs.

[1208] 5. Terminal (equipment manufacturer):

[1209] The technician sets the schedule, and the server notifies the building manager and users of the information.

[1210] In this way, the present invention makes it possible to quickly and efficiently resolve facility problems in buildings and hotels while also taking into consideration the feelings of users.

[1211] The processing flow will be explained below.

[1212] Step 1:

[1213] Device (user): The user opens the app or web portal and enters details of the problem into the problem report form, such as "my air conditioner isn't working." At the same time, the emotion engine analyzes the user's input (text or voice) to identify emotions, such as frustration, anger, or worry.

[1214] Step 2:

[1215] Terminal: The user enters details of the problem and emotional data and presses the "Send" button. The problem report and emotional data are sent to the server.

[1216] Step 3:

[1217] Server: The server receives the defect report and emotion data from the user and records the details in a database. The record contents include details of the reported defect, date and time, emotion data, and attached files.

[1218] Step 4:

[1219] Server: The generative AI retrieves new defect reports from the database, analyzes the report content and emotional data, and identifies the cause of the problem by comparing it with a database of past problems.

[1220] Step 5:

[1221] Server: The generative AI generates solutions based on the analysis results. It takes into account emotional data and suggests high-priority solutions that reduce the user's frustration. For example, it generates a solution such as "Try turning the power off and on. If the problem persists, please contact us again."

[1222] Step 6:

[1223] Server: Notifies the generated solution to the building manager's terminal.

[1224] Step 7:

[1225] Device (Building Manager): The building manager receives a notification, checks the solution via the app or web portal, and turns the air conditioner off / on according to the solution.

[1226] Step 8:

[1227] Terminal (Building Manager): The building manager enters the results of the operation into the app and reports them to the server. If the problem is resolved, this is fed back to the system.

[1228] Step 9:

[1229] Server: Receives reports from building managers and the generative AI determines the next steps. If the problem is not resolved, it escalates to the equipment manufacturer.

[1230] Step 10:

[1231] Server: The generative AI notifies the equipment manufacturer of the details of the problem and the results of the building manager's trial.

[1232] Step 11:

[1233] Terminal (Equipment Manufacturer): The equipment manufacturer's engineer checks the report and emotion data, and arranges the date for the on-site visit. Once the schedule is decided, the engineer contacts the server.

[1234] Step 12:

[1235] Server: Notifies the building manager and users of the adjusted repair schedule.

[1236] Step 13:

[1237] Terminals (building managers and users): Check the repair schedule and make the necessary preparations.

[1238] Step 14:

[1239] Terminal (Building Manager): The building manager sends a follow-up message generated by the emotion engine to the user along with the results of the operation. For example, "We apologize for the inconvenience, but the problem was not resolved after power cycling. We will try another method."

[1240] This series of processing steps allows building and hotel equipment problems to be resolved quickly and efficiently, while also properly managing the emotions of users.

[1241] Example 2

[1242] 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."

[1243] Conventional building and facility management systems handle problems reported by users without considering their emotional state, which has prevented them from fully increasing user satisfaction. Furthermore, they are unable to properly analyze and utilize emotional data, resulting in problems that are not resolved quickly or accurately. Therefore, there is a need for a system that can resolve problems quickly and accurately while taking into account the emotions of users.

[1244] 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.

[1245] In this invention, the server includes a means for receiving a problem reported by a user and analyzing the emotional state of the user at the time, a means for the generative AI model to analyze the received problem and emotional data and generate a solution, and a means for notifying the building manager of the generated solution, which enables the problem to be solved quickly and accurately while taking the user's emotions into consideration.

[1246] "User" means a person who uses the system to report a problem.

[1247] "Emotional state" refers to the emotional state that a user exhibits when reporting a problem, such as frustration, anger, or worry.

[1248] "Generative AI model" refers to an artificial intelligence system that analyzes received problem and emotion data and automatically generates solutions.

[1249] A "building manager" is a person who manages and repairs facilities based on reported problems and generated solutions.

[1250] "Means of notification" refers to a mechanism for transmitting information from the server to building managers and users, and includes, for example, sending messages via email or an application.

[1251] "Equipment manufacturer" refers to the manufacturer of the equipment, and is the party to which you should contact if the problem cannot be resolved.

[1252] "Repair Schedule" means the dates for carrying out repair work on equipment.

[1253] "Means for analysis" refers to the techniques and processes used to analyze received data, identify causes of problems, and generate solutions.

[1254] "Means of receiving" refers to the mechanism for obtaining data from users and building managers.

[1255] "Means for reporting" refers to a system that allows the building manager to communicate the results of attempting the generated solutions to the server.

[1256] "Means of escalation" refers to the method of communicating information to the equipment manufacturer when a specific issue requires a more advanced response.

[1257] This invention uses a system that combines an emotion engine to analyze problems reported by users and their emotions at the time, and solves the problems quickly and accurately. The system is composed of a user terminal equipped with an emotion engine, a building manager terminal, an equipment manufacturer terminal, and a server equipped with a generative AI model.

[1258] System configuration

[1259] The system consists of the following main components:

[1260] 1. User terminal: Enter and send problem reports and emotional data.

[1261] 2. Emotion engine: Analyzes the user's emotional state from their input and voice.

[1262] 3. Server: Analyzes the received data and generates solutions.

[1263] 4. Generative AI models: Analyze problem and emotion data and automatically generate solutions.

[1264] 5. Building manager terminal: Receives solutions and reports implementation results.

[1265] 6. Equipment Manufacturer Terminal: Escalates issues and coordinates repair schedules.

[1266] The role of each element

[1267] User terminal

[1268] The user terminal is provided in the form of an application or web portal, and is used by the user to enter details of the problem into a problem report form. If voice input is possible, it also has an interface for analyzing emotions from the user's voice. For example, when a user reports that "the air conditioner is not working," the emotion engine detects frustration.

[1269] Emotion Engine

[1270] The emotion engine uses natural language processing and speech analysis technologies to extract the user's emotions. For example, it identifies emotions such as frustration, anger, and worry from the input text and sends the analysis results to the server.

[1271] server

[1272] The server records the received report and emotional data in a database and instructs the generative AI to analyze it. Based on the analysis results, it generates a solution that takes the user's emotions into consideration. For example, the generative AI might suggest a solution such as, "Try turning the power off and on. If the problem persists, please contact us again."

[1273] Generative AI Models

[1274] The generative AI model identifies the cause of the problem and generates a solution by comparing it with a huge database of problems. Taking into account emotional measurement data, it is able to provide high-priority solutions that reduce the user's frustration. An example of a specific prompt is, "The air conditioner is not working. Frustration has been detected from the user's input. Please generate a solution that takes into account the emotional data."

[1275] Building manager terminal

[1276] The building manager's terminal receives the solution notified by the server, attempts to deal with the equipment, reports the results to the server, and generates a follow-up message if necessary.

[1277] Equipment manufacturer terminal

[1278] The equipment manufacturer's terminal receives notification of problem escalation and adjusts the repair schedule, which allows for efficient scheduling of on-site visits.

[1279] Specific scenarios

[1280] For example, when a user reports that the air conditioner is not working, the emotion engine detects the user's frustration. This data is received by the server, and the generative AI generates a solution such as "Please try turning the power off and on. If the problem persists, please contact us again." The building manager is then notified, and if the problem is not resolved, it is escalated to the equipment manufacturer. The equipment manufacturer adjusts the repair schedule and notifies the user.

[1281] In this way, the present invention provides a system that takes into account the user's feelings and solves problems quickly and accurately.

[1282] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1283] Step 1:

[1284] User-entered problem report

[1285] Terminal (user):

[1286] A user opens an application or web portal on their device and enters details of the problem into a problem report form. The input can be in text or voice format, for example, "The air conditioner is not working." The input text or voice is then saved on the device (output).

[1287] Step 2:

[1288] Emotion analysis using an emotion engine

[1289] Terminal (user):

[1290] The emotion engine analyzes input text and voice to extract the user's emotional state. Using natural language processing technology, emotions such as "I feel very frustrated" are analyzed (input). As a result of the analysis, emotional data is generated and stored on the device (output).

[1291] Step 3:

[1292] Receiving report content and emotion data on the server

[1293] server:

[1294] The system receives the defect report and emotion data sent from the device. The problem details and emotion data entered by the user are recorded in the server's database (input). This makes the report details and emotion data stored in the database available on the server side (output).

[1295] Step 4:

[1296] Analyzing problems and generating solutions using generative AI

[1297] server:

[1298] Based on the received data, the server instructs the generative AI to analyze the problem. The generative AI compares the report with a database of past problems to identify the cause of the problem (input). Based on the analysis results, a specific solution is generated (output), such as "Try turning the power off and on. If the problem persists, please contact us again."

[1299] Step 5:

[1300] Server notification of solution

[1301] server:

[1302] The generated solution is notified to the building manager's terminal. The generated solution and emotion data are sent from the server to the building manager's terminal (input). A notification is displayed on the building manager's terminal so that the building manager can check it (output).

[1303] Step 6:

[1304] Building manager implements solutions and reports results

[1305] Terminal (Building Manager):

[1306] The building manager receives the notification and checks for a solution via the app or web portal. The building manager then performs the power off / on operation on the air conditioner (input). The device then reports the results of the operation to the server, sending a report such as "I tried the operation but it did not resolve the problem" (output).

[1307] Step 7:

[1308] Server-driven escalation and repair schedule notifications

[1309] server:

[1310] If the problem persists despite the attempted solutions, the generative AI escalates the issue to the equipment manufacturer (input). An engineer at the equipment manufacturer reviews the problem report and emotion data, arranges a date for an on-site visit, and notifies the server of the schedule (output).

[1311] Step 8:

[1312] Repair schedule notification

[1313] server:

[1314] The adjusted repair schedule is notified to the building manager and users (input), allowing users and building managers to be aware of the planned repairs in advance and make preparations (output).

[1315] The above are the specific processing steps of the system. This is a flow that includes the input and output of data, as well as the specific operations performed at each step.

[1316] (Application example 2)

[1317] 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."

[1318] While conventional troubleshooting systems were able to receive and analyze problems reported by users, they were unable to generate solutions that took into account the user's emotional state. As a result, it was difficult to alleviate users' frustration, especially in high-stress environments. Furthermore, when the problem persisted even after factory managers implemented solutions, it was often difficult to provide appropriate follow-up or coordinate smoothly with the equipment manufacturer.

[1319] 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 a means for receiving a problem reported by a user, a means for a generative AI to analyze the received problem and generate a solution, a means for using an emotion engine to analyze the user's emotional state, and a means for notifying the factory manager of the solution. This enables a prompt and accurate solution to be provided while taking the user's emotional state into consideration. Furthermore, by providing a means for the factory manager to try the generated solution and report the results, and a means for determining the next step based on the reported results and emotion data, the efficiency of problem solving is improved. Furthermore, by providing a means for notifying the manufacturing equipment manufacturer of the problem if the generated solution does not solve the problem, a means for coordinating a repair schedule with the manufacturing equipment manufacturer, and a means for notifying the factory manager and the user of the adjusted repair schedule, follow-up for problem resolution can be carried out smoothly.

[1320] "User" means any person or entity that uses the System to report a Problem.

[1321] A "means for receiving problems" is an interface or device for receiving problems reported by users.

[1322] "Generative AI" is a system or algorithm that uses artificial intelligence techniques to analyze incoming problems and generate optimal solutions.

[1323] An "emotion engine" is software or hardware that analyzes emotions from a user's input data (text or voice) and extracts their emotional state.

[1324] A "factory manager" is an employee or staff member in charge of managing production lines and equipment within a factory.

[1325] "Means for notification" refers to the communications infrastructure or devices used to transmit generated solutions and status information to designated recipients.

[1326] The "means for analyzing the problem" refers to a processing device or software for analyzing the content of the received problem.

[1327] A "means for generating solutions" is a system or program that has the function of proposing appropriate solutions based on the analysis results.

[1328] "Emotional state" refers to the psychological state, such as frustration, anger, or worry, that a user feels when reporting a problem.

[1329] A "next step decision method" is a system or algorithm that determines the next action to take based on the reported solution results and sentiment data.

[1330] A "manufacturing equipment manufacturer" is a company that designs, manufactures, sells, and maintains manufacturing equipment used in factories.

[1331] "Means for coordinating repair schedules" means the systems and procedures for scheduling equipment repairs and inspections and communicating with relevant parties.

[1332] "Means of notifying users" are the means of communication or devices used to communicate schedules and resolution results to users.

[1333] This invention includes a troubleshooting support system installed in a robot operating on a factory production line. The specific configuration and operation will be described below.

[1334] First, a factory worker who will be the user uses a device such as a smartphone or tablet to report a problem with a robot on the production line. For example, a problem might be that the robot's arm has stopped mid-operation. Reports can be made using text input or voice input, and the emotion engine analyzes the user's emotional state (frustration, anger, worry, etc.) from this input data.

[1335] The emotion engine uses natural language processing technology to analyze input text and voice data and extract the user's emotional state. This emotional data is sent to the server along with the problem report data and recorded in a database.

[1336] The server analyzes the problem using a generative AI model based on the received problem report and emotional data. The generative AI model compares the results with a database of past problems and generates the optimal solution. The model also takes into account the emotional data and proposes high-priority solutions that reduce user frustration.

[1337] The generated solution is sent to the factory manager's device via the notification system. The factory manager receives the notification, checks the solution through an application or web portal, and implements it. For example, specific actions such as "Please restart the power supply of the arm. Also, please check the contact sensor" are displayed.

[1338] When the factory manager reports the results of the solution attempt to the server, the emotion engine also generates a follow-up message based on the user's emotional state, such as "We apologize for the inconvenience, but we tried cycling the power but it did not resolve the problem. We will try another method."

[1339] If the generated solution does not resolve the problem, the server automatically escalates the issue to the manufacturing equipment manufacturer. The manufacturer's technicians review the report and sentiment data and schedule an on-site visit. The adjusted repair schedule is then notified to the factory manager and users via the server.

[1340] This makes it possible to quickly and efficiently resolve problems with manufacturing robots in factories, and to provide courteous support that takes into account the emotional state of the user.

[1341] Prompt Sentence Examples

[1342] "Analyze problem report text entered from a smartphone, extract sentiment data, and generate solutions based on generative AI models."

[1343] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1344] Step 1:

[1345] Users use a smartphone or tablet to report a problem with a robot on a manufacturing line. They can enter text or voice input, and the input includes details of the problem, such as "The robot's arm is stuck mid-way." This is the input data. The output is the problem report data.

[1346] Step 2:

[1347] The device receives the problem report data and performs emotion analysis using an emotion engine. The emotion engine uses natural language processing technology to extract the user's emotional state (frustration, anger, worry, etc.) from the text and voice data. The input data is text and voice input, and the output data is the analysis result including the emotional state.

[1348] Step 3:

[1349] The device sends the analyzed emotion data and problem report data to the server, which records these data in a database. In this step, the input data is converted into a database format and processed for storage. As an output, confirmation information of the recorded data is generated.

[1350] Step 4:

[1351] The server analyzes the problem using a generative AI model based on the received problem report and emotion data. The generative AI model compares the results with a database of past problems and generates the optimal solution. Here, the problem is analyzed using a matching algorithm with the problem database. The input data is the problem report and emotion data, and the output is the generated solution.

[1352] Step 5:

[1353] The server notifies the generated solution to the factory manager's terminal through the notification system. The factory manager checks and implements the solution through an application or web portal. In this step, the solution is used as input data and a notification message is generated as output data.

[1354] Step 6:

[1355] The factory manager attempts the generated solution and reports the results to the server. The terminal also generates a follow-up message based on the user's emotional state using an emotion engine. The input data is the trial result data and emotion data, and the output data is the follow-up message.

[1356] Step 7:

[1357] If the generated solution does not resolve the problem, the server automatically escalates the problem to the manufacturing equipment manufacturer. The server checks the report content and sentiment data and schedules an on-site visit. The input data is the unresolved problem report, and the output data is the escalation notification.

[1358] Step 8:

[1359] The adjusted repair schedule is then sent back to the server to be notified to the factory manager and user terminals. The server processes the schedule information and generates a notification message in an appropriate format. The input data is the repair schedule, and the output data is the notification message.

[1360] 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.

[1361] 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.

[1362] 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.

[1363] [Fourth embodiment]

[1364] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1365] 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.

[1366] 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).

[1367] 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.

[1368] 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.

[1369] 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).

[1370] 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. 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.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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."

[1377] The present invention relates to a system for quickly and efficiently resolving problems when malfunctions occur in facilities of buildings, hotels, etc. Specific embodiments for carrying out the present invention are described below.

[1378] This system provides a platform for users, building managers, and equipment manufacturers to efficiently handle everything from reporting problems to resolving them. Its main components are a user terminal, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI.

[1379] System Operation

[1380] Receiving problem reports

[1381] Terminal (user):

[1382] If a user experiences a problem with a building or hotel facility, they can report the issue through a smartphone app or web portal. For example, if the air conditioner in their office isn't working, they can enter a message like "The air conditioner isn't working" into the app and attach photos and videos to send it.

[1383] server:

[1384] The server receives reports from users, records the details in a database, and simultaneously instructs the generative AI to analyze the problem.

[1385] Analyzing problems and generating solutions

[1386] server:

[1387] The generative AI analyzes the received report and identifies the cause of the problem by comparing it with a database of past problems. For example, if a problem with an air conditioner is reported, the AI ​​will generate a basic solution such as "Try turning the power off and on."

[1388] Notification and Implementation of Solutions

[1389] server:

[1390] The generated solution is sent to the building manager's terminal, who then checks the proposed solution and attempts to address the problem.

[1391] Terminal (Building Manager):

[1392] The building manager reports the results of his attempts to turn the air conditioner on and off to the server. If the problem is resolved, this is fed back to the system.

[1393] Escalation and cooperation with equipment manufacturers

[1394] server:

[1395] If the problem persists despite the solutions attempted by the building manager, the generative AI will notify the equipment manufacturer of the situation.

[1396] Terminal (equipment manufacturer):

[1397] An engineer from the equipment manufacturer will confirm the problem and, if necessary, schedule an on-site visit.

[1398] Schedule Notifications

[1399] server:

[1400] The set repair schedule is notified to the building manager and users, allowing users to know in advance about the planned repairs and make preparations.

[1401] Specific examples

[1402] Example 1: Air conditioner malfunction

[1403] 1. Terminal (User):

[1404] A user reported through the app that the air conditioner was not working.

[1405] Attach photos and submit a report.

[1406] 2. Server:

[1407] Receives problem reports and instructs generative AI to analyze them.

[1408] The AI ​​generates a solution such as "Try turning the power off and on" and notifies the building manager.

[1409] 3. Terminal (Building Manager):

[1410] The building manager attempts to turn the air conditioner on and off.

[1411] After the operation, the server reported that the problem persisted.

[1412] 4. Server:

[1413] Escalate issues to equipment manufacturers and schedule repairs.

[1414] 5. Terminal (equipment manufacturer):

[1415] The technician sets the schedule, and the server notifies the building manager and users of the information.

[1416] In this way, the present invention makes it possible to quickly and efficiently resolve equipment problems in buildings and hotels.

[1417] The processing flow will be explained below.

[1418] Step 1:

[1419] Device (user): The user opens the app or web portal and fills in the problem report form with details of the problem, such as "The air conditioner is not working." If necessary, they attach photos and videos.

[1420] Step 2:

[1421] Terminal: The user enters the details of the problem and presses the "Send" button. The problem report is sent to the server.

[1422] Step 3:

[1423] Server: The server receives the problem report from the user and records the details in the database, including the details of the reported problem, the date and time, and any attached files.

[1424] Step 4:

[1425] Server: The generative AI retrieves new defect reports from the database and analyzes the problem by comparing them with past trouble data.

[1426] Step 5:

[1427] Server: The generative AI generates a solution based on the analysis results. For example, it generates a solution such as "Try turning the power off and on."

[1428] Step 6:

[1429] Server: Notifies the generated solution to the building manager's terminal.

[1430] Step 7:

[1431] Device (Building Manager): The building manager receives a notification, checks the solution via the app or web portal, and turns the air conditioner off / on according to the solution.

[1432] Step 8:

[1433] Device (Building Manager): The building manager enters the results of the operation into the app and reports them to the server. For example, they may report, "I tried turning the power off and on, but the problem persists."

[1434] Step 9:

[1435] Server: Receives reports from building managers and the generative AI determines the next steps. If the problem is not resolved, it must be escalated to the equipment manufacturer.

[1436] Step 10:

[1437] Server: The generative AI notifies the equipment manufacturer of the details of the problem and the results of the building manager's trial.

[1438] Step 11:

[1439] Terminal (equipment manufacturer): The equipment manufacturer's engineer checks the report and arranges the date for the on-site visit. Once the schedule is decided, he / she contacts the server.

[1440] Step 12:

[1441] Server: Notifies the building manager and users of the adjusted repair schedule.

[1442] Step 13:

[1443] Terminals (building managers and users): Check the repair schedule and make the necessary preparations.

[1444] This series of processing steps allows building and hotel equipment problems to be resolved quickly and efficiently.

[1445] Example 1

[1446] 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."

[1447] In large facilities such as buildings and hotels, when equipment malfunctions occur, efficient information sharing and problem resolution among users, building managers, and equipment manufacturers is essential for rapid and appropriate response. However, currently, the process from reporting a problem to providing notification of a solution, responding, and providing feedback on the results is often done manually, which takes time and effort. Furthermore, if an appropriate solution is not adopted, the problem may be prolonged, resulting in further costs and a decline in reliability.

[1448] 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.

[1449] In this invention, the server includes means for receiving problems reported by users, means for the generative AI to analyze the received problems and generate solutions, means for notifying the building manager of the solutions, means for registering the problem reports in a database, means for the generative AI to identify the cause of the problem, and means for the generative AI to refer to a database of past troubles. This makes it possible to quickly and appropriately solve equipment malfunctions in buildings and hotels.

[1450] "User" refers to the individual or entity who discovers and reports a problem while using the Equipment.

[1451] "Means for receiving problems" refers to the function of receiving data on problems reported by users regarding equipment.

[1452] "Generative AI" refers to artificial intelligence that analyzes received data and automatically generates appropriate solutions.

[1453] "Means of analyzing problems and generating solutions" refers to the function of using generative AI to analyze the causes of problems and create solutions by referring to past data.

[1454] "Building manager" refers to the individual or organization responsible for managing the facilities of a building or facility and for implementing the solutions communicated by the generative AI.

[1455] "Means for notifying solutions" refers to a function for communicating the generated solutions to the building manager.

[1456] "Means for registering in a database" refers to the function of saving problems reported by users in a database with a unique ID.

[1457] "Means for identifying the cause of the problem" refers to the function of the generative AI to refer to past trouble data to identify the cause of the reported problem.

[1458] A "past trouble database" refers to a collection of information that stores detailed records of troubles that have occurred in the past and the solutions to those troubles.

[1459] "Equipment manufacturer" refers to the company or organization that manufactures the equipment and provides technical support.

[1460] "Means to adjust repair schedules" refers to the function of setting specific repair dates and times with the equipment manufacturer to resolve the problem.

[1461] "Means for notifying repair schedules" refers to a function for communicating the adjusted repair schedule to building managers and users.

[1462] The present invention provides a system for quickly and appropriately responding to equipment malfunctions in large facilities such as buildings and hotels. Specific embodiments for carrying out the present invention are described below.

[1463] System configuration

[1464] This system provides a platform for users, building managers, and equipment manufacturers to efficiently handle everything from reporting problems to resolving them. Its main components are a user terminal, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI.

[1465] Hardware and software used

[1466] User device: A device such as a smartphone, tablet, or computer.

[1467] Building manager's terminal: Devices such as PCs, tablets, and smartphones.

[1468] Equipment manufacturer terminal: Devices such as computers, tablets, and smartphones.

[1469] Server: A high-performance computer server equipped with generative AI that analyzes problems and generates solutions.

[1470] System operation explanation

[1471] Accepting problem reports

[1472] Terminal (user)

[1473] If a user experiences a problem with a building or hotel facility, they can report the problem through a smartphone app or web portal. For example, to report a problem like "The air conditioner in my office isn't working," they simply type "The air conditioner isn't working" into the app and attach photos or videos as needed. When the user presses the "Submit" button, the report is sent to the server.

[1474] Problem Report Database Registration

[1475] server

[1476] The server receives problem reports sent by users and records their contents in a database. At this time, details of the reported problem and attached photos and videos are saved together. A unique ID is also assigned to the report contents for management.

[1477] Problem analysis using generative AI models

[1478] server

[1479] Based on problem reports registered in the database, the generative AI model is instructed to perform an analysis. The generative AI model refers to past trouble data and performs an analysis to identify the cause of the problem. For example, in response to a report that "the air conditioner is not working," it will list possible causes, such as a power failure or a clogged filter.

[1480] Solution Generation

[1481] server

[1482] The generative AI model generates optimal solutions based on the analysis results. For example, the AI ​​might suggest basic solutions such as "Try turning the power off and on." If necessary, it also includes detailed instructions and precautions.

[1483] Solution Notification

[1484] server

[1485] The generated solution is sent to the building manager's terminal, and the notification includes a summary of the report along with the details of the solution.

[1486] Building manager's response

[1487] Terminal (Building Manager)

[1488] The building manager receives the notification and takes action according to the proposed solution, for example, turning the air conditioner off and on, and then reports the result to the server.

[1489] Reporting results and feedback

[1490] server

[1491] Receive reports from building managers to see if the problem has been resolved. If the problem has been resolved, record the information in a database and notify the user.

[1492] Escalation and cooperation with equipment manufacturers

[1493] server

[1494] If the problem cannot be resolved by the building manager, the generative AI model escalates the issue to the equipment manufacturer, who sends a detailed report and dispatches a technician to handle the issue as needed.

[1495] Response by equipment manufacturers

[1496] Terminal (equipment manufacturer)

[1497] An engineer from the equipment manufacturer will identify the problem and schedule a site visit or repair. This information is sent to the server.

[1498] Repair schedule notification

[1499] server

[1500] The set repair schedule is notified to the building manager and users, allowing users to know about the planned repairs in advance and make preparations.

[1501] Specific examples

[1502] For example, if a problem is reported that "the air conditioner in the office is not working," the following actions will be taken:

[1503] 1. Terminal (User)

[1504] A user reports "the air conditioner is not working" in the app and sends it with a photo attached.

[1505] 2. Server

[1506] Receives problem reports, stores them in a database, and directs the generative AI model to analyze them.

[1507] 3. Server

[1508] The AI ​​generates a solution such as "Try turning the power off and on" and notifies the building manager.

[1509] 4. Terminal (Building Manager)

[1510] The building manager attempts to operate the power supply, but the problem persists, so he reports the results to the server.

[1511] 5. Server

[1512] Escalate the issue to the equipment manufacturer and schedule a repair response.

[1513] 6. Terminal (equipment manufacturer)

[1514] The technician sets the schedule and the server notifies the building manager and users.

[1515] This makes it possible for the system of the present invention to quickly and efficiently resolve equipment problems in buildings and hotels.

[1516] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1517] Step 1:

[1518] User (Device):

[1519] Users report equipment problems through a smartphone app or web portal. They enter specific prompt text (e.g., "The air conditioner isn't working") into the app and attach photos and videos as needed. A problem report (text, photos, and videos) is generated based on the input data. When the user presses the "Submit" button, the entered problem report is sent to the server.

[1520] Step 2:

[1521] server:

[1522] The server records the problem reports received from users in a database. At this time, it receives the report content data (text, photos, videos) and records it with a unique ID. The input data is the problem report data from the user, and the output is the problem report stored in the database.

[1523] Step 3:

[1524] server:

[1525] Based on the problem reports registered in the database, the generative AI model is instructed to perform analysis. The generative AI model receives the details of the problem report as input data and searches for related information from a database of past troubles. Data processing involves analysis to identify the cause of the problem, and a list of possible causes is generated as output.

[1526] Step 4:

[1527] server:

[1528] The generative AI model generates an appropriate solution from the analysis results. The input data is the analysis results and past trouble data, and the solution is generated as a data calculation. The output is a specific solution (e.g., "Try turning the power off and on").

[1529] Step 5:

[1530] server:

[1531] The generated solution is notified to the building manager's terminal. The input data is the generated solution, and the output data is a solution notification message sent to the building manager. The server sends a notification to the building manager's terminal.

[1532] Step 6:

[1533] Building manager (terminal):

[1534] The building manager receives the solution notification and takes action according to the proposed solution. The input data is the solution notification sent from the server, and the output data is the result of the action taken by the building manager. The building manager actually operates the equipment (e.g., turning the power off / on).

[1535] Step 7:

[1536] server:

[1537] Receives a report from the building manager and verifies whether the problem has been resolved. The input data is the action taken by the building manager, and the data calculation verifies the resolution of the problem. The output data is the resolution status recorded in the database and a feedback message generated as needed.

[1538] Step 8:

[1539] server:

[1540] If the problem cannot be resolved by the building manager's actions, the server escalates the problem to the equipment manufacturer based on the instructions of the generated AI model. The input data are the building manager's actions and analysis results, and the output data is an escalation notification sent to the equipment manufacturer.

[1541] Step 9:

[1542] Equipment manufacturer (terminal):

[1543] The equipment manufacturer's technician receives the escalation notification, checks the problem, and arranges a site visit or repair schedule as necessary. The input data is the escalation notification, and the output data is the adjusted repair schedule.

[1544] Step 10:

[1545] server:

[1546] The set repair schedule is notified to the building manager and users. The input data is the adjusted repair schedule, and the output data is a schedule notification message sent to the building manager and users. By sending the notification from the server, users and building managers can know the repair schedule in advance.

[1547] (Application example 1)

[1548] 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."

[1549] The present invention aims to quickly and efficiently resolve problems that occur in equipment used in factories and other facilities. It also aims to reduce the burden on managers and engineers and improve productivity. In particular, it aims to improve the speed and accuracy of responses in factory equipment management by automating the entire process from reporting problems to implementing countermeasures and escalation.

[1550] 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.

[1551] In this invention, the server includes a means for receiving problems reported by users, a means for the generative AI to analyze the received problems and generate solutions, a means for notifying the administrator of the solutions, a means for the administrator to confirm the solutions and issue instructions to the equipment, and a means for the equipment to execute the instructed solutions. This allows for a smooth process from reporting problems to generating and executing solutions. It also reduces the burden on administrators and engineers and improves response speed.

[1552] 1. "User" refers to the employee or staff member who reports the issue within the factory or facility.

[1553] 2. "Generative AI" refers to an artificial intelligence system that analyzes incoming problems and generates solutions.

[1554] 3. "Manager" refers to a person in charge of managing equipment within a factory or facility.

[1555] 4. "Means for receiving problems" refers to the methods and tools by which problems reported by users are captured by the system.

[1556] 5. “Means of problem analysis” refers to the methods and tools that generative AI uses to understand the content of a problem and identify its causes.

[1557] 6. "Solution generation means" refers to methods or tools that propose solutions to problems analyzed by generative AI.

[1558] 7. "Solution notification means" refers to the methods and tools used to communicate generated solutions to management.

[1559] 8. "Means for verifying solutions and issuing instructions to equipment" refers to the methods and tools by which managers verify proposed solutions and issue instructions to equipment based on their content.

[1560] 9. "Equipment" refers to machinery and devices used within a factory or facility.

[1561] 10. "Means for implementing directed solutions" refers to the methods and tools by which the facility implements solutions as directed by management.

[1562] 11. "Technical Specialist" refers to a technical expert who will provide additional support if the generated solution does not resolve the issue.

[1563] 12. "Measures for coordinating response scheduling" refers to methods and tools for scheduling technical personnel to conduct on-site visits and follow-up responses.

[1564] 13. "Means for notifying adjusted response schedules" refers to methods and tools for notifying administrators and users of the set response schedules.

[1565] The present invention is a system that automates the process from reporting problems in facility management in factories and other facilities to generating and implementing solutions. The system is composed of a user terminal, an administrator terminal, facilities, and a server equipped with generative AI. Specific embodiments for implementing the present invention are described below.

[1566] User-reported problems

[1567] Users report equipment malfunctions using smartphones or robotics control terminals. The report is sent to the server in the form of text, photos, videos, etc. Consider the example where a user reports that "Machine A is not working" and attaches a photo to the report.

[1568] Server-based problem analysis and solution generation

[1569] The server analyzes the received problem report and generates a solution using generative AI. For example, a solution such as "Please restart machine A" may be generated. This generative AI compares the solution with a past database to select the optimal solution.

[1570] Notify administrator of solution

[1571] The generated solution is sent to the administrator's terminal. The administrator checks the solution and issues instructions to the equipment based on its contents. For example, the administrator sends an instruction to restart a factory robot.

[1572] Implementation of solutions by equipment

[1573] The factory robot follows instructions from the administrator and executes a solution. For example, it restarts machine A and reports the results to the server. If the solution is executed and the problem is solved, the process ends there, but if it is not solved, it moves on to the next step.

[1574] Escalation and Scheduling

[1575] If the generated solution does not resolve the problem, the server notifies a specialist engineer, who then schedules a response and notifies the administrator and user. This allows for a smooth response, such as an on-site visit.

[1576] The hardware used includes smartphones, robotics control terminals, factory robots, and servers, while the software includes smartphone apps for Android / iOS, robotics control software, generative AI, and a database management system.

[1577] Specific examples

[1578] 1. User device: A factory employee reports on their smartphone that "Machine A is not working" and attaches a photo.

[1579] 2. Server: The generative AI analyzes the problem and generates a solution: "Please restart machine A."

[1580] 3. Administrator terminal: The administrator checks the solution and sends a restart instruction to the factory robot.

[1581] 4. Equipment: The factory robot restarts Machine A and reports the results.

[1582] 5. Server: If the issue persists, escalate to a technician and schedule an on-site visit.

[1583] Prompt Sentence Examples

[1584] Analyze a problem report for a specific machine in the factory and generate and issue the optimal solution. Please use the following information:

[1585] Problem details: {Problem details text}

[1586] Additional information: {URL of photo or video}

[1587] In this way, the system can be used to quickly and efficiently solve facility management problems within a factory.

[1588] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1589] Step 1:

[1590] Entering a Problem Report

[1591] Users report equipment malfunctions using a smartphone app or robotics control terminal. Input includes text (e.g., "Machine A is not working"), photos, and videos. The user enters this information into the app and sends it to the server, which records the received report in a database.

[1592] Step 2:

[1593] Analyzing problems and generating solutions

[1594] The server passes the received report content to the generative AI. The generative AI analyzes the report content (text, photos, videos) and identifies the cause of the problem by comparing it with a database of past troubles. Based on this analysis, the generative AI generates a solution such as "Please restart machine A." The server records the generated solution in a database.

[1595] Step 3:

[1596] Solution Notification

[1597] The server notifies the generated solution to the administrator terminal. The administrator terminal receives the notification and displays the solution. For example, the administrator sees a message saying "Please restart machine A."

[1598] Step 4:

[1599] Instructions for implementing solutions

[1600] The manager checks the received solution and issues instructions to the factory robot based on the content. A reboot instruction is sent from the manager's terminal to the factory robot control system. For example, the manager presses the "reboot" button on the terminal, and the instruction is transmitted to the robot.

[1601] Step 5:

[1602] Implementing the solution

[1603] The factory robot restarts machine A based on instructions from the administrator. The robot actually performs the restart operation and sends the results to the administrator's terminal. The server records the results reported by the robot in a database.

[1604] Step 6:

[1605] Verify the problem is resolved

[1606] The administrator terminal receives the report from the robot and checks whether the problem has been resolved. If it has been resolved, it sends feedback to the server. If it has not been resolved, it proceeds to the next step. The server records this feedback in a database.

[1607] Step 7:

[1608] Escalation and Scheduling

[1609] If the generated solution does not solve the problem, the server notifies the specialist engineer of the problem. The engineer's terminal receives the notification from the server. The engineer adjusts a response schedule, such as a facility visit, and reports it to the server. The server notifies the administrator and user of the adjusted schedule.

[1610] Step 8:

[1611] Schedule Notifications

[1612] Users and administrators receive schedule notifications from the server and prepare for the response. The server records the notification content in a database. This completes the entire process, ensuring a smooth process from reporting the problem to responding to it.

[1613] 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.

[1614] The present invention is a system for analyzing problems reported by users and their emotions at the time, and for solving the problems quickly and accurately. A specific embodiment of the present invention combined with an emotion engine is shown below.

[1615] This system consists of a user terminal equipped with an emotion engine, a building manager terminal, an equipment manufacturer terminal, and a server equipped with generative AI. By using the emotion engine, it is possible to analyze the emotional state of the user when reporting a problem and provide a more effective solution.

[1616] System Operation

[1617] Receiving problem reports and analyzing sentiment

[1618] Terminal (user):

[1619] When a user opens the app or web portal and enters details of a problem, such as "my air conditioner isn't working," into a problem report form, the emotion engine analyzes the user's input and voice (in the case of voice input) to determine emotions, such as frustration, anger, or worry.

[1620] Device:

[1621] The user enters the details of the problem and presses the "Submit" button. The emotion data is sent to the server along with the problem report.

[1622] Analyzing problems and generating solutions

[1623] server:

[1624] The server receives user reports of problems, records their content and emotional data in a database, and simultaneously instructs the generative AI to analyze the problem.

[1625] server:

[1626] The generative AI analyzes the received report and emotional data, and identifies the cause of the problem by comparing it with a database of past problems. When generating solutions based on the analysis results, it takes into account emotional data to suggest high-priority solutions that reduce the user's frustration. For example, a solution might be generated such as, "Try turning the power off and on. If the problem persists, please contact us again."

[1627] Notification and Implementation of Solutions

[1628] server:

[1629] The generated solution is notified to the building manager's terminal, who then checks the proposed solution and attempts to address the equipment.

[1630] Terminal (Building Manager):

[1631] The building manager receives a notification, checks for a solution via the app or web portal, and then turns the air conditioner off and on according to the solution.

[1632] Applications of the Emotion Engine:

[1633] The terminal (building manager) inputs the results of the operation into the server, and generates a report that takes into account the user's emotional state through an emotion engine. For example, a follow-up message such as "We apologize for the inconvenience, but we tried turning the power off and on again, but that did not resolve the problem. We will try another method."

[1634] Escalation and cooperation with equipment manufacturers

[1635] server:

[1636] If the problem persists despite the solutions attempted by the building manager, the generative AI will notify the equipment manufacturer of the situation.

[1637] Terminal (equipment manufacturer):

[1638] An engineer from the equipment manufacturer will review the report and the sentiment data, and schedule a site visit. Once the schedule is decided, it will be notified to the server.

[1639] Schedule Notifications

[1640] server:

[1641] The adjusted repair schedule is then communicated to building managers and users, allowing users to be aware of upcoming repairs and make preparations in advance.

[1642] Specific examples

[1643] Example 1: Air conditioner malfunction

[1644] 1. Terminal (User):

[1645] A user reports in the app that the air conditioner isn't working, expressing extreme frustration.

[1646] The emotion engine analyzes frustration and sends the emotional data to the server.

[1647] 2. Server:

[1648] Receives problem reports and emotional data and instructs generative AI to analyze them.

[1649] The AI ​​generates a solution, such as "Try turning the power off and on. If the problem persists, please contact us again," and notifies the building manager.

[1650] 3. Terminal (Building Manager):

[1651] The building manager reported that he tried turning the air conditioner on and off but was unable to resolve the issue.

[1652] The emotion engine generates follow-up messages to ease user frustration.

[1653] 4. Server:

[1654] Escalate issues to equipment manufacturers and schedule repairs.

[1655] 5. Terminal (equipment manufacturer):

[1656] The technician sets the schedule, and the server notifies the building manager and users of the information.

[1657] In this way, the present invention makes it possible to quickly and efficiently resolve facility problems in buildings and hotels while also taking into consideration the feelings of users.

[1658] The processing flow will be explained below.

[1659] Step 1:

[1660] Device (user): The user opens the app or web portal and enters details of the problem into the problem report form, such as "my air conditioner isn't working." At the same time, the emotion engine analyzes the user's input (text or voice) to identify emotions, such as frustration, anger, or worry.

[1661] Step 2:

[1662] Terminal: The user enters details of the problem and emotional data and presses the "Send" button. The problem report and emotional data are sent to the server.

[1663] Step 3:

[1664] Server: The server receives the defect report and emotion data from the user and records the details in a database. The record contents include details of the reported defect, date and time, emotion data, and attached files.

[1665] Step 4:

[1666] Server: The generative AI retrieves new defect reports from the database, analyzes the report content and emotional data, and identifies the cause of the problem by comparing it with a database of past problems.

[1667] Step 5:

[1668] Server: The generative AI generates solutions based on the analysis results. It takes into account emotional data and suggests high-priority solutions that reduce the user's frustration. For example, it generates a solution such as "Try turning the power off and on. If the problem persists, please contact us again."

[1669] Step 6:

[1670] Server: Notifies the generated solution to the building manager's terminal.

[1671] Step 7:

[1672] Device (Building Manager): The building manager receives a notification, checks the solution via the app or web portal, and turns the air conditioner off / on according to the solution.

[1673] Step 8:

[1674] Terminal (Building Manager): The building manager enters the results of the operation into the app and reports them to the server. If the problem is resolved, this is fed back to the system.

[1675] Step 9:

[1676] Server: Receives reports from building managers and the generative AI determines the next steps. If the problem is not resolved, it escalates to the equipment manufacturer.

[1677] Step 10:

[1678] Server: The generative AI notifies the equipment manufacturer of the details of the problem and the results of the building manager's trial.

[1679] Step 11:

[1680] Terminal (Equipment Manufacturer): The equipment manufacturer's engineer checks the report and emotion data, and arranges the date for the on-site visit. Once the schedule is decided, the engineer contacts the server.

[1681] Step 12:

[1682] Server: Notifies the building manager and users of the adjusted repair schedule.

[1683] Step 13:

[1684] Terminals (building managers and users): Check the repair schedule and make the necessary preparations.

[1685] Step 14:

[1686] Terminal (Building Manager): The building manager sends a follow-up message generated by the emotion engine to the user along with the results of the operation. For example, "We apologize for the inconvenience, but the problem was not resolved after power cycling. We will try another method."

[1687] This series of processing steps allows building and hotel equipment problems to be resolved quickly and efficiently, while also properly managing the emotions of users.

[1688] Example 2

[1689] 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."

[1690] Conventional building and facility management systems handle problems reported by users without considering their emotional state, which has prevented them from fully increasing user satisfaction. Furthermore, they are unable to properly analyze and utilize emotional data, resulting in problems that are not resolved quickly or accurately. Therefore, there is a need for a system that can resolve problems quickly and accurately while taking into account the emotions of users.

[1691] 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.

[1692] In this invention, the server includes a means for receiving a problem reported by a user and analyzing the emotional state of the user at the time, a means for the generative AI model to analyze the received problem and emotional data and generate a solution, and a means for notifying the building manager of the generated solution, which enables the problem to be solved quickly and accurately while taking the user's emotions into consideration.

[1693] "User" means a person who uses the system to report a problem.

[1694] "Emotional state" refers to the emotional state that a user exhibits when reporting a problem, such as frustration, anger, or worry.

[1695] "Generative AI model" refers to an artificial intelligence system that analyzes received problem and emotion data and automatically generates solutions.

[1696] A "building manager" is a person who manages and repairs facilities based on reported problems and generated solutions.

[1697] "Means of notification" refers to a mechanism for transmitting information from the server to building managers and users, and includes, for example, sending messages via email or an application.

[1698] "Equipment manufacturer" refers to the manufacturer of the equipment, and is the party to which you should contact if the problem cannot be resolved.

[1699] "Repair Schedule" means the dates for carrying out repair work on equipment.

[1700] "Means for analysis" refers to the techniques and processes used to analyze received data, identify causes of problems, and generate solutions.

[1701] "Means of receiving" refers to the mechanism for obtaining data from users and building managers.

[1702] "Means for reporting" refers to a system that allows the building manager to communicate the results of attempting the generated solutions to the server.

[1703] "Means of escalation" refers to the method of communicating information to the equipment manufacturer when a specific issue requires a more advanced response.

[1704] This invention uses a system that combines an emotion engine to analyze problems reported by users and their emotions at the time, and solves the problems quickly and accurately. The system is composed of a user terminal equipped with an emotion engine, a building manager terminal, an equipment manufacturer terminal, and a server equipped with a generative AI model.

[1705] System configuration

[1706] The system consists of the following main components:

[1707] 1. User terminal: Enter and send problem reports and emotional data.

[1708] 2. Emotion engine: Analyzes the user's emotional state from their input and voice.

[1709] 3. Server: Analyzes the received data and generates solutions.

[1710] 4. Generative AI models: Analyze problem and emotion data and automatically generate solutions.

[1711] 5. Building manager terminal: Receives solutions and reports implementation results.

[1712] 6. Equipment Manufacturer Terminal: Escalates issues and coordinates repair schedules.

[1713] The role of each element

[1714] User terminal

[1715] The user terminal is provided in the form of an application or web portal, and is used by the user to enter details of the problem into a problem report form. If voice input is possible, it also has an interface for analyzing emotions from the user's voice. For example, when a user reports that "the air conditioner is not working," the emotion engine detects frustration.

[1716] Emotion Engine

[1717] The emotion engine uses natural language processing and speech analysis technologies to extract the user's emotions. For example, it identifies emotions such as frustration, anger, and worry from the input text and sends the analysis results to the server.

[1718] server

[1719] The server records the received report and emotional data in a database and instructs the generative AI to analyze it. Based on the analysis results, it generates a solution that takes the user's emotions into consideration. For example, the generative AI might suggest a solution such as, "Try turning the power off and on. If the problem persists, please contact us again."

[1720] Generative AI Models

[1721] The generative AI model identifies the cause of the problem and generates a solution by comparing it with a huge database of problems. Taking into account emotional measurement data, it is able to provide high-priority solutions that reduce the user's frustration. An example of a specific prompt is, "The air conditioner is not working. Frustration has been detected from the user's input. Please generate a solution that takes into account the emotional data."

[1722] Building manager terminal

[1723] The building manager's terminal receives the solution notified by the server, attempts to deal with the equipment, reports the results to the server, and generates a follow-up message if necessary.

[1724] Equipment manufacturer terminal

[1725] The equipment manufacturer's terminal receives notification of problem escalation and adjusts the repair schedule, which allows for efficient scheduling of on-site visits.

[1726] Specific scenarios

[1727] For example, when a user reports that the air conditioner is not working, the emotion engine detects the user's frustration. This data is received by the server, and the generative AI generates a solution such as "Please try turning the power off and on. If the problem persists, please contact us again." The building manager is then notified, and if the problem is not resolved, it is escalated to the equipment manufacturer. The equipment manufacturer adjusts the repair schedule and notifies the user.

[1728] In this way, the present invention provides a system that takes into account the user's feelings and solves problems quickly and accurately.

[1729] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1730] Step 1:

[1731] User-entered problem report

[1732] Terminal (user):

[1733] A user opens an application or web portal on their device and enters details of the problem into a problem report form. The input can be in text or voice format, for example, "The air conditioner is not working." The input text or voice is then saved on the device (output).

[1734] Step 2:

[1735] Emotion analysis using an emotion engine

[1736] Terminal (user):

[1737] The emotion engine analyzes input text and voice to extract the user's emotional state. Using natural language processing technology, emotions such as "I feel very frustrated" are analyzed (input). As a result of the analysis, emotional data is generated and stored on the device (output).

[1738] Step 3:

[1739] Receiving report content and emotion data on the server

[1740] server:

[1741] The system receives the defect report and emotion data sent from the device. The problem details and emotion data entered by the user are recorded in the server's database (input). This makes the report details and emotion data stored in the database available on the server side (output).

[1742] Step 4:

[1743] Analyzing problems and generating solutions using generative AI

[1744] server:

[1745] Based on the received data, the server instructs the generative AI to analyze the problem. The generative AI compares the report with a database of past problems to identify the cause of the problem (input). Based on the analysis results, a specific solution is generated (output), such as "Try turning the power off and on. If the problem persists, please contact us again."

[1746] Step 5:

[1747] Server notification of solution

[1748] server:

[1749] The generated solution is notified to the building manager's terminal. The generated solution and emotion data are sent from the server to the building manager's terminal (input). A notification is displayed on the building manager's terminal so that the building manager can check it (output).

[1750] Step 6:

[1751] Building manager implements solutions and reports results

[1752] Terminal (Building Manager):

[1753] The building manager receives the notification and checks for a solution via the app or web portal. The building manager then performs the power off / on operation on the air conditioner (input). The device then reports the results of the operation to the server, sending a report such as "I tried the operation but it did not resolve the problem" (output).

[1754] Step 7:

[1755] Server-driven escalation and repair schedule notifications

[1756] server:

[1757] If the problem persists despite the attempted solutions, the generative AI escalates the issue to the equipment manufacturer (input). An engineer at the equipment manufacturer reviews the problem report and emotion data, arranges a date for an on-site visit, and notifies the server of the schedule (output).

[1758] Step 8:

[1759] Repair schedule notification

[1760] server:

[1761] The adjusted repair schedule is notified to the building manager and users (input), allowing users and building managers to be aware of the planned repairs in advance and make preparations (output).

[1762] The above are the specific processing steps of the system. This is a flow that includes the input and output of data, as well as the specific operations performed at each step.

[1763] (Application example 2)

[1764] 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."

[1765] While conventional troubleshooting systems were able to receive and analyze problems reported by users, they were unable to generate solutions that took into account the user's emotional state. As a result, it was difficult to alleviate users' frustration, especially in high-stress environments. Furthermore, when the problem persisted even after factory managers implemented solutions, it was often difficult to provide appropriate follow-up or coordinate smoothly with the equipment manufacturer.

[1766] 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 a means for receiving a problem reported by a user, a means for a generative AI to analyze the received problem and generate a solution, a means for using an emotion engine to analyze the user's emotional state, and a means for notifying the factory manager of the solution. This enables a prompt and accurate solution to be provided while taking the user's emotional state into consideration. Furthermore, by providing a means for the factory manager to try the generated solution and report the results, and a means for determining the next step based on the reported results and emotion data, the efficiency of problem solving is improved. Furthermore, by providing a means for notifying the manufacturing equipment manufacturer of the problem if the generated solution does not solve the problem, a means for coordinating a repair schedule with the manufacturing equipment manufacturer, and a means for notifying the factory manager and the user of the adjusted repair schedule, follow-up for problem resolution can be carried out smoothly.

[1767] "User" means any person or entity that uses the System to report a Problem.

[1768] A "means for receiving problems" is an interface or device for receiving problems reported by users.

[1769] "Generative AI" is a system or algorithm that uses artificial intelligence techniques to analyze incoming problems and generate optimal solutions.

[1770] An "emotion engine" is software or hardware that analyzes emotions from a user's input data (text or voice) and extracts their emotional state.

[1771] A "factory manager" is an employee or staff member in charge of managing production lines and equipment within a factory.

[1772] "Means for notification" refers to the communications infrastructure or devices used to transmit generated solutions and status information to designated recipients.

[1773] The "means for analyzing the problem" refers to a processing device or software for analyzing the content of the received problem.

[1774] A "means for generating solutions" is a system or program that has the function of proposing appropriate solutions based on the analysis results.

[1775] "Emotional state" refers to the psychological state, such as frustration, anger, or worry, that a user feels when reporting a problem.

[1776] A "next step decision method" is a system or algorithm that determines the next action to take based on the reported solution results and sentiment data.

[1777] A "manufacturing equipment manufacturer" is a company that designs, manufactures, sells, and maintains manufacturing equipment used in factories.

[1778] "Means for coordinating repair schedules" means the systems and procedures for scheduling equipment repairs and inspections and communicating with relevant parties.

[1779] "Means of notifying users" are the means of communication or devices used to communicate schedules and resolution results to users.

[1780] This invention includes a troubleshooting support system installed in a robot operating on a factory production line. The specific configuration and operation will be described below.

[1781] First, a factory worker who will be the user uses a device such as a smartphone or tablet to report a problem with a robot on the production line. For example, a problem might be that the robot's arm has stopped mid-operation. Reports can be made using text input or voice input, and the emotion engine analyzes the user's emotional state (frustration, anger, worry, etc.) from this input data.

[1782] The emotion engine uses natural language processing technology to analyze input text and voice data and extract the user's emotional state. This emotional data is sent to the server along with the problem report data and recorded in a database.

[1783] The server analyzes the problem using a generative AI model based on the received problem report and emotional data. The generative AI model compares the results with a database of past problems and generates the optimal solution. The model also takes into account the emotional data and proposes high-priority solutions that reduce user frustration.

[1784] The generated solution is sent to the factory manager's device via the notification system. The factory manager receives the notification, checks the solution through an application or web portal, and implements it. For example, specific actions such as "Please restart the power supply of the arm. Also, please check the contact sensor" are displayed.

[1785] When the factory manager reports the results of the solution attempt to the server, the emotion engine also generates a follow-up message based on the user's emotional state, such as "We apologize for the inconvenience, but we tried cycling the power but it did not resolve the problem. We will try another method."

[1786] If the generated solution does not resolve the problem, the server automatically escalates the issue to the manufacturing equipment manufacturer. The manufacturer's technicians review the report and sentiment data and schedule an on-site visit. The adjusted repair schedule is then notified to the factory manager and users via the server.

[1787] This makes it possible to quickly and efficiently resolve problems with manufacturing robots in factories, and to provide courteous support that takes into account the emotional state of the user.

[1788] Prompt Sentence Examples

[1789] "Analyze problem report text entered from a smartphone, extract sentiment data, and generate solutions based on generative AI models."

[1790] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1791] Step 1:

[1792] Users use a smartphone or tablet to report a problem with a robot on a manufacturing line. They can enter text or voice input, and the input includes details of the problem, such as "The robot's arm is stuck mid-way." This is the input data. The output is the problem report data.

[1793] Step 2:

[1794] The device receives the problem report data and performs emotion analysis using an emotion engine. The emotion engine uses natural language processing technology to extract the user's emotional state (frustration, anger, worry, etc.) from the text and voice data. The input data is text and voice input, and the output data is the analysis result including the emotional state.

[1795] Step 3:

[1796] The device sends the analyzed emotion data and problem report data to the server, which records these data in a database. In this step, the input data is converted into a database format and processed for storage. As an output, confirmation information of the recorded data is generated.

[1797] Step 4:

[1798] The server analyzes the problem using a generative AI model based on the received problem report and emotion data. The generative AI model compares the results with a database of past problems and generates the optimal solution. Here, the problem is analyzed using a matching algorithm with the problem database. The input data is the problem report and emotion data, and the output is the generated solution.

[1799] Step 5:

[1800] The server notifies the generated solution to the factory manager's terminal through the notification system. The factory manager checks and implements the solution through an application or web portal. In this step, the solution is used as input data and a notification message is generated as output data.

[1801] Step 6:

[1802] The factory manager attempts the generated solution and reports the results to the server. The terminal also generates a follow-up message based on the user's emotional state using an emotion engine. The input data is the trial result data and emotion data, and the output data is the follow-up message.

[1803] Step 7:

[1804] If the generated solution does not resolve the problem, the server automatically escalates the problem to the manufacturing equipment manufacturer. The server checks the report content and sentiment data and schedules an on-site visit. The input data is the unresolved problem report, and the output data is the escalation notification.

[1805] Step 8:

[1806] The adjusted repair schedule is then sent back to the server to be notified to the factory manager and user terminals. The server processes the schedule information and generates a notification message in an appropriate format. The input data is the repair schedule, and the output data is the notification message.

[1807] 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.

[1808] 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.

[1809] 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.

[1810] 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.

[1811] 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.

[1812] 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.

[1813] 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).

[1814] 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.

[1815] 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."

[1816] 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.

[1817] 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).

[1818] 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.

[1819] 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.

[1820] 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.

[1821] 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.

[1822] 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.

[1823] 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.

[1824] 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.

[1825] 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.

[1826] 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.

[1827] 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.

[1828] The following is further disclosed regarding the above embodiment.

[1829] (Claim 1)

[1830] means for receiving user reported problems;

[1831] A means for the generative AI to analyze the received problem and generate a solution;

[1832] a means of informing building managers of the solution;

[1833] A system including:

[1834] (Claim 2)

[1835] a means for the building manager to attempt the generated solutions and report the results;

[1836] A means of determining next steps based on the reported results; and

[1837] 10. The system of claim 1, comprising:

[1838] (Claim 3)

[1839] a means of notifying the equipment manufacturer of the problem if the generated solution does not resolve the problem;

[1840] A means of coordinating repair schedules with equipment manufacturers;

[1841] a means of notifying building managers and occupants of the adjusted repair schedule;

[1842] 10. The system of claim 1, comprising:

[1843] "Example 1"

[1844] (Claim 1)

[1845] means for receiving user reported problems;

[1846] A means for the generative AI to analyze the received problem and generate a solution;

[1847] a means of informing building managers of the solution;

[1848] a means for registering problem reports in a database;

[1849] How generative AI can identify the cause of a problem,

[1850] A means for generative AI to refer to a database of past problems,

[1851] A system including:

[1852] (Claim 2)

[1853] a means for the building manager to attempt the generated solutions and report the results;

[1854] A means of determining next steps based on the reported results; and

[1855] means for notifying a user of a repair schedule;

[1856] 10. The system of claim 1, comprising:

[1857] (Claim 3)

[1858] a means of notifying the equipment manufacturer of the problem if the generated solution does not resolve the problem;

[1859] A means of coordinating repair schedules with equipment manufacturers;

[1860] a means of notifying building managers and occupants of the adjusted repair schedule;

[1861] 10. The system of claim 1, comprising:

[1862] "Application Example 1"

[1863] (Claim 1)

[1864] means for receiving user reported problems;

[1865] A means for the generative AI to analyze the received problem and generate a solution;

[1866] A means of notifying administrators of the solution;

[1867] A means for managers to check solutions and give instructions to the equipment,

[1868] A means by which the facility implements the indicated solution; and

[1869] A system including:

[1870] (Claim 2)

[1871] a means for the administrator to attempt the generated solutions and report the results;

[1872] A means of determining next steps based on the reported results; and

[1873] The means by which the facility implements the solution based on the manager's instructions; and

[1874] 10. The system of claim 1, comprising:

[1875] (Claim 3)

[1876] a means of notifying a technical expert of the problem if the generated solution does not resolve the problem;

[1877] A means of coordinating response schedules with specialized technicians; and

[1878] a means for notifying administrators and users of the adjusted response schedule;

[1879] 10. The system of claim 1, comprising:

[1880] "Example 2: Combining Emotion Engines"

[1881] (Claim 1)

[1882] means for receiving a problem reported by a user and analyzing the emotional state of the user at that time;

[1883] a means for the generative AI model to analyze the received problem and emotion data and generate a solution;

[1884] a means for notifying the building manager of the generated solution;

[1885] A system including:

[1886] (Claim 2)

[1887] A means for the building manager to implement the generated solution and report the implementation results;

[1888] a means for determining next steps based on the reported performance results and the user's emotional state;

[1889] 10. The system of claim 1, comprising:

[1890] (Claim 3)

[1891] a means of notifying the equipment manufacturer of the problem if the generated solution does not resolve the problem;

[1892] A means of coordinating repair schedules with equipment manufacturers;

[1893] a means of notifying building managers and occupants of the adjusted repair schedule;

[1894] 10. The system of claim 1, comprising:

[1895] "Application example 2 when combining emotion engines"

[1896] (Claim 1)

[1897] means for receiving user reported problems;

[1898] A means for the generative AI to analyze the received problem and generate a solution;

[1899] using an emotion engine to analyze the user's emotional state;

[1900] a means of informing factory management of the solution;

[1901] ...

[1902] A system including:

[1903] (Claim 2)

[1904] a means for the plant manager to attempt the generated solutions and report the results;

[1905] a means for determining next steps based on the reported results and sentiment data;

[1906] 10. The system of claim 1, comprising:

[1907] (Claim 3)

[1908] a means for notifying the equipment manufacturer of the problem if the generated solution does not resolve the problem;

[1909] A means of coordinating repair schedules with manufacturing equipment manufacturers;

[1910] a means for notifying plant management and users of the adjusted repair schedule;

[1911] 10. The system of claim 1, comprising: [Explanation of symbols]

[1912] 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. means for receiving user reported problems; A means for the generative AI to analyze the received problem and generate a solution; a means of informing building managers of the solution; A system including:

2. a means for the building manager to attempt the generated solutions and report the results; A means of determining next steps based on the reported results; and The system of claim 1 , comprising:

3. a means of notifying the equipment manufacturer of the problem if the generated solution does not resolve the problem; A means of coordinating repair schedules with equipment manufacturers; a means of notifying building managers and occupants of the adjusted repair schedule; The system of claim 1 , comprising:

Images