System

Abstract

A system is provided.SOLUTION: A system including means for allowing a user to select a check item of an automobile, means for acquiring an image of the automobile using a camera of a smartphone, means for acquiring a voice datum of the automobile using a microphone of the smartphone, means for transmitting the acquired image and voice datum to a server, means for analyzing the transmitted image and voice datum using a generative AI model in the server, and means for notifying the user of an analysis result.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] With the increasing incidence of vehicle troubles such as wheel slippage and battery malfunctions, it is difficult for car owners to perform highly accurate inspections, and self-inspections are particularly difficult for users with little knowledge of automobiles. Furthermore, the automatic inspection functions installed in luxury cars are expensive, so there is a demand for an easy, inexpensive method that is accessible to a wide range of users. The objective of this invention is to solve these problems and provide safe and efficient vehicle inspections. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for allowing a user to select vehicle inspection items, a means for capturing images of the vehicle using a smartphone camera, a means for capturing audio data of the vehicle using a smartphone microphone, a means for transmitting the captured image and audio data to a server, a means for analyzing the transmitted image and audio data using a generative AI model in the server, and a means for notifying the user of the analysis results. This allows users to easily perform high-precision vehicle inspections and prevent problems from occurring.

[0006] "User" refers to a person who operates the system, and is a concept that includes individuals or corporations who wish to inspect their automobiles.

[0007] "Inspection items" refers to a checklist for evaluating each part and condition of a vehicle, including tires and engine noise.

[0008] A "smartphone" refers to a portable computing device equipped with features such as internet connectivity, a camera, and a microphone.

[0009] The term "camera" refers to a device for taking still images and videos, and in the present invention includes those built into smartphones.

[0010] A "microphone" refers to a device that picks up sound and converts it into an electrical signal, and in the present invention includes those built into smartphones.

[0011] "Image" refers to visual data captured using a camera.

[0012] "Audio data" refers to sound information recorded using a microphone.

[0013] "Server" refers to a remote computer system that processes data over a network.

[0014] A "generative AI model" refers to an artificial intelligence model trained using techniques such as machine learning and deep learning.

[0015] "Analysis" refers to the process of processing acquired data to evaluate or diagnose its content.

[0016] "Notification" refers to a means of communicating the analysis results to the user. [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] A specific embodiment for carrying out the present invention will be described in detail. The system described below allows a user to perform a pre-boarding inspection of a vehicle using a smartphone. This system uses the smartphone's camera and microphone, and transmits the acquired data to a server for analysis, thereby achieving highly accurate vehicle inspections.

[0039] System configuration

[0040] The main components of the system are:

[0041] User: The individual who operates the smartphone and performs the vehicle inspection.

[0042] Device: A smartphone used for vehicle inspections, equipped with a built-in camera and microphone.

[0043] Server: A remote computer system that analyzes the acquired data using a generative AI model.

[0044] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[0045] Explanation of program processing

[0046] 1. User operations and data acquisition

[0047] The user starts the dedicated app on their smartphone and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[0048] 2. Check your tires

[0049] The device uses the camera to take photos of each tire to check its condition. When taking photos, the app guides the user on the shooting position and angle. The photos are temporarily saved on the smartphone and then automatically sent to the server.

[0050] The server inputs the received photos into a generative AI model to analyze tire pressure, loose screws, and distortion. Once the analysis is complete, the results are notified to the user.

[0051] 3. Inspect the vehicle body

[0052] To check the overall condition of the vehicle, the user takes a photo of the vehicle using the smartphone camera. The app guides the user to take an appropriate photo by specifying the shooting position and angle. The captured photo of the vehicle is temporarily saved on the smartphone and then sent to the server.

[0053] The server inputs the received photos of the car body into a generative AI model, which analyzes the car for scratches, cracks in the glass, and dangerous distortions. The results of the analysis are then notified to the user.

[0054] 4. Check the sound when starting the engine

[0055] The user follows the app's instructions to record the engine sound using the smartphone's microphone. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[0056] The server inputs the received audio data into a generative AI model to analyze any abnormalities in the engine start-up sound. The server notifies the user of the analysis results and advises them on the necessary measures.

[0057] 5. Check the engine sound after starting

[0058] The user records the engine sound for a certain period of time after the engine starts. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[0059] The server inputs the received audio data into a generative AI model to analyze the engine sound for abnormalities. If an abnormality is detected, the analysis results are sent to the user as a notification containing details.

[0060] Specific examples

[0061] Examples of tire inspections:

[0062] 1. The user launches the app and selects "Tire Inspection."

[0063] 2. The app will prompt you to take a photo of the left front tire.

[0064] 3. The user uses their smartphone to take a photo of the left front tire.

[0065] 4. The photo is sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[0066] 5. The server notifies the user of the analysis results and sends a message such as "There is a loose screw in the left front tire."

[0067] Examples of engine sound checks:

[0068] 1. The user launches the app and selects "Check Engine Sound."

[0069] 2. The app will prompt you to "Start the engine and record the sound."

[0070] 3. The user starts the engine and records the sound.

[0071] 4. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[0072] 5. The server detects an abnormal sound and notifies the user that "there is something wrong with the engine startup sound."

[0073] As described above, the user can perform highly accurate vehicle inspections with simple operations.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] The user launches the dedicated app on their smartphone and selects an inspection item (e.g., tire inspection, vehicle body inspection, engine sound inspection) from the main screen.

[0077] Step 2:

[0078] The app will then display specific instructions for the inspection item selected by the user (e.g., "Take a photo of the left front tire").

[0079] Step 3:

[0080] The user uses the smartphone camera to take a photo of the specified area according to the instructions (e.g., a photo of the left front tire).

[0081] Step 4:

[0082] The device temporarily stores the captured photos in its internal storage.

[0083] Step 5:

[0084] The device transmits the stored photo data to a server via the Internet.

[0085] Step 6:

[0086] The server receives the transmitted photo data and inputs it into the generative AI model.

[0087] Step 7:

[0088] The server uses a generative AI model to analyze the photo data and detect, for example, tire pressure, loose screws, and distortions.

[0089] Step 8:

[0090] The server generates the analysis results and organizes them, including details of any problems.

[0091] Step 9:

[0092] The server sends the analysis results to the device.

[0093] Step 10:

[0094] The device notifies the user of the analysis results it has received, including a specific message such as, "There is a loose screw in the left front tire."

[0095] Step 11:

[0096] The user checks the notification and takes appropriate measures as instructed, if necessary (e.g., check the tire screws and correct any looseness).

[0097] Engine sound inspections follow similar steps, but use a smartphone's microphone instead of a camera to analyze the recorded audio data. Specifically, the engine sound is recorded, the recorded data is sent to a server, analyzed by a generative AI model, and the user is notified if any abnormalities are detected. In this way, the system is designed to enable users to easily perform high-precision vehicle inspections.

[0098] Example 1

[0099] 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."

[0100] Conventional vehicle inspection systems require specialized knowledge and advanced equipment, making it difficult for general users to easily perform pre-inspections of their vehicles. Furthermore, they are limited to simply checking inspection items, and even if a problem is discovered, it is difficult to obtain analysis results that lead to details and countermeasures. This has led to many vehicle owners neglecting daily inspections, resulting in an increased risk of accidents and breakdowns.

[0101] 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.

[0102] In this invention, the server includes means for allowing a user to select vehicle inspection items, means for capturing images of the vehicle using a camera of a mobile device, means for capturing audio data of the vehicle using a microphone of the mobile device, means for transmitting the captured image and audio data to a remote computer system, means for analyzing the transmitted image and audio data using a generative AI model in the remote computer system, means for guiding the user to appropriate shooting positions and angles according to the inspection items, and means for notifying the user of the analysis results upon completion of the analysis. This enables general users to easily perform high-precision pre-inspections of their vehicles using their smartphones.

[0103] "User" refers to an individual who operates a mobile terminal to perform an automobile inspection.

[0104] "Mobile device" means a mobile electronic device containing a camera and microphone used for motor vehicle inspections.

[0105] "Camera" refers to a device for taking images and acquiring the data.

[0106] A "microphone" refers to a device for recording sound and acquiring that data.

[0107] "Server" refers to a remote computer system for receiving and analyzing data, generating results and notifying the user.

[0108] "Generative AI model" refers to an algorithm that uses machine learning to analyze transmitted image and audio data.

[0109] "Inspection item" refers to an action that the user can select to inspect a specific part of the vehicle.

[0110] A "prompt sentence" refers to a sentence that indicates the next operation or instruction to the user.

[0111] "Analysis results" refers to the diagnostic information obtained after data analysis is performed by a generative AI model.

[0112] "Remote computer system" refers to a computer system at a remote location that is used to receive and analyze data transmitted from a mobile device.

[0113] MODE FOR CARRYING OUT THE INVENTION

[0114] A specific embodiment for carrying out the present invention will be described in detail. This system allows a user to perform a pre-ride inspection of a vehicle using a mobile device. This system uses the camera and microphone of the mobile device, and transmits the acquired data to a server for analysis, thereby achieving highly accurate vehicle inspections.

[0115] System Components

[0116] The main components of the system are:

[0117] User: The individual who operates the mobile device and performs the vehicle inspection.

[0118] Terminal: A mobile terminal used for vehicle inspections, equipped with a camera and microphone.

[0119] Server: A remote computer system that analyzes the acquired data using generative AI models.

[0120] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[0121] Program processing overview

[0122] 1. The user launches the dedicated app on their mobile device and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[0123] 2. The device uses the camera to capture images for each inspection item. For example, if inspecting tires, the app will guide the user on the shooting position and angle, and the user will follow the instructions to take a photo of the tires. The captured image is temporarily stored on the device and then sent to the server.

[0124] 3. The device uses a microphone to capture audio data. For example, if you are checking the engine sound, it will record the sound when the engine starts, store the data temporarily on the device, and then send it to the server.

[0125] 4. The server inputs the received image and audio data into a generative AI model, which analyzes tire pressure, loose screws, distortions, scratches on the body, cracked glass, dangerous distortions, and abnormal engine start-up sounds.

[0126] 5. The server notifies the user of the analysis results, for example, sending a message such as "There is a loose screw in the left front tire" or "There is something unusual about the engine start-up sound."

[0127] Examples of concrete examples and prompts

[0128] Consider the following scenario:

[0129] 1. The user launches the app and selects "Tire Inspection."

[0130] Example prompt: "Take a photo of the left front tire."

[0131] 2. Following the prompts from the app, the user takes a photo of the left front tire using their smartphone camera.

[0132] 3. The photos are sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[0133] 4. The server notifies the user with the message "There is a loose screw in the left front tire."

[0134] Also, specific examples of engine sound checks include:

[0135] 1. The user launches the app and selects "Check Engine Sound."

[0136] Example prompt: "Start the engine and record the sound."

[0137] 2. The user starts the engine and records the sound.

[0138] 3. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[0139] 4. The server notifies the user that "there is something wrong with the engine start-up sound."

[0140] As explained above, users can perform highly accurate vehicle inspections with simple operations. This allows general users to know the condition of their vehicles in real time, enabling safe and efficient vehicle management.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Program processing flow

[0143] Step 1:

[0144] The user launches the dedicated app on their mobile device and taps the "Start Inspection" button from the main menu. The input here is the user's operation, and the output is the display of a screen for selecting inspection items.

[0145] Step 2:

[0146] The user selects the desired inspection item from the displayed list of inspection items, such as "tire inspection," "body inspection," or "engine sound inspection." The input is the selection of the inspection item, and the output is the next instruction screen based on the selected item.

[0147] Step 3:

[0148] The terminal displays a prompt corresponding to the selected inspection item. For example, if "Tire Inspection" is selected, the prompt "Please take a photo of the left front tire" is displayed. The input is the selected inspection item, and the output is the display of instructions to the user.

[0149] Step 4:

[0150] The user uses the camera on the mobile device to take a picture of the specified area according to the prompt. The input is the camera operation, and the output is the captured image data.

[0151] Step 5:

[0152] The device temporarily stores the captured image data and prepares it for transmission to the server. The input is the image data, and the output is the temporarily stored data and subsequent preparation for data transmission.

[0153] Step 6:

[0154] The terminal sends the temporarily stored image data to the server. The input is the stored image data, and the output is the data sent to the server.

[0155] Step 7:

[0156] The server inputs the received image data into a generative AI model to analyze tire pressure, loose screws, and distortion. The input is image data, and the output is the analysis results.

[0157] Step 8:

[0158] The server generates the analysis results and creates a notification message such as "There is a loose screw on the left front tire." The input is the analysis results, and the output is the notification message.

[0159] Step 9:

[0160] The server sends the generated notification message to the user's mobile terminal. The input is the notification message, and the output is the message displayed on the user's terminal.

[0161] Engine sound inspection procedure

[0162] Step 1:

[0163] The user launches the app and selects "Check Engine Sound." The input is the user's operation, and the output is the display of a screen instructing the user to record the engine sound.

[0164] Step 2:

[0165] The terminal displays the prompt "Start the engine and record the sound." The input is the selected inspection item, and the output is the display of instructions to the user.

[0166] Step 3:

[0167] The user starts the engine and records the sound. The input is the microphone operation, and the output is the recorded audio data.

[0168] Step 4:

[0169] The terminal temporarily stores the recorded voice data and prepares it to be sent to the server. The input is the voice data, and the output is the temporarily stored data and the preparation for subsequent data transmission.

[0170] Step 5:

[0171] The terminal transmits the temporarily stored voice data to the server. The input is the stored voice data, and the output is the data transmitted to the server.

[0172] Step 6:

[0173] The server inputs the received audio data into the generative AI model and analyzes engine sound abnormalities. The input is the audio data, and the output is the analysis result.

[0174] Step 7:

[0175] The server generates the analysis result and creates a notification message saying, "There is something wrong with the engine start sound." The input is the analysis result, and the output is the notification message.

[0176] Step 8:

[0177] The server sends the generated notification message to the user's mobile terminal. The input is the notification message, and the output is the message displayed on the user's terminal.

[0178] The detailed processing in each step above allows the user to properly perform various inspections of the vehicle, allowing the user to grasp the condition of the vehicle in real time and manage it safely and efficiently.

[0179] (Application example 1)

[0180] 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."

[0181] Periodic or reactive diagnosis of vehicle conditions is important for operational safety and performance maintenance. However, conventional methods require specialized knowledge for many inspection tasks, making it difficult for users to easily perform self-diagnosis. Furthermore, autonomous vehicles also require methods for quickly and accurately detecting abnormalities in each part of the vehicle, but this requires advanced functionality and analytical capabilities.

[0182] 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.

[0183] In this invention, the server includes means for allowing a user to select vehicle inspection items, means for capturing images of the vehicle using a camera of the smart device, means for capturing audio data of the vehicle using a microphone of the smart device, means for transmitting the captured image and audio data to the server, means for analyzing the transmitted image and audio data using a generative AI model in the server, means for notifying the user of the analysis results, and means for periodically or reactively diagnosing the vehicle condition so that the autonomous vehicle can perform self-diagnosis. This allows users to easily diagnose the condition of the vehicle without requiring specialized knowledge, and the autonomous vehicle's self-diagnosis function allows it to quickly and accurately detect vehicle abnormalities, thereby maintaining safety and performance.

[0184] A "user" is an individual who operates a smart device to perform an automobile inspection.

[0185] A "smart device" is an electronic device that has a built-in camera and microphone and has the ability to acquire data and send it to a server.

[0186] A "camera" is an optical device for acquiring image data.

[0187] A "microphone" is an acoustic device for acquiring audio data.

[0188] A "server" is a remote computer system that analyzes the acquired data and notifies the user of the results.

[0189] A "generative AI model" is a machine learning model used to analyze captured image and audio data.

[0190] "Analysis" is the process of extracting information based on the acquired data and identifying abnormalities or problems.

[0191] "Notification" is the process of informing the user of the analysis results.

[0192] An "autonomous vehicle" is a vehicle that does not require human operation and has self-diagnostic capabilities.

[0193] "Self-diagnosis" is a function that allows the vehicle itself to check its condition and detect abnormalities.

[0194] "Periodic" means repeatedly at a series of intervals.

[0195] "Reactive" means responding immediately to events that occur.

[0196] "Condition" refers to the current state of each part and function of the vehicle.

[0197] An "image" is visual data captured by a camera.

[0198] "Audio data" is acoustic data acquired by a microphone.

[0199] "Data transmission" is the process of sending the acquired data over the network to the server.

[0200] "Safety" refers to the reliability of vehicles to ensure safe operation.

[0201] "Performance retention" means that the vehicle maintains good performance over a long period of time.

[0202] The present invention provides a system for easily diagnosing the condition of an automobile, and in particular for enhancing the self-diagnosis function of an autonomous vehicle. Specific embodiments for carrying out the present invention will be described in detail below.

[0203] System configuration

[0204] The main components of the system are:

[0205] User: An individual who operates a smart device to inspect a vehicle. In the case of autonomous vehicles, the vehicle itself performs self-diagnosis.

[0206] Smart device: An electronic device used for vehicle inspections that has a built-in camera and microphone. The camera captures image data, and the microphone captures audio data.

[0207] Server: A remote computer system that uses generative AI models to analyze the acquired data and notify the user of the results.

[0208] Generative AI model: Performs data analysis as a machine learning model to analyze the condition of each part of the car.

[0209] Data acquisition and analysis

[0210] Tire Diagnosis

[0211] The user captures an image of the tire using the camera on their smart device. The image is then sent to a server, where it is analyzed using a generative AI model to detect tire pressure, loose screws, and distortion. The results of the analysis are then reported to the user.

[0212] Body diagnostics

[0213] The user uses the camera on their smart device to capture images of the vehicle, which are then sent to a server that analyzes them using a generative AI model to detect scratches on the vehicle body, cracks in the glass, and dangerous distortions. The results of the analysis are then reported to the user.

[0214] Engine sound diagnosis

[0215] The user records the engine sound using the microphone on their smart device. The captured audio data is sent to the server, which then analyzes the engine sound using a generative AI model. If an abnormality is detected, the user is notified of the details.

[0216] Self-diagnosis for autonomous vehicles

[0217] In autonomous vehicles, the system performs self-diagnosis periodically or reactively. It uses cameras, microphones, and other sensors built into the vehicle to collect data, which is then sent to a server. The server then analyzes the data using generative AI models, and if an abnormality is detected, a notification is sent to the vehicle's infotainment system or the driver.

[0218] Hardware and software used

[0219] Hardware:

[0220] Smart device (with built-in camera and microphone)

[0221] Built-in cameras, microphones, and various sensors in autonomous vehicles

[0222] software:

[0223] OpenCV: Camera control and image acquisition

[0224] sounddevice library: audio recording

[0225] The requests library: data transmission and server communication

[0226] Generative AI Models: Data Analysis

[0227] Specific examples

[0228] Example prompt sentence:

[0229] "Take a photo of the left front tire and automatically transfer it."

[0230] "Start the engine, record the audio, and automatically transmit it."

[0231] Example of operation steps:

[0232] The user opens the smart device app and selects the tire diagnosis item.

[0233] The user points the smart device at the front wheel of the vehicle, activates the camera, and captures an image.

[0234] The captured images are sent to a server and analyzed by a generative AI model.

[0235] The analysis results are notified to the user, displaying the message "Loose screws have been detected in the left front tire."

[0236] In this way, the present invention aims to enable users to easily diagnose the condition of their vehicle without requiring specialized knowledge. Furthermore, by strengthening the self-diagnosis function of autonomous vehicles, it is possible to quickly and accurately detect vehicle abnormalities, thereby realizing safety and maintaining performance.

[0237] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0238] Step 1:

[0239] The user launches the app on their smart device and selects an inspection item. The user's operation is input, the inspection item selection is output, and the system proceeds to the next data acquisition step.

[0240] Step 2:

[0241] The terminal uses the smart device's camera to capture images corresponding to the selected inspection item. Specifically, the user points the smart device at the relevant part of the vehicle (e.g., tire or body) and takes a photo with the camera. The input is video data from the camera, and the captured image is output.

[0242] Step 3:

[0243] When the terminal uses the microphone of the smart device to acquire voice data corresponding to the selected inspection item, the user records the engine sound according to the instructions. The input is the voice data from the microphone, and the acquired voice is output.

[0244] Step 4:

[0245] The image and audio data acquired by the device is sent to the server. Specifically, a network request is used to upload the acquired data files to the server. The input is the image and audio data files, and the output is the completion of data transmission to the server.

[0246] Step 5:

[0247] The image and audio data received by the server is input into the generative AI model for analysis. Specifically, the server inputs the data into the generative AI model, which then performs image and audio analysis. The input is image data and audio data, and the analysis results are output.

[0248] Step 6:

[0249] The server notifies the user of the analysis results. Specifically, the analysis results (for example, abnormal tire pressure, loose screws, abnormal engine noise, etc.) are generated and sent to the user's smart device as a notification message. The input is the analysis results, and the output is the completion of notification to the user.

[0250] Step 7:

[0251] In the case of self-diagnosis in an autonomous vehicle, the vehicle automatically performs steps 1 to 6 periodically or as needed, without requiring user intervention. The input is the vehicle's automatic diagnostic system, and the output is notification of the self-diagnosis results.

[0252] 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.

[0253] A specific embodiment for carrying out the present invention will be described in detail. The system described below allows a user to use a smartphone to perform a pre-ride inspection of a vehicle, and uses an emotion engine to recognize the user's emotions and provide appropriate feedback. This system transmits data acquired using the smartphone's camera and microphone to a server, and notifies the user of the analysis results based on the user's emotions.

[0254] System configuration

[0255] The main components of the system are:

[0256] User: The individual who operates the smartphone and performs the vehicle inspection.

[0257] Device: A smartphone used for vehicle inspections, equipped with a built-in camera and microphone.

[0258] Server: A remote computer system that analyzes the acquired data using a generative AI model and emotion engine.

[0259] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[0260] Emotion engine: A model that recognizes emotions from user voice and text data and generates appropriate feedback based on those emotions.

[0261] Explanation of program processing

[0262] 1. User operations and data acquisition

[0263] The user starts the dedicated app on their smartphone and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[0264] 2. Check your tires

[0265] The device uses the camera to take photos of each tire to check its condition. When taking photos, the app guides the user on the shooting position and angle. The photos are temporarily saved on the smartphone and then automatically sent to the server.

[0266] The server inputs the received photos into a generative AI model to analyze tire pressure, loose screws, and distortions. The analysis results are then sent to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[0267] The server generates a feedback message based on the user's sentiment, including specific advice such as "A slight looseness has been detected, but it can be easily corrected with a specific tool."

[0268] 3. Inspect the vehicle body

[0269] To check the overall condition of the vehicle, the user takes a photo of the vehicle using the smartphone camera. The app guides the user to take an appropriate photo by specifying the shooting position and angle. The captured photo of the vehicle is temporarily saved on the smartphone and then sent to the server.

[0270] The server inputs the received photos of the car body into a generative AI model, which analyzes scratches on the car body, cracks in the glass, and dangerous distortions.The analysis results are then sent to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[0271] The server generates a feedback message based on the user's sentiment, including specific advice such as "I found a small scratch on the car body, but it's not a serious problem."

[0272] 4. Check the sound when starting the engine

[0273] The user follows the app's instructions to record the engine sound using the smartphone's microphone. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[0274] The server inputs the received voice data into a generative AI model to analyze any abnormalities in the engine start-up sound.Then, it sends the analysis results to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[0275] The server generates a feedback message based on the user's emotions, including specific advice such as "An abnormality has been detected in the engine start-up sound. We recommend that you repair it immediately."

[0276] Specific examples

[0277] Examples of tire inspections:

[0278] 1. The user launches the app and selects "Tire Inspection."

[0279] 2. The app will prompt you to take a photo of the left front tire.

[0280] 3. The user uses their smartphone to take a photo of the left front tire.

[0281] 4. The photo is sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[0282] 5. The analysis results are sent to the emotion engine.

[0283] 6. The emotion engine recognizes emotions from the user's voice data and generates a feedback message.

[0284] 7. The server notifies the user of the analysis results and a feedback message, such as "There is a loose screw on the left front tire, but this can be easily fixed."

[0285] Examples of engine sound checks:

[0286] 1. The user launches the app and selects "Check Engine Sound."

[0287] 2. The app will prompt you to "Start the engine and record the sound."

[0288] 3. The user starts the engine and records the sound.

[0289] 4. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[0290] 5. The analysis results are sent to the emotion engine.

[0291] 6. The emotion engine recognizes emotions from the user's voice data and generates a feedback message.

[0292] 7. The server notifies the user of the analysis results and a feedback message, such as "There is something wrong with the engine start-up sound. Repairs are recommended."

[0293] As described above, the user can perform highly accurate vehicle inspections with simple operations and can also receive appropriate feedback according to their emotions.

[0294] The processing flow will be explained below.

[0295] Step 1:

[0296] The user launches the dedicated app on their smartphone. The app's main screen appears, and they can select an inspection item (tire inspection, vehicle body inspection, engine sound inspection).

[0297] Step 2:

[0298] The app will then display specific instructions based on the inspection item the user selects. For example, if the user selects a tire inspection, the app will prompt the user to "take a photo of the left front tire."

[0299] Step 3:

[0300] The user uses the smartphone camera to take a photo of the specified area (e.g., the left front tire).

[0301] Step 4:

[0302] The device temporarily stores the captured photos in its internal storage.

[0303] Step 5:

[0304] The device transmits the stored photo data to a server via the Internet.

[0305] Step 6:

[0306] The server receives the transmitted photo data and inputs it into the generative AI model.

[0307] Step 7:

[0308] The server uses a generative AI model to analyze the photo data and detect, for example, tire pressure, loose screws, and distortions.

[0309] Step 8:

[0310] The server sends the analysis results to the emotion engine.

[0311] Step 9:

[0312] In order for the emotion engine to recognize emotions from the user's voice data, it asks the user a question (e.g., "Are you okay?") and acquires the voice data.

[0313] Step 10:

[0314] The emotion engine analyzes the voice data and recognizes the user's emotions, such as anxiety, relief, and surprise.

[0315] Step 11:

[0316] The server generates an appropriate feedback message based on the analysis results and the user's emotions. For example, if the user is feeling anxious, it creates a message saying, "A loose screw has been detected, but don't worry, it can be easily fixed."

[0317] Step 12:

[0318] The server sends the generated feedback message to the terminal.

[0319] Step 13:

[0320] The device notifies the user of the received feedback message, which includes the analysis results and advice based on the user's emotions.

[0321] Step 14:

[0322] The user checks the notification and takes appropriate measures as instructed, if necessary (e.g., check the tire screws and correct any looseness).

[0323] Specific examples

[0324] Examples of tire inspections:

[0325] Step 1:

[0326] The user launches the app and selects "Tire Inspection."

[0327] Step 2:

[0328] The app will then prompt you to "Take a photo of the left front tire."

[0329] Step 3:

[0330] The user uses a smartphone to take a photo of the left front tire.

[0331] Step 4:

[0332] The photos you take will be saved on your device.

[0333] Step 5:

[0334] The saved photo data is sent to the server.

[0335] Step 6:

[0336] The server receives the photo data and analyzes it using a generative AI model.

[0337] Step 7:

[0338] The server detects tire pressure, loose screws, and distortion.

[0339] Step 8:

[0340] The analysis results are sent to the emotion engine.

[0341] Step 9:

[0342] The emotion engine asks the user for their reaction and tells them, "Loose screws detected."

[0343] Step 10:

[0344] The user responds and asks, "What do I do?"

[0345] Step 11:

[0346] The emotion engine recognizes anxiety from the user's voice data and combines it with the analysis results to generate appropriate feedback.

[0347] Step 12:

[0348] The server creates a message saying, "Loose screws have been detected, but don't worry, they can be easily fixed with a specific tool."

[0349] Step 13:

[0350] The generated message is sent to the terminal.

[0351] Step 14:

[0352] The device will then send a message to the user, containing the tire analysis results and instructions on how to fix the threads.

[0353] Through these steps, users can not only perform highly accurate inspections of their vehicles, but also receive appropriate support tailored to their emotions.

[0354] Example 2

[0355] 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."

[0356] Conventional vehicle inspection methods require specialized knowledge and tools, making it difficult for ordinary users to perform inspections themselves. In addition, since feedback that takes into account the user's emotions is not provided, there is a risk that the user may not understand or respond well to the inspection results.

[0357] 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.

[0358] In this invention, the server includes means for analyzing the transmitted image and audio data using a generative AI model, means for sending the analysis results to an emotion recognition engine and generating feedback based on the user's emotions, and means for notifying the user of the analysis results and feedback. This allows even ordinary users to easily inspect their vehicles and receive appropriate feedback according to the user's emotions.

[0359] "User" refers to an individual who uses a mobile information terminal to perform an automobile inspection.

[0360] A "mobile information terminal" refers to a device such as a smartphone or tablet that has a built-in camera and microphone and can run dedicated apps.

[0361] "Server" refers to a remote computer system that uses a generative AI model and an emotion recognition engine to analyze the received data and notify the user of the analysis results.

[0362] A "generative AI model" refers to a model that uses machine learning technology to analyze the condition of each part of a car.

[0363] An "emotion recognition engine" refers to a model that recognizes emotions from a user's voice or text data and generates appropriate feedback based on that.

[0364] "Analysis results" refers to information analyzed by the generative AI model, such as tire pressure, loose screws, distortions, scratches on the body, cracks in the glass, and abnormal engine sounds.

[0365] "Feedback" refers to specific advice or notification messages generated based on the analysis results and the user's emotions.

[0366] "Inspection items" refer to vehicle inspection items that can be selected by the user, such as tire inspection, body inspection, and engine sound inspection.

[0367] "Data acquisition means" refers to a means for acquiring images and audio data of a vehicle using a camera or microphone of a mobile information terminal.

[0368] The "data transmission means" refers to a means for transmitting image and audio data acquired by the mobile information terminal to the server.

[0369] This invention is a system that allows a user to inspect a vehicle using a mobile information terminal, and uses a generative AI model and an emotion recognition engine to recognize the user's emotions and provide appropriate feedback. This system acquires data using the mobile information terminal's camera and microphone, sends it to a server, and generates and notifies feedback based on the analysis results.

[0370] System Components

[0371] The main components of the system are:

[0372] User: An individual who operates a mobile information terminal and performs a vehicle inspection.

[0373] Terminal: A personal digital assistant used for vehicle inspections, equipped with a camera and microphone.

[0374] Server: A remote computer system that analyzes acquired data using a generative AI model and emotion recognition engine.

[0375] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[0376] Emotion recognition engine: A model that recognizes emotions from the user's voice and text data and generates appropriate feedback based on that.

[0377] Data Acquisition and Transmission

[0378] The user starts the dedicated app on their mobile device and begins the inspection. They select the desired inspection item from the app's main screen and follow the data acquisition procedure. Inspection items include tire inspection, vehicle body inspection, and engine sound inspection.

[0379] In the case of tire inspections, the device uses the camera to take a photo of each tire. The app guides the user on the shooting position and angle, and the photos are temporarily stored on the mobile information device before being sent to the server. As a concrete example, the user may be instructed to "take a photo of the left front tire" and follow that instruction.

[0380] During a vehicle inspection, the user uses the camera on their mobile device to take a photo of the vehicle. The app instructs the user on the best shooting position and angle. The photos are temporarily stored on the device and later sent to the server. A specific example is a procedure where the user is guided to "take a photo of the entire vehicle."

[0381] To check the engine sound, the user records the engine sound using the microphone on the mobile information terminal. The recorded audio data is temporarily stored in the terminal and then sent to the server. As a concrete example, the user is instructed to "start the engine and record the sound."

[0382] Data analysis and feedback

[0383] The server receives the transmitted image and audio data and analyzes it using a generative AI model. For example, tire images can be used to detect air pressure, loose screws, and distortions. Images of the car body can be analyzed for scratches, cracked glass, and dangerous distortions. Engine sound data can be used to detect abnormal sounds.

[0384] The analysis results are sent to an emotion recognition engine on the server, which recognizes the user's emotional state from their voice and text data. Specific and appropriate feedback is generated based on the analysis results and emotional data. For example, it may include advice such as, "There's a loose screw on the left front tire, but that can be easily fixed."

[0385] Notifications and Feedback

[0386] The server notifies the user of the generated feedback message. For example, when the user receives the analysis result, the server notifies the user that "a small scratch was found on the car body, but it is not a serious problem."

[0387] In this way, the system of the present invention allows even ordinary users to easily inspect their vehicles and provides appropriate feedback according to the user's emotions. By using this system, users can easily obtain highly accurate inspection results and can quickly take appropriate action.

[0388] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0389] Step 1:

[0390] The user launches a dedicated app on their mobile information terminal and begins the inspection.

[0391] Input: Launching an app on a mobile device

[0392] Output: The main screen of the app is displayed, and the Start Inspection button is available.

[0393] Specific operation: The user taps the icon to launch the app. After launching, a "Start inspection" button appears on the main screen.

[0394] Step 2:

[0395] The user selects the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection).

[0396] Input: User taps to select an inspection item

[0397] Output: A screen corresponding to the selected inspection item will be displayed.

[0398] Specific operation: The user taps the desired item from "Tire Inspection," "Body Inspection," or "Engine Sound Inspection" on the main screen. Depending on the selection, a guide screen for the next step will be displayed.

[0399] Step 3:

[0400] The terminal displays instructions to the user to retrieve the data.

[0401] Input: Selected inspection items

[0402] Output: A guide message for data acquisition is displayed.

[0403] Specific actions: Instructions such as "Take a photo of the left front tire" and "Start the engine and record the sound" will appear on the device screen.

[0404] Step 4:

[0405] The user captures the data using the camera or microphone of the mobile information terminal.

[0406] Input: User performs data capture operations (photographs and audio recordings)

[0407] Output: Captured image or audio data

[0408] Specific operation: The user uses the camera to take photos of the tires and vehicle body, and uses the microphone to record the engine sound. The acquired data is temporarily stored on the device.

[0409] Step 5:

[0410] The terminal transmits the acquired data to the server.

[0411] Input: Captured image or audio data

[0412] Output: The data sent.

[0413] Specific operation: The device automatically uploads images and audio data stored internally to the server.

[0414] Step 6:

[0415] The server inputs the received data into the generative AI model and analyzes it.

[0416] Input: Transmitted image or audio data

[0417] Output: Analysis results (tire pressure, loose screws, scratches on the car body, abnormal engine sounds, etc.)

[0418] Specific operation: The server inputs the received data into the generative AI model and performs analytical processing to identify abnormalities and conditions.

[0419] Step 7:

[0420] The server sends the analysis results to an emotion recognition engine to recognize the user's emotions.

[0421] Input: Analysis results and user voice data

[0422] Output: User's emotional state

[0423] Specific operation: The server inputs the analysis results into an emotion recognition engine, analyzes the user's voice and text data, and recognizes major emotions such as joy, anger, sadness, and happiness.

[0424] Step 8:

[0425] The server generates a feedback message based on the analysis results and the user's emotions.

[0426] Input: Analysis results and emotion data

[0427] Output: Feedback message (e.g. "There is a loose screw in the left front tire, but this is an easy fix.")

[0428] Specific behavior: The server combines the analysis results with the user's emotions to generate specific and appropriate feedback.

[0429] Step 9:

[0430] The server notifies the user of the feedback message.

[0431] Input: Feedback message

[0432] Output: Notification message sent to the user

[0433] Specific operation: The server sends the generated feedback message to the mobile information terminal and displays it on the terminal screen.

[0434] (Application example 2)

[0435] 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."

[0436] In conventional vehicle inspection systems, it is difficult for users to accurately grasp the situation when performing the inspection themselves, resulting in the risk of making inappropriate decisions.Furthermore, they often provide uniform feedback without considering the user's emotional state, which has the problem of not being able to reduce user stress.

[0437] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring images of the vehicle using a camera of the communication terminal, means for acquiring voice data of the vehicle using a microphone of the communication terminal, means for analyzing the transmitted image and voice data using a generative AI model, means for generating a feedback message based on the analysis result by the generative AI model and the user's emotion using an emotion recognition engine, and means for notifying the user of the feedback message. This allows the user to obtain accurate vehicle inspection results and, further, to receive appropriate feedback according to the user's emotional state, thereby reducing stress.

[0438] A "user" is an individual or group that operates a communication terminal to inspect a vehicle.

[0439] A "communication terminal" is a device that has a built-in camera and microphone and is used by a user to inspect a vehicle. Examples include smartphones.

[0440] "Camera" means an optical instrument used to capture images of a vehicle.

[0441] A "microphone" is an acoustic device used to capture audio data from a vehicle.

[0442] A "server" is a remote computer system that analyzes data sent by a communication terminal and generates appropriate feedback messages.

[0443] A "generative AI model" is a machine learning model that analyzes acquired image and audio data to determine the vehicle's condition.

[0444] An "emotion recognition engine" is a software model for identifying emotions from a user's voice or text data and adjusting feedback messages accordingly.

[0445] A "feedback message" is a message that the server generates based on the analysis results and that includes advice or warning information to notify the user.

[0446] A "vehicle" is a machine used as a means of transportation, and specific examples include automobiles and self-driving vehicles.

[0447] To implement this invention, a system is required in which users, communication terminals, servers, generative AI models, and emotion recognition engines work together seamlessly. The detailed configuration of this system and the role of each element are described below.

[0448] Key components of the system

[0449] User: An individual or organization that inspects a vehicle and operates a communication terminal.

[0450] Communication terminal: A device with a built-in camera and microphone that allows users to obtain vehicle inspection data. Specific examples include smartphones.

[0451] Server: A high-performance computer system that receives data sent from communication devices and analyzes and provides feedback using a generative AI model and emotion recognition engine.

[0452] Generative AI model: A model that uses machine learning techniques to analyze transmitted image and audio data.

[0453] Emotion recognition engine: A software model that recognizes emotions from user voice and text data and adjusts the content of feedback messages.

[0454] Program processing overview

[0455] The user launches a dedicated app on the communication device and selects an inspection item. The communication device uses a camera to capture images of the vehicle and a microphone to capture audio data from the vehicle. This data is temporarily stored on the device and then sent to the server.

[0456] The server inputs the received image and voice data into a generative AI model to analyze the condition of each part of the vehicle. The analysis results are then transferred to an emotion recognition engine, which recognizes emotions from the user's voice data and generates appropriate feedback messages based on that.

[0457] Hardware and software used

[0458] Hardware: Smartphone (camera, built-in microphone), server (high-performance computer)

[0459] Software: Python, OpenCV (image processing library), requests (HTTP request library), emotion_recognition (emotion recognition library), ai_model (generative AI model)

[0460] Data processing and calculation

[0461] Image and audio data captured using the communication device's camera and microphone are sent to the server via HTTP requests. On the server, a generative AI model analyzes the image data to determine the condition of each part of the vehicle. An emotion recognition engine also evaluates the user's emotions from the audio data and uses the results to generate feedback messages that are optimal for the analysis results.

[0462] Specific examples

[0463] When selecting "tire inspection" as an inspection item, the user uses the camera on their communication device to take sequential images of the tires. The communication device then sends this image data to the server, which then uses a generative AI model to analyze the tire's air pressure, loose screws, and distortion. Based on the analysis results and the user's emotion recognition results, a feedback message containing specific advice is generated.

[0464] Example prompts to input to the generative AI model

[0465] "Please analyze images taken from the front of the vehicle to check the status of the front sensors. Also, please detect any abnormalities based on the recorded engine sound data."

[0466] In this way, the present invention enables users to easily perform highly accurate vehicle inspections, and further reduces stress for users by providing appropriate feedback based on emotion recognition.

[0467] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0468] Step 1: The user launches the dedicated app on the communication device and selects an inspection item. This allows the user to begin operations to inspect specific vehicle parts, such as tires, the body, or engine noise. The input is the inspection item selected by the user, and the output is the next guideline for the inspection item.

[0469] Step 2: The user acquires images of the vehicle using the camera on the communication device. For example, if the user selects tire inspection, the user takes a photo of each tire with the smartphone camera. The app displays guidelines to guide the user to take photos from the appropriate position and angle. The input is the image data captured by the user, and the output is the image data temporarily stored in the communication device.

[0470] Step 3: The user acquires vehicle audio data using the microphone on the communication device. For example, if the user selects engine sound inspection, the user records the engine start-up sound using the microphone on their smartphone. The input is the recorded audio data, and the output is the audio data temporarily stored in the communication device.

[0471] Step 4: The captured image and audio data are sent to the server via an HTTP request. The communication device combines the image and audio data into a single request and sends it to the server's data receiving endpoint. The input is the image and audio data stored in the communication device, and the output is the data sent to the server.

[0472] Step 5: The server uses the generative AI model to analyze the received image data and determine the condition of each part of the vehicle. For example, if it is an image of a tire, it will analyze the air pressure, loose screws, and distortion. The input is the image data sent to the server, and the output is the tire condition data as the analysis result.

[0473] Step 6: The server similarly analyzes the received audio data using the generative AI model to check for abnormalities in the vehicle's engine sound. The input is the audio data sent to the server, and the output is the engine sound status data as the analysis result.

[0474] Step 7: The analysis results are passed to the emotion recognition engine in the server, where the process of recognizing emotions from the user's voice data is carried out. The input is the user's voice data, and the output is the recognized user's emotion data.

[0475] Step 8: The server generates an appropriate feedback message based on the analysis results and the user's emotional data. For example, if the user is nervous, the feedback message can use gentler language or include more detailed explanations. The input is the analysis results and emotional data, and the output is the feedback message.

[0476] Step 9: The feedback message is sent to the communication terminal as an HTTP response and notified to the user. The communication terminal receives this and displays the message to the user in the app. The input is the feedback message from the server, and the output is the feedback message notified to the user.

[0477] 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.

[0478] 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.

[0479] 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.

[0480] [Second embodiment]

[0481] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0482] 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.

[0483] 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).

[0484] 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.

[0485] 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.

[0486] 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).

[0487] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0492] 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."

[0493] A specific embodiment for carrying out the present invention will be described in detail. The system described below allows a user to perform a pre-boarding inspection of a vehicle using a smartphone. This system uses the smartphone's camera and microphone, and transmits the acquired data to a server for analysis, thereby achieving highly accurate vehicle inspections.

[0494] System configuration

[0495] The main components of the system are:

[0496] User: The individual who operates the smartphone and performs the vehicle inspection.

[0497] Device: A smartphone used for vehicle inspections, equipped with a built-in camera and microphone.

[0498] Server: A remote computer system that analyzes the acquired data using a generative AI model.

[0499] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[0500] Explanation of program processing

[0501] 1. User operations and data acquisition

[0502] The user starts the dedicated app on their smartphone and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[0503] 2. Check your tires

[0504] The device uses the camera to take photos of each tire to check its condition. When taking photos, the app guides the user on the shooting position and angle. The photos are temporarily saved on the smartphone and then automatically sent to the server.

[0505] The server inputs the received photos into a generative AI model to analyze tire pressure, loose screws, and distortion. Once the analysis is complete, the results are notified to the user.

[0506] 3. Inspect the vehicle body

[0507] To check the overall condition of the vehicle, the user takes a photo of the vehicle using the smartphone camera. The app guides the user to take an appropriate photo by specifying the shooting position and angle. The captured photo of the vehicle is temporarily saved on the smartphone and then sent to the server.

[0508] The server inputs the received photos of the car body into a generative AI model, which analyzes the car for scratches, cracks in the glass, and dangerous distortions. The results of the analysis are then notified to the user.

[0509] 4. Check the sound when starting the engine

[0510] The user follows the app's instructions to record the engine sound using the smartphone's microphone. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[0511] The server inputs the received audio data into a generative AI model to analyze any abnormalities in the engine start-up sound. The server notifies the user of the analysis results and advises them on the necessary measures.

[0512] 5. Check the engine sound after starting

[0513] The user records the engine sound for a certain period of time after the engine starts. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[0514] The server inputs the received audio data into a generative AI model to analyze the engine sound for abnormalities. If an abnormality is detected, the analysis results are sent to the user as a notification containing details.

[0515] Specific examples

[0516] Examples of tire inspections:

[0517] 1. The user launches the app and selects "Tire Inspection."

[0518] 2. The app will prompt you to take a photo of the left front tire.

[0519] 3. The user uses their smartphone to take a photo of the left front tire.

[0520] 4. The photo is sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[0521] 5. The server notifies the user of the analysis results and sends a message such as "There is a loose screw in the left front tire."

[0522] Examples of engine sound checks:

[0523] 1. The user launches the app and selects "Check Engine Sound."

[0524] 2. The app will prompt you to "Start the engine and record the sound."

[0525] 3. The user starts the engine and records the sound.

[0526] 4. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[0527] 5. The server detects an abnormal sound and notifies the user that "there is something wrong with the engine startup sound."

[0528] As described above, the user can perform highly accurate vehicle inspections with simple operations.

[0529] The processing flow will be explained below.

[0530] Step 1:

[0531] The user launches the dedicated app on their smartphone and selects an inspection item (e.g., tire inspection, vehicle body inspection, engine sound inspection) from the main screen.

[0532] Step 2:

[0533] The app will then display specific instructions for the inspection item selected by the user (e.g., "Take a photo of the left front tire").

[0534] Step 3:

[0535] The user uses the smartphone camera to take a photo of the specified area according to the instructions (e.g., a photo of the left front tire).

[0536] Step 4:

[0537] The device temporarily stores the captured photos in its internal storage.

[0538] Step 5:

[0539] The device transmits the stored photo data to a server via the Internet.

[0540] Step 6:

[0541] The server receives the transmitted photo data and inputs it into the generative AI model.

[0542] Step 7:

[0543] The server uses a generative AI model to analyze the photo data and detect, for example, tire pressure, loose screws, and distortions.

[0544] Step 8:

[0545] The server generates the analysis results and organizes them, including details of any problems.

[0546] Step 9:

[0547] The server sends the analysis results to the device.

[0548] Step 10:

[0549] The device notifies the user of the analysis results it has received, including a specific message such as, "There is a loose screw in the left front tire."

[0550] Step 11:

[0551] The user checks the notification and takes appropriate measures as instructed, if necessary (e.g., check the tire screws and correct any looseness).

[0552] Engine sound inspections follow similar steps, but use a smartphone's microphone instead of a camera to analyze the recorded audio data. Specifically, the engine sound is recorded, the recorded data is sent to a server, analyzed by a generative AI model, and the user is notified if any abnormalities are detected. In this way, the system is designed to enable users to easily perform high-precision vehicle inspections.

[0553] Example 1

[0554] 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."

[0555] Conventional vehicle inspection systems require specialized knowledge and advanced equipment, making it difficult for general users to easily perform pre-inspections of their vehicles. Furthermore, they are limited to simply checking inspection items, and even if a problem is discovered, it is difficult to obtain analysis results that lead to details and countermeasures. This has led to many vehicle owners neglecting daily inspections, resulting in an increased risk of accidents and breakdowns.

[0556] 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.

[0557] In this invention, the server includes means for allowing a user to select vehicle inspection items, means for capturing images of the vehicle using a camera of a mobile device, means for capturing audio data of the vehicle using a microphone of the mobile device, means for transmitting the captured image and audio data to a remote computer system, means for analyzing the transmitted image and audio data using a generative AI model in the remote computer system, means for guiding the user to appropriate shooting positions and angles according to the inspection items, and means for notifying the user of the analysis results upon completion of the analysis. This enables general users to easily perform high-precision pre-inspections of their vehicles using their smartphones.

[0558] "User" refers to an individual who operates a mobile terminal to perform an automobile inspection.

[0559] "Mobile device" means a mobile electronic device containing a camera and microphone used for motor vehicle inspections.

[0560] "Camera" refers to a device for taking images and acquiring the data.

[0561] A "microphone" refers to a device for recording sound and acquiring that data.

[0562] "Server" refers to a remote computer system for receiving and analyzing data, generating results and notifying the user.

[0563] "Generative AI model" refers to an algorithm that uses machine learning to analyze transmitted image and audio data.

[0564] "Inspection item" refers to an action that the user can select to inspect a specific part of the vehicle.

[0565] A "prompt sentence" refers to a sentence that indicates the next operation or instruction to the user.

[0566] "Analysis results" refers to the diagnostic information obtained after data analysis is performed by a generative AI model.

[0567] "Remote computer system" refers to a computer system at a remote location that is used to receive and analyze data transmitted from a mobile device.

[0568] MODE FOR CARRYING OUT THE INVENTION

[0569] A specific embodiment for carrying out the present invention will be described in detail. This system allows a user to perform a pre-ride inspection of a vehicle using a mobile device. This system uses the camera and microphone of the mobile device, and transmits the acquired data to a server for analysis, thereby achieving highly accurate vehicle inspections.

[0570] System Components

[0571] The main components of the system are:

[0572] User: The individual who operates the mobile device and performs the vehicle inspection.

[0573] Terminal: A mobile terminal used for vehicle inspections, equipped with a camera and microphone.

[0574] Server: A remote computer system that analyzes the acquired data using generative AI models.

[0575] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[0576] Program processing overview

[0577] 1. The user launches the dedicated app on their mobile device and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[0578] 2. The device uses the camera to capture images for each inspection item. For example, if inspecting tires, the app will guide the user on the shooting position and angle, and the user will follow the instructions to take a photo of the tires. The captured image is temporarily stored on the device and then sent to the server.

[0579] 3. The device uses a microphone to capture audio data. For example, if you are checking the engine sound, it will record the sound when the engine starts, store the data temporarily on the device, and then send it to the server.

[0580] 4. The server inputs the received image and audio data into a generative AI model, which analyzes tire pressure, loose screws, distortions, scratches on the body, cracked glass, dangerous distortions, and abnormal engine start-up sounds.

[0581] 5. The server notifies the user of the analysis results, for example, sending a message such as "There is a loose screw in the left front tire" or "There is something unusual about the engine start-up sound."

[0582] Examples of concrete examples and prompts

[0583] Consider the following scenario:

[0584] 1. The user launches the app and selects "Tire Inspection."

[0585] Example prompt: "Take a photo of the left front tire."

[0586] 2. Following the prompts from the app, the user takes a photo of the left front tire using their smartphone camera.

[0587] 3. The photos are sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[0588] 4. The server notifies the user with the message "There is a loose screw in the left front tire."

[0589] Also, specific examples of engine sound checks include:

[0590] 1. The user launches the app and selects "Check Engine Sound."

[0591] Example prompt: "Start the engine and record the sound."

[0592] 2. The user starts the engine and records the sound.

[0593] 3. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[0594] 4. The server notifies the user that "there is something wrong with the engine start-up sound."

[0595] As explained above, users can perform highly accurate vehicle inspections with simple operations. This allows general users to know the condition of their vehicles in real time, enabling safe and efficient vehicle management.

[0596] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0597] Program processing flow

[0598] Step 1:

[0599] The user launches the dedicated app on their mobile device and taps the "Start Inspection" button from the main menu. The input here is the user's operation, and the output is the display of a screen for selecting inspection items.

[0600] Step 2:

[0601] The user selects the desired inspection item from the displayed list of inspection items, such as "tire inspection," "body inspection," or "engine sound inspection." The input is the selection of the inspection item, and the output is the next instruction screen based on the selected item.

[0602] Step 3:

[0603] The terminal displays a prompt corresponding to the selected inspection item. For example, if "Tire Inspection" is selected, the prompt "Please take a photo of the left front tire" is displayed. The input is the selected inspection item, and the output is the display of instructions to the user.

[0604] Step 4:

[0605] The user uses the camera on the mobile device to take a picture of the specified area according to the prompt. The input is the camera operation, and the output is the captured image data.

[0606] Step 5:

[0607] The device temporarily stores the captured image data and prepares it for transmission to the server. The input is the image data, and the output is the temporarily stored data and subsequent preparation for data transmission.

[0608] Step 6:

[0609] The terminal sends the temporarily stored image data to the server. The input is the stored image data, and the output is the data sent to the server.

[0610] Step 7:

[0611] The server inputs the received image data into a generative AI model to analyze tire pressure, loose screws, and distortion. The input is image data, and the output is the analysis results.

[0612] Step 8:

[0613] The server generates the analysis results and creates a notification message such as "There is a loose screw on the left front tire." The input is the analysis results, and the output is the notification message.

[0614] Step 9:

[0615] The server sends the generated notification message to the user's mobile terminal. The input is the notification message, and the output is the message displayed on the user's terminal.

[0616] Engine sound inspection procedure

[0617] Step 1:

[0618] The user launches the app and selects "Check Engine Sound." The input is the user's operation, and the output is the display of a screen instructing the user to record the engine sound.

[0619] Step 2:

[0620] The terminal displays the prompt "Start the engine and record the sound." The input is the selected inspection item, and the output is the display of instructions to the user.

[0621] Step 3:

[0622] The user starts the engine and records the sound. The input is the microphone operation, and the output is the recorded audio data.

[0623] Step 4:

[0624] The terminal temporarily stores the recorded voice data and prepares it to be sent to the server. The input is the voice data, and the output is the temporarily stored data and the preparation for subsequent data transmission.

[0625] Step 5:

[0626] The terminal transmits the temporarily stored voice data to the server. The input is the stored voice data, and the output is the data transmitted to the server.

[0627] Step 6:

[0628] The server inputs the received audio data into the generative AI model and analyzes engine sound abnormalities. The input is the audio data, and the output is the analysis result.

[0629] Step 7:

[0630] The server generates the analysis result and creates a notification message saying, "There is something wrong with the engine start sound." The input is the analysis result, and the output is the notification message.

[0631] Step 8:

[0632] The server sends the generated notification message to the user's mobile terminal. The input is the notification message, and the output is the message displayed on the user's terminal.

[0633] The detailed processing in each step above allows the user to properly perform various inspections of the vehicle, allowing the user to grasp the condition of the vehicle in real time and manage it safely and efficiently.

[0634] (Application example 1)

[0635] 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."

[0636] Periodic or reactive diagnosis of vehicle conditions is important for operational safety and performance maintenance. However, conventional methods require specialized knowledge for many inspection tasks, making it difficult for users to easily perform self-diagnosis. Furthermore, autonomous vehicles also require methods for quickly and accurately detecting abnormalities in each part of the vehicle, but this requires advanced functionality and analytical capabilities.

[0637] 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.

[0638] In this invention, the server includes means for allowing a user to select vehicle inspection items, means for capturing images of the vehicle using a camera of the smart device, means for capturing audio data of the vehicle using a microphone of the smart device, means for transmitting the captured image and audio data to the server, means for analyzing the transmitted image and audio data using a generative AI model in the server, means for notifying the user of the analysis results, and means for periodically or reactively diagnosing the vehicle condition so that the autonomous vehicle can perform self-diagnosis. This allows users to easily diagnose the condition of the vehicle without requiring specialized knowledge, and the autonomous vehicle's self-diagnosis function allows it to quickly and accurately detect vehicle abnormalities, thereby maintaining safety and performance.

[0639] A "user" is an individual who operates a smart device to perform an automobile inspection.

[0640] A "smart device" is an electronic device that has a built-in camera and microphone and has the ability to acquire data and send it to a server.

[0641] A "camera" is an optical device for acquiring image data.

[0642] A "microphone" is an acoustic device for acquiring audio data.

[0643] A "server" is a remote computer system that analyzes the acquired data and notifies the user of the results.

[0644] A "generative AI model" is a machine learning model used to analyze captured image and audio data.

[0645] "Analysis" is the process of extracting information based on the acquired data and identifying abnormalities or problems.

[0646] "Notification" is the process of informing the user of the analysis results.

[0647] An "autonomous vehicle" is a vehicle that does not require human operation and has self-diagnostic capabilities.

[0648] "Self-diagnosis" is a function that allows the vehicle itself to check its condition and detect abnormalities.

[0649] "Periodic" means repeatedly at a series of intervals.

[0650] "Reactive" means responding immediately to events that occur.

[0651] "Condition" refers to the current state of each part and function of the vehicle.

[0652] An "image" is visual data captured by a camera.

[0653] "Audio data" is acoustic data acquired by a microphone.

[0654] "Data transmission" is the process of sending the acquired data over the network to the server.

[0655] "Safety" refers to the reliability of vehicles to ensure safe operation.

[0656] "Performance retention" means that the vehicle maintains good performance over a long period of time.

[0657] The present invention provides a system for easily diagnosing the condition of an automobile, and in particular for enhancing the self-diagnosis function of an autonomous vehicle. Specific embodiments for carrying out the present invention will be described in detail below.

[0658] System configuration

[0659] The main components of the system are:

[0660] User: An individual who operates a smart device to inspect a vehicle. In the case of autonomous vehicles, the vehicle itself performs self-diagnosis.

[0661] Smart device: An electronic device used for vehicle inspections that has a built-in camera and microphone. The camera captures image data, and the microphone captures audio data.

[0662] Server: A remote computer system that uses generative AI models to analyze the acquired data and notify the user of the results.

[0663] Generative AI model: Performs data analysis as a machine learning model to analyze the condition of each part of the car.

[0664] Data acquisition and analysis

[0665] Tire Diagnosis

[0666] The user captures an image of the tire using the camera on their smart device. The image is then sent to a server, where it is analyzed using a generative AI model to detect tire pressure, loose screws, and distortion. The results of the analysis are then reported to the user.

[0667] Body diagnostics

[0668] The user uses the camera on their smart device to capture images of the vehicle, which are then sent to a server that analyzes them using a generative AI model to detect scratches on the vehicle body, cracks in the glass, and dangerous distortions. The results of the analysis are then reported to the user.

[0669] Engine sound diagnosis

[0670] The user records the engine sound using the microphone on their smart device. The captured audio data is sent to the server, which then analyzes the engine sound using a generative AI model. If an abnormality is detected, the user is notified of the details.

[0671] Self-diagnosis for autonomous vehicles

[0672] In autonomous vehicles, the system performs self-diagnosis periodically or reactively. It uses cameras, microphones, and other sensors built into the vehicle to collect data, which is then sent to a server. The server then analyzes the data using generative AI models, and if an abnormality is detected, a notification is sent to the vehicle's infotainment system or the driver.

[0673] Hardware and software used

[0674] Hardware:

[0675] Smart device (with built-in camera and microphone)

[0676] Built-in cameras, microphones, and various sensors in autonomous vehicles

[0677] software:

[0678] OpenCV: Camera control and image acquisition

[0679] sounddevice library: audio recording

[0680] The requests library: data transmission and server communication

[0681] Generative AI Models: Data Analysis

[0682] Specific examples

[0683] Example prompt sentence:

[0684] "Take a photo of the left front tire and automatically transfer it."

[0685] "Start the engine, record the audio, and automatically transmit it."

[0686] Example of operation steps:

[0687] The user opens the smart device app and selects the tire diagnosis item.

[0688] The user points the smart device at the front wheel of the vehicle, activates the camera, and captures an image.

[0689] The captured images are sent to a server and analyzed by a generative AI model.

[0690] The analysis results are notified to the user, displaying the message "Loose screws have been detected in the left front tire."

[0691] In this way, the present invention aims to enable users to easily diagnose the condition of their vehicle without requiring specialized knowledge. Furthermore, by strengthening the self-diagnosis function of autonomous vehicles, it is possible to quickly and accurately detect vehicle abnormalities, thereby realizing safety and maintaining performance.

[0692] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0693] Step 1:

[0694] The user launches the app on their smart device and selects an inspection item. The user's operation is input, the inspection item selection is output, and the system proceeds to the next data acquisition step.

[0695] Step 2:

[0696] The terminal uses the smart device's camera to capture images corresponding to the selected inspection item. Specifically, the user points the smart device at the relevant part of the vehicle (e.g., tire or body) and takes a photo with the camera. The input is video data from the camera, and the captured image is output.

[0697] Step 3:

[0698] When the terminal uses the microphone of the smart device to acquire voice data corresponding to the selected inspection item, the user records the engine sound according to the instructions. The input is the voice data from the microphone, and the acquired voice is output.

[0699] Step 4:

[0700] The image and audio data acquired by the device is sent to the server. Specifically, a network request is used to upload the acquired data files to the server. The input is the image and audio data files, and the output is the completion of data transmission to the server.

[0701] Step 5:

[0702] The image and audio data received by the server is input into the generative AI model for analysis. Specifically, the server inputs the data into the generative AI model, which then performs image and audio analysis. The input is image data and audio data, and the analysis results are output.

[0703] Step 6:

[0704] The server notifies the user of the analysis results. Specifically, the analysis results (for example, abnormal tire pressure, loose screws, abnormal engine noise, etc.) are generated and sent to the user's smart device as a notification message. The input is the analysis results, and the output is the completion of notification to the user.

[0705] Step 7:

[0706] In the case of self-diagnosis in an autonomous vehicle, the vehicle automatically performs steps 1 to 6 periodically or as needed, without requiring user intervention. The input is the vehicle's automatic diagnostic system, and the output is notification of the self-diagnosis results.

[0707] 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.

[0708] A specific embodiment for carrying out the present invention will be described in detail. The system described below allows a user to use a smartphone to perform a pre-ride inspection of a vehicle, and uses an emotion engine to recognize the user's emotions and provide appropriate feedback. This system transmits data acquired using the smartphone's camera and microphone to a server, and notifies the user of the analysis results based on the user's emotions.

[0709] System configuration

[0710] The main components of the system are:

[0711] User: The individual who operates the smartphone and performs the vehicle inspection.

[0712] Device: A smartphone used for vehicle inspections, equipped with a built-in camera and microphone.

[0713] Server: A remote computer system that analyzes the acquired data using a generative AI model and emotion engine.

[0714] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[0715] Emotion engine: A model that recognizes emotions from user voice and text data and generates appropriate feedback based on those emotions.

[0716] Explanation of program processing

[0717] 1. User operations and data acquisition

[0718] The user starts the dedicated app on their smartphone and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[0719] 2. Check your tires

[0720] The device uses the camera to take photos of each tire to check its condition. When taking photos, the app guides the user on the shooting position and angle. The photos are temporarily saved on the smartphone and then automatically sent to the server.

[0721] The server inputs the received photos into a generative AI model to analyze tire pressure, loose screws, and distortions. The analysis results are then sent to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[0722] The server generates a feedback message based on the user's sentiment, including specific advice such as "A slight looseness has been detected, but it can be easily corrected with a specific tool."

[0723] 3. Inspect the vehicle body

[0724] To check the overall condition of the vehicle, the user takes a photo of the vehicle using the smartphone camera. The app guides the user to take an appropriate photo by specifying the shooting position and angle. The captured photo of the vehicle is temporarily saved on the smartphone and then sent to the server.

[0725] The server inputs the received photos of the car body into a generative AI model, which analyzes scratches on the car body, cracks in the glass, and dangerous distortions.The analysis results are then sent to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[0726] The server generates a feedback message based on the user's sentiment, including specific advice such as "I found a small scratch on the car body, but it's not a serious problem."

[0727] 4. Check the sound when starting the engine

[0728] The user follows the app's instructions to record the engine sound using the smartphone's microphone. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[0729] The server inputs the received voice data into a generative AI model to analyze any abnormalities in the engine start-up sound.Then, it sends the analysis results to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[0730] The server generates a feedback message based on the user's emotions, including specific advice such as "An abnormality has been detected in the engine start-up sound. We recommend that you repair it immediately."

[0731] Specific examples

[0732] Examples of tire inspections:

[0733] 1. The user launches the app and selects "Tire Inspection."

[0734] 2. The app will prompt you to take a photo of the left front tire.

[0735] 3. The user uses their smartphone to take a photo of the left front tire.

[0736] 4. The photo is sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[0737] 5. The analysis results are sent to the emotion engine.

[0738] 6. The emotion engine recognizes emotions from the user's voice data and generates a feedback message.

[0739] 7. The server notifies the user of the analysis results and a feedback message, such as "There is a loose screw on the left front tire, but this can be easily fixed."

[0740] Examples of engine sound checks:

[0741] 1. The user launches the app and selects "Check Engine Sound."

[0742] 2. The app will prompt you to "Start the engine and record the sound."

[0743] 3. The user starts the engine and records the sound.

[0744] 4. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[0745] 5. The analysis results are sent to the emotion engine.

[0746] 6. The emotion engine recognizes emotions from the user's voice data and generates a feedback message.

[0747] 7. The server notifies the user of the analysis results and a feedback message, such as "There is something wrong with the engine start-up sound. Repairs are recommended."

[0748] As described above, the user can perform highly accurate vehicle inspections with simple operations and can also receive appropriate feedback according to their emotions.

[0749] The processing flow will be explained below.

[0750] Step 1:

[0751] The user launches the dedicated app on their smartphone. The app's main screen appears, and they can select an inspection item (tire inspection, vehicle body inspection, engine sound inspection).

[0752] Step 2:

[0753] The app will then display specific instructions based on the inspection item the user selects. For example, if the user selects a tire inspection, the app will prompt the user to "take a photo of the left front tire."

[0754] Step 3:

[0755] The user uses the smartphone camera to take a photo of the specified area (e.g., the left front tire).

[0756] Step 4:

[0757] The device temporarily stores the captured photos in its internal storage.

[0758] Step 5:

[0759] The device transmits the stored photo data to a server via the Internet.

[0760] Step 6:

[0761] The server receives the transmitted photo data and inputs it into the generative AI model.

[0762] Step 7:

[0763] The server uses a generative AI model to analyze the photo data and detect, for example, tire pressure, loose screws, and distortions.

[0764] Step 8:

[0765] The server sends the analysis results to the emotion engine.

[0766] Step 9:

[0767] In order for the emotion engine to recognize emotions from the user's voice data, it asks the user a question (e.g., "Are you okay?") and acquires the voice data.

[0768] Step 10:

[0769] The emotion engine analyzes the voice data and recognizes the user's emotions, such as anxiety, relief, and surprise.

[0770] Step 11:

[0771] The server generates an appropriate feedback message based on the analysis results and the user's emotions. For example, if the user is feeling anxious, it creates a message saying, "A loose screw has been detected, but don't worry, it can be easily fixed."

[0772] Step 12:

[0773] The server sends the generated feedback message to the terminal.

[0774] Step 13:

[0775] The device notifies the user of the received feedback message, which includes the analysis results and advice based on the user's emotions.

[0776] Step 14:

[0777] The user checks the notification and takes appropriate measures as instructed, if necessary (e.g., check the tire screws and correct any looseness).

[0778] Specific examples

[0779] Examples of tire inspections:

[0780] Step 1:

[0781] The user launches the app and selects "Tire Inspection."

[0782] Step 2:

[0783] The app will then prompt you to "Take a photo of the left front tire."

[0784] Step 3:

[0785] The user uses a smartphone to take a photo of the left front tire.

[0786] Step 4:

[0787] The photos you take will be saved on your device.

[0788] Step 5:

[0789] The saved photo data is sent to the server.

[0790] Step 6:

[0791] The server receives the photo data and analyzes it using a generative AI model.

[0792] Step 7:

[0793] The server detects tire pressure, loose screws, and distortion.

[0794] Step 8:

[0795] The analysis results are sent to the emotion engine.

[0796] Step 9:

[0797] The emotion engine asks the user for their reaction and tells them, "Loose screws detected."

[0798] Step 10:

[0799] The user responds and asks, "What do I do?"

[0800] Step 11:

[0801] The emotion engine recognizes anxiety from the user's voice data and combines it with the analysis results to generate appropriate feedback.

[0802] Step 12:

[0803] The server creates a message saying, "Loose screws have been detected, but don't worry, they can be easily fixed with a specific tool."

[0804] Step 13:

[0805] The generated message is sent to the terminal.

[0806] Step 14:

[0807] The device will then send a message to the user, containing the tire analysis results and instructions on how to fix the threads.

[0808] Through these steps, users can not only perform highly accurate inspections of their vehicles, but also receive appropriate support tailored to their emotions.

[0809] Example 2

[0810] 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."

[0811] Conventional vehicle inspection methods require specialized knowledge and tools, making it difficult for ordinary users to perform inspections themselves. In addition, since feedback that takes into account the user's emotions is not provided, there is a risk that the user may not understand or respond well to the inspection results.

[0812] 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.

[0813] In this invention, the server includes means for analyzing the transmitted image and audio data using a generative AI model, means for sending the analysis results to an emotion recognition engine and generating feedback based on the user's emotions, and means for notifying the user of the analysis results and feedback. This allows even ordinary users to easily inspect their vehicles and receive appropriate feedback according to the user's emotions.

[0814] "User" refers to an individual who uses a mobile information terminal to perform an automobile inspection.

[0815] A "mobile information terminal" refers to a device such as a smartphone or tablet that has a built-in camera and microphone and can run dedicated apps.

[0816] "Server" refers to a remote computer system that uses a generative AI model and an emotion recognition engine to analyze the received data and notify the user of the analysis results.

[0817] A "generative AI model" refers to a model that uses machine learning technology to analyze the condition of each part of a car.

[0818] An "emotion recognition engine" refers to a model that recognizes emotions from a user's voice or text data and generates appropriate feedback based on that.

[0819] "Analysis results" refers to information analyzed by the generative AI model, such as tire pressure, loose screws, distortions, scratches on the body, cracks in the glass, and abnormal engine sounds.

[0820] "Feedback" refers to specific advice or notification messages generated based on the analysis results and the user's emotions.

[0821] "Inspection items" refer to vehicle inspection items that can be selected by the user, such as tire inspection, body inspection, and engine sound inspection.

[0822] "Data acquisition means" refers to a means for acquiring images and audio data of a vehicle using a camera or microphone of a mobile information terminal.

[0823] The "data transmission means" refers to a means for transmitting image and audio data acquired by the mobile information terminal to the server.

[0824] This invention is a system that allows a user to inspect a vehicle using a mobile information terminal, and uses a generative AI model and an emotion recognition engine to recognize the user's emotions and provide appropriate feedback. This system acquires data using the mobile information terminal's camera and microphone, sends it to a server, and generates and notifies feedback based on the analysis results.

[0825] System Components

[0826] The main components of the system are:

[0827] User: An individual who operates a mobile information terminal and performs a vehicle inspection.

[0828] Terminal: A personal digital assistant used for vehicle inspections, equipped with a camera and microphone.

[0829] Server: A remote computer system that analyzes acquired data using a generative AI model and emotion recognition engine.

[0830] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[0831] Emotion recognition engine: A model that recognizes emotions from the user's voice and text data and generates appropriate feedback based on that.

[0832] Data Acquisition and Transmission

[0833] The user starts the dedicated app on their mobile device and begins the inspection. They select the desired inspection item from the app's main screen and follow the data acquisition procedure. Inspection items include tire inspection, vehicle body inspection, and engine sound inspection.

[0834] In the case of tire inspections, the device uses the camera to take a photo of each tire. The app guides the user on the shooting position and angle, and the photos are temporarily stored on the mobile information device before being sent to the server. As a concrete example, the user may be instructed to "take a photo of the left front tire" and follow that instruction.

[0835] During a vehicle inspection, the user uses the camera on their mobile device to take a photo of the vehicle. The app instructs the user on the best shooting position and angle. The photos are temporarily stored on the device and later sent to the server. A specific example is a procedure where the user is guided to "take a photo of the entire vehicle."

[0836] To check the engine sound, the user records the engine sound using the microphone on the mobile information terminal. The recorded audio data is temporarily stored in the terminal and then sent to the server. As a concrete example, the user is instructed to "start the engine and record the sound."

[0837] Data analysis and feedback

[0838] The server receives the transmitted image and audio data and analyzes it using a generative AI model. For example, tire images can be used to detect air pressure, loose screws, and distortions. Images of the car body can be analyzed for scratches, cracked glass, and dangerous distortions. Engine sound data can be used to detect abnormal sounds.

[0839] The analysis results are sent to an emotion recognition engine on the server, which recognizes the user's emotional state from their voice and text data. Specific and appropriate feedback is generated based on the analysis results and emotional data. For example, it may include advice such as, "There's a loose screw on the left front tire, but that can be easily fixed."

[0840] Notifications and Feedback

[0841] The server notifies the user of the generated feedback message. For example, when the user receives the analysis result, the server notifies the user that "a small scratch was found on the car body, but it is not a serious problem."

[0842] In this way, the system of the present invention allows even ordinary users to easily inspect their vehicles and provides appropriate feedback according to the user's emotions. By using this system, users can easily obtain highly accurate inspection results and can quickly take appropriate action.

[0843] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0844] Step 1:

[0845] The user launches a dedicated app on their mobile information terminal and begins the inspection.

[0846] Input: Launching an app on a mobile device

[0847] Output: The main screen of the app is displayed, and the Start Inspection button is available.

[0848] Specific operation: The user taps the icon to launch the app. After launching, a "Start inspection" button appears on the main screen.

[0849] Step 2:

[0850] The user selects the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection).

[0851] Input: User taps to select an inspection item

[0852] Output: A screen corresponding to the selected inspection item will be displayed.

[0853] Specific operation: The user taps the desired item from "Tire Inspection," "Body Inspection," or "Engine Sound Inspection" on the main screen. Depending on the selection, a guide screen for the next step will be displayed.

[0854] Step 3:

[0855] The terminal displays instructions to the user to retrieve the data.

[0856] Input: Selected inspection items

[0857] Output: A guide message for data acquisition is displayed.

[0858] Specific actions: Instructions such as "Take a photo of the left front tire" and "Start the engine and record the sound" will appear on the device screen.

[0859] Step 4:

[0860] The user captures the data using the camera or microphone of the mobile information terminal.

[0861] Input: User performs data capture operations (photographs and audio recordings)

[0862] Output: Captured image or audio data

[0863] Specific operation: The user uses the camera to take photos of the tires and vehicle body, and uses the microphone to record the engine sound. The acquired data is temporarily stored on the device.

[0864] Step 5:

[0865] The terminal transmits the acquired data to the server.

[0866] Input: Captured image or audio data

[0867] Output: The data sent.

[0868] Specific operation: The device automatically uploads images and audio data stored internally to the server.

[0869] Step 6:

[0870] The server inputs the received data into the generative AI model and analyzes it.

[0871] Input: Transmitted image or audio data

[0872] Output: Analysis results (tire pressure, loose screws, scratches on the car body, abnormal engine sounds, etc.)

[0873] Specific operation: The server inputs the received data into the generative AI model and performs analytical processing to identify abnormalities and conditions.

[0874] Step 7:

[0875] The server sends the analysis results to an emotion recognition engine to recognize the user's emotions.

[0876] Input: Analysis results and user voice data

[0877] Output: User's emotional state

[0878] Specific operation: The server inputs the analysis results into an emotion recognition engine, analyzes the user's voice and text data, and recognizes major emotions such as joy, anger, sadness, and happiness.

[0879] Step 8:

[0880] The server generates a feedback message based on the analysis results and the user's emotions.

[0881] Input: Analysis results and emotion data

[0882] Output: Feedback message (e.g. "There is a loose screw in the left front tire, but this is an easy fix.")

[0883] Specific behavior: The server combines the analysis results with the user's emotions to generate specific and appropriate feedback.

[0884] Step 9:

[0885] The server notifies the user of the feedback message.

[0886] Input: Feedback message

[0887] Output: Notification message sent to the user

[0888] Specific operation: The server sends the generated feedback message to the mobile information terminal and displays it on the terminal screen.

[0889] (Application example 2)

[0890] 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."

[0891] In conventional vehicle inspection systems, it is difficult for users to accurately grasp the situation when performing the inspection themselves, resulting in the risk of making inappropriate decisions.Furthermore, they often provide uniform feedback without considering the user's emotional state, which has the problem of not being able to reduce user stress.

[0892] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring images of the vehicle using a camera of the communication terminal, means for acquiring voice data of the vehicle using a microphone of the communication terminal, means for analyzing the transmitted image and voice data using a generative AI model, means for generating a feedback message based on the analysis result by the generative AI model and the user's emotion using an emotion recognition engine, and means for notifying the user of the feedback message. This allows the user to obtain accurate vehicle inspection results and, further, to receive appropriate feedback according to the user's emotional state, thereby reducing stress.

[0893] A "user" is an individual or group that operates a communication terminal to inspect a vehicle.

[0894] A "communication terminal" is a device that has a built-in camera and microphone and is used by a user to inspect a vehicle. Examples include smartphones.

[0895] "Camera" means an optical instrument used to capture images of a vehicle.

[0896] A "microphone" is an acoustic device used to capture audio data from a vehicle.

[0897] A "server" is a remote computer system that analyzes data sent by a communication terminal and generates appropriate feedback messages.

[0898] A "generative AI model" is a machine learning model that analyzes acquired image and audio data to determine the vehicle's condition.

[0899] An "emotion recognition engine" is a software model for identifying emotions from a user's voice or text data and adjusting feedback messages accordingly.

[0900] A "feedback message" is a message that the server generates based on the analysis results and that includes advice or warning information to notify the user.

[0901] A "vehicle" is a machine used as a means of transportation, and specific examples include automobiles and self-driving vehicles.

[0902] To implement this invention, a system is required in which users, communication terminals, servers, generative AI models, and emotion recognition engines work together seamlessly. The detailed configuration of this system and the role of each element are described below.

[0903] Key components of the system

[0904] User: An individual or organization that inspects a vehicle and operates a communication terminal.

[0905] Communication terminal: A device with a built-in camera and microphone that allows users to obtain vehicle inspection data. Specific examples include smartphones.

[0906] Server: A high-performance computer system that receives data sent from communication devices and analyzes and provides feedback using a generative AI model and emotion recognition engine.

[0907] Generative AI model: A model that uses machine learning techniques to analyze transmitted image and audio data.

[0908] Emotion recognition engine: A software model that recognizes emotions from user voice and text data and adjusts the content of feedback messages.

[0909] Program processing overview

[0910] The user launches a dedicated app on the communication device and selects an inspection item. The communication device uses a camera to capture images of the vehicle and a microphone to capture audio data from the vehicle. This data is temporarily stored on the device and then sent to the server.

[0911] The server inputs the received image and voice data into a generative AI model to analyze the condition of each part of the vehicle. The analysis results are then transferred to an emotion recognition engine, which recognizes emotions from the user's voice data and generates appropriate feedback messages based on that.

[0912] Hardware and software used

[0913] Hardware: Smartphone (camera, built-in microphone), server (high-performance computer)

[0914] Software: Python, OpenCV (image processing library), requests (HTTP request library), emotion_recognition (emotion recognition library), ai_model (generative AI model)

[0915] Data processing and calculation

[0916] Image and audio data captured using the communication device's camera and microphone are sent to the server via HTTP requests. On the server, a generative AI model analyzes the image data to determine the condition of each part of the vehicle. An emotion recognition engine also evaluates the user's emotions from the audio data and uses the results to generate feedback messages that are optimal for the analysis results.

[0917] Specific examples

[0918] When selecting "tire inspection" as an inspection item, the user uses the camera on their communication device to take sequential images of the tires. The communication device then sends this image data to the server, which then uses a generative AI model to analyze the tire's air pressure, loose screws, and distortion. Based on the analysis results and the user's emotion recognition results, a feedback message containing specific advice is generated.

[0919] Example prompts to input to the generative AI model

[0920] "Please analyze images taken from the front of the vehicle to check the status of the front sensors. Also, please detect any abnormalities based on the recorded engine sound data."

[0921] In this way, the present invention enables users to easily perform highly accurate vehicle inspections, and further reduces stress for users by providing appropriate feedback based on emotion recognition.

[0922] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0923] Step 1: The user launches the dedicated app on the communication device and selects an inspection item. This allows the user to begin operations to inspect specific vehicle parts, such as tires, the body, or engine noise. The input is the inspection item selected by the user, and the output is the next guideline for the inspection item.

[0924] Step 2: The user acquires images of the vehicle using the camera on the communication device. For example, if the user selects tire inspection, the user takes a photo of each tire with the smartphone camera. The app displays guidelines to guide the user to take photos from the appropriate position and angle. The input is the image data captured by the user, and the output is the image data temporarily stored in the communication device.

[0925] Step 3: The user acquires vehicle audio data using the microphone on the communication device. For example, if the user selects engine sound inspection, the user records the engine start-up sound using the microphone on their smartphone. The input is the recorded audio data, and the output is the audio data temporarily stored in the communication device.

[0926] Step 4: The captured image and audio data are sent to the server via an HTTP request. The communication device combines the image and audio data into a single request and sends it to the server's data receiving endpoint. The input is the image and audio data stored in the communication device, and the output is the data sent to the server.

[0927] Step 5: The server uses the generative AI model to analyze the received image data and determine the condition of each part of the vehicle. For example, if it is an image of a tire, it will analyze the air pressure, loose screws, and distortion. The input is the image data sent to the server, and the output is the tire condition data as the analysis result.

[0928] Step 6: The server similarly analyzes the received audio data using the generative AI model to check for abnormalities in the vehicle's engine sound. The input is the audio data sent to the server, and the output is the engine sound status data as the analysis result.

[0929] Step 7: The analysis results are passed to the emotion recognition engine in the server, where the process of recognizing emotions from the user's voice data is carried out. The input is the user's voice data, and the output is the recognized user's emotion data.

[0930] Step 8: The server generates an appropriate feedback message based on the analysis results and the user's emotional data. For example, if the user is nervous, the feedback message can use gentler language or include more detailed explanations. The input is the analysis results and emotional data, and the output is the feedback message.

[0931] Step 9: The feedback message is sent to the communication terminal as an HTTP response and notified to the user. The communication terminal receives this and displays the message to the user in the app. The input is the feedback message from the server, and the output is the feedback message notified to the user.

[0932] 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.

[0933] 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.

[0934] 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.

[0935] [Third embodiment]

[0936] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0937] 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.

[0938] 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).

[0939] 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.

[0940] 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.

[0941] 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).

[0942] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0943] 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.

[0944] 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.

[0945] 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.

[0946] 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.

[0947] 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."

[0948] A specific embodiment for carrying out the present invention will be described in detail. The system described below allows a user to perform a pre-boarding inspection of a vehicle using a smartphone. This system uses the smartphone's camera and microphone, and transmits the acquired data to a server for analysis, thereby achieving highly accurate vehicle inspections.

[0949] System configuration

[0950] The main components of the system are:

[0951] User: The individual who operates the smartphone and performs the vehicle inspection.

[0952] Device: A smartphone used for vehicle inspections, equipped with a built-in camera and microphone.

[0953] Server: A remote computer system that analyzes the acquired data using a generative AI model.

[0954] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[0955] Explanation of program processing

[0956] 1. User operations and data acquisition

[0957] The user starts the dedicated app on their smartphone and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[0958] 2. Check your tires

[0959] The device uses the camera to take photos of each tire to check its condition. When taking photos, the app guides the user on the shooting position and angle. The photos are temporarily saved on the smartphone and then automatically sent to the server.

[0960] The server inputs the received photos into a generative AI model to analyze tire pressure, loose screws, and distortion. Once the analysis is complete, the results are notified to the user.

[0961] 3. Inspect the vehicle body

[0962] To check the overall condition of the vehicle, the user takes a photo of the vehicle using the smartphone camera. The app guides the user to take an appropriate photo by specifying the shooting position and angle. The captured photo of the vehicle is temporarily saved on the smartphone and then sent to the server.

[0963] The server inputs the received photos of the car body into a generative AI model, which analyzes the car for scratches, cracks in the glass, and dangerous distortions. The results of the analysis are then notified to the user.

[0964] 4. Check the sound when starting the engine

[0965] The user follows the app's instructions to record the engine sound using the smartphone's microphone. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[0966] The server inputs the received audio data into a generative AI model to analyze any abnormalities in the engine start-up sound. The server notifies the user of the analysis results and advises them on the necessary measures.

[0967] 5. Check the engine sound after starting

[0968] The user records the engine sound for a certain period of time after the engine starts. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[0969] The server inputs the received audio data into a generative AI model to analyze the engine sound for abnormalities. If an abnormality is detected, the analysis results are sent to the user as a notification containing details.

[0970] Specific examples

[0971] Examples of tire inspections:

[0972] 1. The user launches the app and selects "Tire Inspection."

[0973] 2. The app will prompt you to take a photo of the left front tire.

[0974] 3. The user uses their smartphone to take a photo of the left front tire.

[0975] 4. The photo is sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[0976] 5. The server notifies the user of the analysis results and sends a message such as "There is a loose screw in the left front tire."

[0977] Examples of engine sound checks:

[0978] 1. The user launches the app and selects "Check Engine Sound."

[0979] 2. The app will prompt you to "Start the engine and record the sound."

[0980] 3. The user starts the engine and records the sound.

[0981] 4. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[0982] 5. The server detects an abnormal sound and notifies the user that "there is something wrong with the engine startup sound."

[0983] As described above, the user can perform highly accurate vehicle inspections with simple operations.

[0984] The processing flow will be explained below.

[0985] Step 1:

[0986] The user launches the dedicated app on their smartphone and selects an inspection item (e.g., tire inspection, vehicle body inspection, engine sound inspection) from the main screen.

[0987] Step 2:

[0988] The app will then display specific instructions for the inspection item selected by the user (e.g., "Take a photo of the left front tire").

[0989] Step 3:

[0990] The user uses the smartphone camera to take a photo of the specified area according to the instructions (e.g., a photo of the left front tire).

[0991] Step 4:

[0992] The device temporarily stores the captured photos in its internal storage.

[0993] Step 5:

[0994] The device transmits the stored photo data to a server via the Internet.

[0995] Step 6:

[0996] The server receives the transmitted photo data and inputs it into the generative AI model.

[0997] Step 7:

[0998] The server uses a generative AI model to analyze the photo data and detect, for example, tire pressure, loose screws, and distortions.

[0999] Step 8:

[1000] The server generates the analysis results and organizes them, including details of any problems.

[1001] Step 9:

[1002] The server sends the analysis results to the device.

[1003] Step 10:

[1004] The device notifies the user of the analysis results it has received, including a specific message such as, "There is a loose screw in the left front tire."

[1005] Step 11:

[1006] The user checks the notification and takes appropriate measures as instructed, if necessary (e.g., check the tire screws and correct any looseness).

[1007] Engine sound inspections follow similar steps, but use a smartphone's microphone instead of a camera to analyze the recorded audio data. Specifically, the engine sound is recorded, the recorded data is sent to a server, analyzed by a generative AI model, and the user is notified if any abnormalities are detected. In this way, the system is designed to enable users to easily perform high-precision vehicle inspections.

[1008] Example 1

[1009] 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."

[1010] Conventional vehicle inspection systems require specialized knowledge and advanced equipment, making it difficult for general users to easily perform pre-inspections of their vehicles. Furthermore, they are limited to simply checking inspection items, and even if a problem is discovered, it is difficult to obtain analysis results that lead to details and countermeasures. This has led to many vehicle owners neglecting daily inspections, resulting in an increased risk of accidents and breakdowns.

[1011] 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.

[1012] In this invention, the server includes means for allowing a user to select vehicle inspection items, means for capturing images of the vehicle using a camera of a mobile device, means for capturing audio data of the vehicle using a microphone of the mobile device, means for transmitting the captured image and audio data to a remote computer system, means for analyzing the transmitted image and audio data using a generative AI model in the remote computer system, means for guiding the user to appropriate shooting positions and angles according to the inspection items, and means for notifying the user of the analysis results upon completion of the analysis. This enables general users to easily perform high-precision pre-inspections of their vehicles using their smartphones.

[1013] "User" refers to an individual who operates a mobile terminal to perform an automobile inspection.

[1014] "Mobile device" means a mobile electronic device containing a camera and microphone used for motor vehicle inspections.

[1015] "Camera" refers to a device for taking images and acquiring the data.

[1016] A "microphone" refers to a device for recording sound and acquiring that data.

[1017] "Server" refers to a remote computer system for receiving and analyzing data, generating results and notifying the user.

[1018] "Generative AI model" refers to an algorithm that uses machine learning to analyze transmitted image and audio data.

[1019] "Inspection item" refers to an action that the user can select to inspect a specific part of the vehicle.

[1020] A "prompt sentence" refers to a sentence that indicates the next operation or instruction to the user.

[1021] "Analysis results" refers to the diagnostic information obtained after data analysis is performed by a generative AI model.

[1022] "Remote computer system" refers to a computer system at a remote location that is used to receive and analyze data transmitted from a mobile device.

[1023] MODE FOR CARRYING OUT THE INVENTION

[1024] A specific embodiment for carrying out the present invention will be described in detail. This system allows a user to perform a pre-ride inspection of a vehicle using a mobile device. This system uses the camera and microphone of the mobile device, and transmits the acquired data to a server for analysis, thereby achieving highly accurate vehicle inspections.

[1025] System Components

[1026] The main components of the system are:

[1027] User: The individual who operates the mobile device and performs the vehicle inspection.

[1028] Terminal: A mobile terminal used for vehicle inspections, equipped with a camera and microphone.

[1029] Server: A remote computer system that analyzes the acquired data using generative AI models.

[1030] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[1031] Program processing overview

[1032] 1. The user launches the dedicated app on their mobile device and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[1033] 2. The device uses the camera to capture images for each inspection item. For example, if inspecting tires, the app will guide the user on the shooting position and angle, and the user will follow the instructions to take a photo of the tires. The captured image is temporarily stored on the device and then sent to the server.

[1034] 3. The device uses a microphone to capture audio data. For example, if you are checking the engine sound, it will record the sound when the engine starts, store the data temporarily on the device, and then send it to the server.

[1035] 4. The server inputs the received image and audio data into a generative AI model, which analyzes tire pressure, loose screws, distortions, scratches on the body, cracked glass, dangerous distortions, and abnormal engine start-up sounds.

[1036] 5. The server notifies the user of the analysis results, for example, sending a message such as "There is a loose screw in the left front tire" or "There is something unusual about the engine start-up sound."

[1037] Examples of concrete examples and prompts

[1038] Consider the following scenario:

[1039] 1. The user launches the app and selects "Tire Inspection."

[1040] Example prompt: "Take a photo of the left front tire."

[1041] 2. Following the prompts from the app, the user takes a photo of the left front tire using their smartphone camera.

[1042] 3. The photos are sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[1043] 4. The server notifies the user with the message "There is a loose screw in the left front tire."

[1044] Also, specific examples of engine sound checks include:

[1045] 1. The user launches the app and selects "Check Engine Sound."

[1046] Example prompt: "Start the engine and record the sound."

[1047] 2. The user starts the engine and records the sound.

[1048] 3. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[1049] 4. The server notifies the user that "there is something wrong with the engine start-up sound."

[1050] As explained above, users can perform highly accurate vehicle inspections with simple operations. This allows general users to know the condition of their vehicles in real time, enabling safe and efficient vehicle management.

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

[1052] Program processing flow

[1053] Step 1:

[1054] The user launches the dedicated app on their mobile device and taps the "Start Inspection" button from the main menu. The input here is the user's operation, and the output is the display of a screen for selecting inspection items.

[1055] Step 2:

[1056] The user selects the desired inspection item from the displayed list of inspection items, such as "tire inspection," "body inspection," or "engine sound inspection." The input is the selection of the inspection item, and the output is the next instruction screen based on the selected item.

[1057] Step 3:

[1058] The terminal displays a prompt corresponding to the selected inspection item. For example, if "Tire Inspection" is selected, the prompt "Please take a photo of the left front tire" is displayed. The input is the selected inspection item, and the output is the display of instructions to the user.

[1059] Step 4:

[1060] The user uses the camera on the mobile device to take a picture of the specified area according to the prompt. The input is the camera operation, and the output is the captured image data.

[1061] Step 5:

[1062] The device temporarily stores the captured image data and prepares it for transmission to the server. The input is the image data, and the output is the temporarily stored data and subsequent preparation for data transmission.

[1063] Step 6:

[1064] The terminal sends the temporarily stored image data to the server. The input is the stored image data, and the output is the data sent to the server.

[1065] Step 7:

[1066] The server inputs the received image data into a generative AI model to analyze tire pressure, loose screws, and distortion. The input is image data, and the output is the analysis results.

[1067] Step 8:

[1068] The server generates the analysis results and creates a notification message such as "There is a loose screw on the left front tire." The input is the analysis results, and the output is the notification message.

[1069] Step 9:

[1070] The server sends the generated notification message to the user's mobile terminal. The input is the notification message, and the output is the message displayed on the user's terminal.

[1071] Engine sound inspection procedure

[1072] Step 1:

[1073] The user launches the app and selects "Check Engine Sound." The input is the user's operation, and the output is the display of a screen instructing the user to record the engine sound.

[1074] Step 2:

[1075] The terminal displays the prompt "Start the engine and record the sound." The input is the selected inspection item, and the output is the display of instructions to the user.

[1076] Step 3:

[1077] The user starts the engine and records the sound. The input is the microphone operation, and the output is the recorded audio data.

[1078] Step 4:

[1079] The terminal temporarily stores the recorded voice data and prepares it to be sent to the server. The input is the voice data, and the output is the temporarily stored data and the preparation for subsequent data transmission.

[1080] Step 5:

[1081] The terminal transmits the temporarily stored voice data to the server. The input is the stored voice data, and the output is the data transmitted to the server.

[1082] Step 6:

[1083] The server inputs the received audio data into the generative AI model and analyzes engine sound abnormalities. The input is the audio data, and the output is the analysis result.

[1084] Step 7:

[1085] The server generates the analysis result and creates a notification message saying, "There is something wrong with the engine start sound." The input is the analysis result, and the output is the notification message.

[1086] Step 8:

[1087] The server sends the generated notification message to the user's mobile terminal. The input is the notification message, and the output is the message displayed on the user's terminal.

[1088] The detailed processing in each step above allows the user to properly perform various inspections of the vehicle, allowing the user to grasp the condition of the vehicle in real time and manage it safely and efficiently.

[1089] (Application example 1)

[1090] 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."

[1091] Periodic or reactive diagnosis of vehicle conditions is important for operational safety and performance maintenance. However, conventional methods require specialized knowledge for many inspection tasks, making it difficult for users to easily perform self-diagnosis. Furthermore, autonomous vehicles also require methods for quickly and accurately detecting abnormalities in each part of the vehicle, but this requires advanced functionality and analytical capabilities.

[1092] 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.

[1093] In this invention, the server includes means for allowing a user to select vehicle inspection items, means for capturing images of the vehicle using a camera of the smart device, means for capturing audio data of the vehicle using a microphone of the smart device, means for transmitting the captured image and audio data to the server, means for analyzing the transmitted image and audio data using a generative AI model in the server, means for notifying the user of the analysis results, and means for periodically or reactively diagnosing the vehicle condition so that the autonomous vehicle can perform self-diagnosis. This allows users to easily diagnose the condition of the vehicle without requiring specialized knowledge, and the autonomous vehicle's self-diagnosis function allows it to quickly and accurately detect vehicle abnormalities, thereby maintaining safety and performance.

[1094] A "user" is an individual who operates a smart device to perform an automobile inspection.

[1095] A "smart device" is an electronic device that has a built-in camera and microphone and has the ability to acquire data and send it to a server.

[1096] A "camera" is an optical device for acquiring image data.

[1097] A "microphone" is an acoustic device for acquiring audio data.

[1098] A "server" is a remote computer system that analyzes the acquired data and notifies the user of the results.

[1099] A "generative AI model" is a machine learning model used to analyze captured image and audio data.

[1100] "Analysis" is the process of extracting information based on the acquired data and identifying abnormalities or problems.

[1101] "Notification" is the process of informing the user of the analysis results.

[1102] An "autonomous vehicle" is a vehicle that does not require human operation and has self-diagnostic capabilities.

[1103] "Self-diagnosis" is a function that allows the vehicle itself to check its condition and detect abnormalities.

[1104] "Periodic" means repeatedly at a series of intervals.

[1105] "Reactive" means responding immediately to events that occur.

[1106] "Condition" refers to the current state of each part and function of the vehicle.

[1107] An "image" is visual data captured by a camera.

[1108] "Audio data" is acoustic data acquired by a microphone.

[1109] "Data transmission" is the process of sending the acquired data over the network to the server.

[1110] "Safety" refers to the reliability of vehicles to ensure safe operation.

[1111] "Performance retention" means that the vehicle maintains good performance over a long period of time.

[1112] The present invention provides a system for easily diagnosing the condition of an automobile, and in particular for enhancing the self-diagnosis function of an autonomous vehicle. Specific embodiments for carrying out the present invention will be described in detail below.

[1113] System configuration

[1114] The main components of the system are:

[1115] User: An individual who operates a smart device to inspect a vehicle. In the case of autonomous vehicles, the vehicle itself performs self-diagnosis.

[1116] Smart device: An electronic device used for vehicle inspections that has a built-in camera and microphone. The camera captures image data, and the microphone captures audio data.

[1117] Server: A remote computer system that uses generative AI models to analyze the acquired data and notify the user of the results.

[1118] Generative AI model: Performs data analysis as a machine learning model to analyze the condition of each part of the car.

[1119] Data acquisition and analysis

[1120] Tire Diagnosis

[1121] The user captures an image of the tire using the camera on their smart device. The image is then sent to a server, where it is analyzed using a generative AI model to detect tire pressure, loose screws, and distortion. The results of the analysis are then reported to the user.

[1122] Body diagnostics

[1123] The user uses the camera on their smart device to capture images of the vehicle, which are then sent to a server that analyzes them using a generative AI model to detect scratches on the vehicle body, cracks in the glass, and dangerous distortions. The results of the analysis are then reported to the user.

[1124] Engine sound diagnosis

[1125] The user records the engine sound using the microphone on their smart device. The captured audio data is sent to the server, which then analyzes the engine sound using a generative AI model. If an abnormality is detected, the user is notified of the details.

[1126] Self-diagnosis for autonomous vehicles

[1127] In autonomous vehicles, the system performs self-diagnosis periodically or reactively. It uses cameras, microphones, and other sensors built into the vehicle to collect data, which is then sent to a server. The server then analyzes the data using generative AI models, and if an abnormality is detected, a notification is sent to the vehicle's infotainment system or the driver.

[1128] Hardware and software used

[1129] Hardware:

[1130] Smart device (with built-in camera and microphone)

[1131] Built-in cameras, microphones, and various sensors in autonomous vehicles

[1132] software:

[1133] OpenCV: Camera control and image acquisition

[1134] sounddevice library: audio recording

[1135] The requests library: data transmission and server communication

[1136] Generative AI Models: Data Analysis

[1137] Specific examples

[1138] Example prompt sentence:

[1139] "Take a photo of the left front tire and automatically transfer it."

[1140] "Start the engine, record the audio, and automatically transmit it."

[1141] Example of operation steps:

[1142] The user opens the smart device app and selects the tire diagnosis item.

[1143] The user points the smart device at the front wheel of the vehicle, activates the camera, and captures an image.

[1144] The captured images are sent to a server and analyzed by a generative AI model.

[1145] The analysis results are notified to the user, displaying the message "Loose screws have been detected in the left front tire."

[1146] In this way, the present invention aims to enable users to easily diagnose the condition of their vehicle without requiring specialized knowledge. Furthermore, by strengthening the self-diagnosis function of autonomous vehicles, it is possible to quickly and accurately detect vehicle abnormalities, thereby realizing safety and maintaining performance.

[1147] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1148] Step 1:

[1149] The user launches the app on their smart device and selects an inspection item. The user's operation is input, the inspection item selection is output, and the system proceeds to the next data acquisition step.

[1150] Step 2:

[1151] The terminal uses the smart device's camera to capture images corresponding to the selected inspection item. Specifically, the user points the smart device at the relevant part of the vehicle (e.g., tire or body) and takes a photo with the camera. The input is video data from the camera, and the captured image is output.

[1152] Step 3:

[1153] When the terminal uses the microphone of the smart device to acquire voice data corresponding to the selected inspection item, the user records the engine sound according to the instructions. The input is the voice data from the microphone, and the acquired voice is output.

[1154] Step 4:

[1155] The image and audio data acquired by the device is sent to the server. Specifically, a network request is used to upload the acquired data files to the server. The input is the image and audio data files, and the output is the completion of data transmission to the server.

[1156] Step 5:

[1157] The image and audio data received by the server is input into the generative AI model for analysis. Specifically, the server inputs the data into the generative AI model, which then performs image and audio analysis. The input is image data and audio data, and the analysis results are output.

[1158] Step 6:

[1159] The server notifies the user of the analysis results. Specifically, the analysis results (for example, abnormal tire pressure, loose screws, abnormal engine noise, etc.) are generated and sent to the user's smart device as a notification message. The input is the analysis results, and the output is the completion of notification to the user.

[1160] Step 7:

[1161] In the case of self-diagnosis in an autonomous vehicle, the vehicle automatically performs steps 1 to 6 periodically or as needed, without requiring user intervention. The input is the vehicle's automatic diagnostic system, and the output is notification of the self-diagnosis results.

[1162] 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.

[1163] A specific embodiment for carrying out the present invention will be described in detail. The system described below allows a user to use a smartphone to perform a pre-ride inspection of a vehicle, and uses an emotion engine to recognize the user's emotions and provide appropriate feedback. This system transmits data acquired using the smartphone's camera and microphone to a server, and notifies the user of the analysis results based on the user's emotions.

[1164] System configuration

[1165] The main components of the system are:

[1166] User: The individual who operates the smartphone and performs the vehicle inspection.

[1167] Device: A smartphone used for vehicle inspections, equipped with a built-in camera and microphone.

[1168] Server: A remote computer system that analyzes the acquired data using a generative AI model and emotion engine.

[1169] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[1170] Emotion engine: A model that recognizes emotions from user voice and text data and generates appropriate feedback based on those emotions.

[1171] Explanation of program processing

[1172] 1. User operations and data acquisition

[1173] The user starts the dedicated app on their smartphone and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[1174] 2. Check your tires

[1175] The device uses the camera to take photos of each tire to check its condition. When taking photos, the app guides the user on the shooting position and angle. The photos are temporarily saved on the smartphone and then automatically sent to the server.

[1176] The server inputs the received photos into a generative AI model to analyze tire pressure, loose screws, and distortions. The analysis results are then sent to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[1177] The server generates a feedback message based on the user's sentiment, including specific advice such as "A slight looseness has been detected, but it can be easily corrected with a specific tool."

[1178] 3. Inspect the vehicle body

[1179] To check the overall condition of the vehicle, the user takes a photo of the vehicle using the smartphone camera. The app guides the user to take an appropriate photo by specifying the shooting position and angle. The captured photo of the vehicle is temporarily saved on the smartphone and then sent to the server.

[1180] The server inputs the received photos of the car body into a generative AI model, which analyzes scratches on the car body, cracks in the glass, and dangerous distortions.The analysis results are then sent to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[1181] The server generates a feedback message based on the user's sentiment, including specific advice such as "I found a small scratch on the car body, but it's not a serious problem."

[1182] 4. Check the sound when starting the engine

[1183] The user follows the app's instructions to record the engine sound using the smartphone's microphone. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[1184] The server inputs the received voice data into a generative AI model to analyze any abnormalities in the engine start-up sound.Then, it sends the analysis results to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[1185] The server generates a feedback message based on the user's emotions, including specific advice such as "An abnormality has been detected in the engine start-up sound. We recommend that you repair it immediately."

[1186] Specific examples

[1187] Examples of tire inspections:

[1188] 1. The user launches the app and selects "Tire Inspection."

[1189] 2. The app will prompt you to take a photo of the left front tire.

[1190] 3. The user uses their smartphone to take a photo of the left front tire.

[1191] 4. The photo is sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[1192] 5. The analysis results are sent to the emotion engine.

[1193] 6. The emotion engine recognizes emotions from the user's voice data and generates a feedback message.

[1194] 7. The server notifies the user of the analysis results and a feedback message, such as "There is a loose screw on the left front tire, but this can be easily fixed."

[1195] Examples of engine sound checks:

[1196] 1. The user launches the app and selects "Check Engine Sound."

[1197] 2. The app will prompt you to "Start the engine and record the sound."

[1198] 3. The user starts the engine and records the sound.

[1199] 4. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[1200] 5. The analysis results are sent to the emotion engine.

[1201] 6. The emotion engine recognizes emotions from the user's voice data and generates a feedback message.

[1202] 7. The server notifies the user of the analysis results and a feedback message, such as "There is something wrong with the engine start-up sound. Repairs are recommended."

[1203] As described above, the user can perform highly accurate vehicle inspections with simple operations and can also receive appropriate feedback according to their emotions.

[1204] The processing flow will be explained below.

[1205] Step 1:

[1206] The user launches the dedicated app on their smartphone. The app's main screen appears, and they can select an inspection item (tire inspection, vehicle body inspection, engine sound inspection).

[1207] Step 2:

[1208] The app will then display specific instructions based on the inspection item the user selects. For example, if the user selects a tire inspection, the app will prompt the user to "take a photo of the left front tire."

[1209] Step 3:

[1210] The user uses the smartphone camera to take a photo of the specified area (e.g., the left front tire).

[1211] Step 4:

[1212] The device temporarily stores the captured photos in its internal storage.

[1213] Step 5:

[1214] The device transmits the stored photo data to a server via the Internet.

[1215] Step 6:

[1216] The server receives the transmitted photo data and inputs it into the generative AI model.

[1217] Step 7:

[1218] The server uses a generative AI model to analyze the photo data and detect, for example, tire pressure, loose screws, and distortions.

[1219] Step 8:

[1220] The server sends the analysis results to the emotion engine.

[1221] Step 9:

[1222] In order for the emotion engine to recognize emotions from the user's voice data, it asks the user a question (e.g., "Are you okay?") and acquires the voice data.

[1223] Step 10:

[1224] The emotion engine analyzes the voice data and recognizes the user's emotions, such as anxiety, relief, and surprise.

[1225] Step 11:

[1226] The server generates an appropriate feedback message based on the analysis results and the user's emotions. For example, if the user is feeling anxious, it creates a message saying, "A loose screw has been detected, but don't worry, it can be easily fixed."

[1227] Step 12:

[1228] The server sends the generated feedback message to the terminal.

[1229] Step 13:

[1230] The device notifies the user of the received feedback message, which includes the analysis results and advice based on the user's emotions.

[1231] Step 14:

[1232] The user checks the notification and takes appropriate measures as instructed, if necessary (e.g., check the tire screws and correct any looseness).

[1233] Specific examples

[1234] Examples of tire inspections:

[1235] Step 1:

[1236] The user launches the app and selects "Tire Inspection."

[1237] Step 2:

[1238] The app will then prompt you to "Take a photo of the left front tire."

[1239] Step 3:

[1240] The user uses a smartphone to take a photo of the left front tire.

[1241] Step 4:

[1242] The photos you take will be saved on your device.

[1243] Step 5:

[1244] The saved photo data is sent to the server.

[1245] Step 6:

[1246] The server receives the photo data and analyzes it using a generative AI model.

[1247] Step 7:

[1248] The server detects tire pressure, loose screws, and distortion.

[1249] Step 8:

[1250] The analysis results are sent to the emotion engine.

[1251] Step 9:

[1252] The emotion engine asks the user for their reaction and tells them, "Loose screws detected."

[1253] Step 10:

[1254] The user responds and asks, "What do I do?"

[1255] Step 11:

[1256] The emotion engine recognizes anxiety from the user's voice data and combines it with the analysis results to generate appropriate feedback.

[1257] Step 12:

[1258] The server creates a message saying, "Loose screws have been detected, but don't worry, they can be easily fixed with a specific tool."

[1259] Step 13:

[1260] The generated message is sent to the terminal.

[1261] Step 14:

[1262] The device will then send a message to the user, containing the tire analysis results and instructions on how to fix the threads.

[1263] Through these steps, users can not only perform highly accurate inspections of their vehicles, but also receive appropriate support tailored to their emotions.

[1264] Example 2

[1265] 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."

[1266] Conventional vehicle inspection methods require specialized knowledge and tools, making it difficult for ordinary users to perform inspections themselves. In addition, since feedback that takes into account the user's emotions is not provided, there is a risk that the user may not understand or respond well to the inspection results.

[1267] 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.

[1268] In this invention, the server includes means for analyzing the transmitted image and audio data using a generative AI model, means for sending the analysis results to an emotion recognition engine and generating feedback based on the user's emotions, and means for notifying the user of the analysis results and feedback. This allows even ordinary users to easily inspect their vehicles and receive appropriate feedback according to the user's emotions.

[1269] "User" refers to an individual who uses a mobile information terminal to perform an automobile inspection.

[1270] A "mobile information terminal" refers to a device such as a smartphone or tablet that has a built-in camera and microphone and can run dedicated apps.

[1271] "Server" refers to a remote computer system that uses a generative AI model and an emotion recognition engine to analyze the received data and notify the user of the analysis results.

[1272] A "generative AI model" refers to a model that uses machine learning technology to analyze the condition of each part of a car.

[1273] An "emotion recognition engine" refers to a model that recognizes emotions from a user's voice or text data and generates appropriate feedback based on that.

[1274] "Analysis results" refers to information analyzed by the generative AI model, such as tire pressure, loose screws, distortions, scratches on the body, cracks in the glass, and abnormal engine sounds.

[1275] "Feedback" refers to specific advice or notification messages generated based on the analysis results and the user's emotions.

[1276] "Inspection items" refer to vehicle inspection items that can be selected by the user, such as tire inspection, body inspection, and engine sound inspection.

[1277] "Data acquisition means" refers to a means for acquiring images and audio data of a vehicle using a camera or microphone of a mobile information terminal.

[1278] The "data transmission means" refers to a means for transmitting image and audio data acquired by the mobile information terminal to the server.

[1279] This invention is a system that allows a user to inspect a vehicle using a mobile information terminal, and uses a generative AI model and an emotion recognition engine to recognize the user's emotions and provide appropriate feedback. This system acquires data using the mobile information terminal's camera and microphone, sends it to a server, and generates and notifies feedback based on the analysis results.

[1280] System Components

[1281] The main components of the system are:

[1282] User: An individual who operates a mobile information terminal and performs a vehicle inspection.

[1283] Terminal: A personal digital assistant used for vehicle inspections, equipped with a camera and microphone.

[1284] Server: A remote computer system that analyzes acquired data using a generative AI model and emotion recognition engine.

[1285] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[1286] Emotion recognition engine: A model that recognizes emotions from the user's voice and text data and generates appropriate feedback based on that.

[1287] Data Acquisition and Transmission

[1288] The user starts the dedicated app on their mobile device and begins the inspection. They select the desired inspection item from the app's main screen and follow the data acquisition procedure. Inspection items include tire inspection, vehicle body inspection, and engine sound inspection.

[1289] In the case of tire inspections, the device uses the camera to take a photo of each tire. The app guides the user on the shooting position and angle, and the photos are temporarily stored on the mobile information device before being sent to the server. As a concrete example, the user may be instructed to "take a photo of the left front tire" and follow that instruction.

[1290] During a vehicle inspection, the user uses the camera on their mobile device to take a photo of the vehicle. The app instructs the user on the best shooting position and angle. The photos are temporarily stored on the device and later sent to the server. A specific example is a procedure where the user is guided to "take a photo of the entire vehicle."

[1291] To check the engine sound, the user records the engine sound using the microphone on the mobile information terminal. The recorded audio data is temporarily stored in the terminal and then sent to the server. As a concrete example, the user is instructed to "start the engine and record the sound."

[1292] Data analysis and feedback

[1293] The server receives the transmitted image and audio data and analyzes it using a generative AI model. For example, tire images can be used to detect air pressure, loose screws, and distortions. Images of the car body can be analyzed for scratches, cracked glass, and dangerous distortions. Engine sound data can be used to detect abnormal sounds.

[1294] The analysis results are sent to an emotion recognition engine on the server, which recognizes the user's emotional state from their voice and text data. Specific and appropriate feedback is generated based on the analysis results and emotional data. For example, it may include advice such as, "There's a loose screw on the left front tire, but that can be easily fixed."

[1295] Notifications and Feedback

[1296] The server notifies the user of the generated feedback message. For example, when the user receives the analysis result, the server notifies the user that "a small scratch was found on the car body, but it is not a serious problem."

[1297] In this way, the system of the present invention allows even ordinary users to easily inspect their vehicles and provides appropriate feedback according to the user's emotions. By using this system, users can easily obtain highly accurate inspection results and can quickly take appropriate action.

[1298] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1299] Step 1:

[1300] The user launches a dedicated app on their mobile information terminal and begins the inspection.

[1301] Input: Launching an app on a mobile device

[1302] Output: The main screen of the app is displayed, and the Start Inspection button is available.

[1303] Specific operation: The user taps the icon to launch the app. After launching, a "Start inspection" button appears on the main screen.

[1304] Step 2:

[1305] The user selects the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection).

[1306] Input: User taps to select an inspection item

[1307] Output: A screen corresponding to the selected inspection item will be displayed.

[1308] Specific operation: The user taps the desired item from "Tire Inspection," "Body Inspection," or "Engine Sound Inspection" on the main screen. Depending on the selection, a guide screen for the next step will be displayed.

[1309] Step 3:

[1310] The terminal displays instructions to the user to retrieve the data.

[1311] Input: Selected inspection items

[1312] Output: A guide message for data acquisition is displayed.

[1313] Specific actions: Instructions such as "Take a photo of the left front tire" and "Start the engine and record the sound" will appear on the device screen.

[1314] Step 4:

[1315] The user captures the data using the camera or microphone of the mobile information terminal.

[1316] Input: User performs data capture operations (photographs and audio recordings)

[1317] Output: Captured image or audio data

[1318] Specific operation: The user uses the camera to take photos of the tires and vehicle body, and uses the microphone to record the engine sound. The acquired data is temporarily stored on the device.

[1319] Step 5:

[1320] The terminal transmits the acquired data to the server.

[1321] Input: Captured image or audio data

[1322] Output: The data sent.

[1323] Specific operation: The device automatically uploads images and audio data stored internally to the server.

[1324] Step 6:

[1325] The server inputs the received data into the generative AI model and analyzes it.

[1326] Input: Transmitted image or audio data

[1327] Output: Analysis results (tire pressure, loose screws, scratches on the car body, abnormal engine sounds, etc.)

[1328] Specific operation: The server inputs the received data into the generative AI model and performs analytical processing to identify abnormalities and conditions.

[1329] Step 7:

[1330] The server sends the analysis results to an emotion recognition engine to recognize the user's emotions.

[1331] Input: Analysis results and user voice data

[1332] Output: User's emotional state

[1333] Specific operation: The server inputs the analysis results into an emotion recognition engine, analyzes the user's voice and text data, and recognizes major emotions such as joy, anger, sadness, and happiness.

[1334] Step 8:

[1335] The server generates a feedback message based on the analysis results and the user's emotions.

[1336] Input: Analysis results and emotion data

[1337] Output: Feedback message (e.g. "There is a loose screw in the left front tire, but this is an easy fix.")

[1338] Specific behavior: The server combines the analysis results with the user's emotions to generate specific and appropriate feedback.

[1339] Step 9:

[1340] The server notifies the user of the feedback message.

[1341] Input: Feedback message

[1342] Output: Notification message sent to the user

[1343] Specific operation: The server sends the generated feedback message to the mobile information terminal and displays it on the terminal screen.

[1344] (Application example 2)

[1345] 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."

[1346] In conventional vehicle inspection systems, it is difficult for users to accurately grasp the situation when performing the inspection themselves, resulting in the risk of making inappropriate decisions.Furthermore, they often provide uniform feedback without considering the user's emotional state, which has the problem of not being able to reduce user stress.

[1347] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring images of the vehicle using a camera of the communication terminal, means for acquiring voice data of the vehicle using a microphone of the communication terminal, means for analyzing the transmitted image and voice data using a generative AI model, means for generating a feedback message based on the analysis result by the generative AI model and the user's emotion using an emotion recognition engine, and means for notifying the user of the feedback message. This allows the user to obtain accurate vehicle inspection results and, further, to receive appropriate feedback according to the user's emotional state, thereby reducing stress.

[1348] A "user" is an individual or group that operates a communication terminal to inspect a vehicle.

[1349] A "communication terminal" is a device that has a built-in camera and microphone and is used by a user to inspect a vehicle. Examples include smartphones.

[1350] "Camera" means an optical instrument used to capture images of a vehicle.

[1351] A "microphone" is an acoustic device used to capture audio data from a vehicle.

[1352] A "server" is a remote computer system that analyzes data sent by a communication terminal and generates appropriate feedback messages.

[1353] A "generative AI model" is a machine learning model that analyzes acquired image and audio data to determine the vehicle's condition.

[1354] An "emotion recognition engine" is a software model for identifying emotions from a user's voice or text data and adjusting feedback messages accordingly.

[1355] A "feedback message" is a message that the server generates based on the analysis results and that includes advice or warning information to notify the user.

[1356] A "vehicle" is a machine used as a means of transportation, and specific examples include automobiles and self-driving vehicles.

[1357] To implement this invention, a system is required in which users, communication terminals, servers, generative AI models, and emotion recognition engines work together seamlessly. The detailed configuration of this system and the role of each element are described below.

[1358] Key components of the system

[1359] User: An individual or organization that inspects a vehicle and operates a communication terminal.

[1360] Communication terminal: A device with a built-in camera and microphone that allows users to obtain vehicle inspection data. Specific examples include smartphones.

[1361] Server: A high-performance computer system that receives data sent from communication devices and analyzes and provides feedback using a generative AI model and emotion recognition engine.

[1362] Generative AI model: A model that uses machine learning techniques to analyze transmitted image and audio data.

[1363] Emotion recognition engine: A software model that recognizes emotions from user voice and text data and adjusts the content of feedback messages.

[1364] Program processing overview

[1365] The user launches a dedicated app on the communication device and selects an inspection item. The communication device uses a camera to capture images of the vehicle and a microphone to capture audio data from the vehicle. This data is temporarily stored on the device and then sent to the server.

[1366] The server inputs the received image and voice data into a generative AI model to analyze the condition of each part of the vehicle. The analysis results are then transferred to an emotion recognition engine, which recognizes emotions from the user's voice data and generates appropriate feedback messages based on that.

[1367] Hardware and software used

[1368] Hardware: Smartphone (camera, built-in microphone), server (high-performance computer)

[1369] Software: Python, OpenCV (image processing library), requests (HTTP request library), emotion_recognition (emotion recognition library), ai_model (generative AI model)

[1370] Data processing and calculation

[1371] Image and audio data captured using the communication device's camera and microphone are sent to the server via HTTP requests. On the server, a generative AI model analyzes the image data to determine the condition of each part of the vehicle. An emotion recognition engine also evaluates the user's emotions from the audio data and uses the results to generate feedback messages that are optimal for the analysis results.

[1372] Specific examples

[1373] When selecting "tire inspection" as an inspection item, the user uses the camera on their communication device to take sequential images of the tires. The communication device then sends this image data to the server, which then uses a generative AI model to analyze the tire's air pressure, loose screws, and distortion. Based on the analysis results and the user's emotion recognition results, a feedback message containing specific advice is generated.

[1374] Example prompts to input to the generative AI model

[1375] "Please analyze images taken from the front of the vehicle to check the status of the front sensors. Also, please detect any abnormalities based on the recorded engine sound data."

[1376] In this way, the present invention enables users to easily perform highly accurate vehicle inspections, and further reduces stress for users by providing appropriate feedback based on emotion recognition.

[1377] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1378] Step 1: The user launches the dedicated app on the communication device and selects an inspection item. This allows the user to begin operations to inspect specific vehicle parts, such as tires, the body, or engine noise. The input is the inspection item selected by the user, and the output is the next guideline for the inspection item.

[1379] Step 2: The user acquires images of the vehicle using the camera on the communication device. For example, if the user selects tire inspection, the user takes a photo of each tire with the smartphone camera. The app displays guidelines to guide the user to take photos from the appropriate position and angle. The input is the image data captured by the user, and the output is the image data temporarily stored in the communication device.

[1380] Step 3: The user acquires vehicle audio data using the microphone on the communication device. For example, if the user selects engine sound inspection, the user records the engine start-up sound using the microphone on their smartphone. The input is the recorded audio data, and the output is the audio data temporarily stored in the communication device.

[1381] Step 4: The captured image and audio data are sent to the server via an HTTP request. The communication device combines the image and audio data into a single request and sends it to the server's data receiving endpoint. The input is the image and audio data stored in the communication device, and the output is the data sent to the server.

[1382] Step 5: The server uses the generative AI model to analyze the received image data and determine the condition of each part of the vehicle. For example, if it is an image of a tire, it will analyze the air pressure, loose screws, and distortion. The input is the image data sent to the server, and the output is the tire condition data as the analysis result.

[1383] Step 6: The server similarly analyzes the received audio data using the generative AI model to check for abnormalities in the vehicle's engine sound. The input is the audio data sent to the server, and the output is the engine sound status data as the analysis result.

[1384] Step 7: The analysis results are passed to the emotion recognition engine in the server, where the process of recognizing emotions from the user's voice data is carried out. The input is the user's voice data, and the output is the recognized user's emotion data.

[1385] Step 8: The server generates an appropriate feedback message based on the analysis results and the user's emotional data. For example, if the user is nervous, the feedback message can use gentler language or include more detailed explanations. The input is the analysis results and emotional data, and the output is the feedback message.

[1386] Step 9: The feedback message is sent to the communication terminal as an HTTP response and notified to the user. The communication terminal receives this and displays the message to the user in the app. The input is the feedback message from the server, and the output is the feedback message notified to the user.

[1387] 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.

[1388] 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.

[1389] 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.

[1390] [Fourth embodiment]

[1391] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1392] 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.

[1393] 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).

[1394] 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.

[1395] 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.

[1396] 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).

[1397] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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.

[1402] 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.

[1403] 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."

[1404] A specific embodiment for carrying out the present invention will be described in detail. The system described below allows a user to perform a pre-boarding inspection of a vehicle using a smartphone. This system uses the smartphone's camera and microphone, and transmits the acquired data to a server for analysis, thereby achieving highly accurate vehicle inspections.

[1405] System configuration

[1406] The main components of the system are:

[1407] User: The individual who operates the smartphone and performs the vehicle inspection.

[1408] Device: A smartphone used for vehicle inspections, equipped with a built-in camera and microphone.

[1409] Server: A remote computer system that analyzes the acquired data using a generative AI model.

[1410] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[1411] Explanation of program processing

[1412] 1. User operations and data acquisition

[1413] The user starts the dedicated app on their smartphone and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[1414] 2. Check your tires

[1415] The device uses the camera to take photos of each tire to check its condition. When taking photos, the app guides the user on the shooting position and angle. The photos are temporarily saved on the smartphone and then automatically sent to the server.

[1416] The server inputs the received photos into a generative AI model to analyze tire pressure, loose screws, and distortion. Once the analysis is complete, the results are notified to the user.

[1417] 3. Inspect the vehicle body

[1418] To check the overall condition of the vehicle, the user takes a photo of the vehicle using the smartphone camera. The app guides the user to take an appropriate photo by specifying the shooting position and angle. The captured photo of the vehicle is temporarily saved on the smartphone and then sent to the server.

[1419] The server inputs the received photos of the car body into a generative AI model, which analyzes the car for scratches, cracks in the glass, and dangerous distortions. The results of the analysis are then notified to the user.

[1420] 4. Check the sound when starting the engine

[1421] The user follows the app's instructions to record the engine sound using the smartphone's microphone. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[1422] The server inputs the received audio data into a generative AI model to analyze any abnormalities in the engine start-up sound. The server notifies the user of the analysis results and advises them on the necessary measures.

[1423] 5. Check the engine sound after starting

[1424] The user records the engine sound for a certain period of time after the engine starts. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[1425] The server inputs the received audio data into a generative AI model to analyze the engine sound for abnormalities. If an abnormality is detected, the analysis results are sent to the user as a notification containing details.

[1426] Specific examples

[1427] Examples of tire inspections:

[1428] 1. The user launches the app and selects "Tire Inspection."

[1429] 2. The app will prompt you to take a photo of the left front tire.

[1430] 3. The user uses their smartphone to take a photo of the left front tire.

[1431] 4. The photo is sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[1432] 5. The server notifies the user of the analysis results and sends a message such as "There is a loose screw in the left front tire."

[1433] Examples of engine sound checks:

[1434] 1. The user launches the app and selects "Check Engine Sound."

[1435] 2. The app will prompt you to "Start the engine and record the sound."

[1436] 3. The user starts the engine and records the sound.

[1437] 4. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[1438] 5. The server detects an abnormal sound and notifies the user that "there is something wrong with the engine startup sound."

[1439] As described above, the user can perform highly accurate vehicle inspections with simple operations.

[1440] The processing flow will be explained below.

[1441] Step 1:

[1442] The user launches the dedicated app on their smartphone and selects an inspection item (e.g., tire inspection, vehicle body inspection, engine sound inspection) from the main screen.

[1443] Step 2:

[1444] The app will then display specific instructions for the inspection item selected by the user (e.g., "Take a photo of the left front tire").

[1445] Step 3:

[1446] The user uses the smartphone camera to take a photo of the specified area according to the instructions (e.g., a photo of the left front tire).

[1447] Step 4:

[1448] The device temporarily stores the captured photos in its internal storage.

[1449] Step 5:

[1450] The device transmits the stored photo data to a server via the Internet.

[1451] Step 6:

[1452] The server receives the transmitted photo data and inputs it into the generative AI model.

[1453] Step 7:

[1454] The server uses a generative AI model to analyze the photo data and detect, for example, tire pressure, loose screws, and distortions.

[1455] Step 8:

[1456] The server generates the analysis results and organizes them, including details of any problems.

[1457] Step 9:

[1458] The server sends the analysis results to the device.

[1459] Step 10:

[1460] The device notifies the user of the analysis results it has received, including a specific message such as, "There is a loose screw in the left front tire."

[1461] Step 11:

[1462] The user checks the notification and takes appropriate measures as instructed, if necessary (e.g., check the tire screws and correct any looseness).

[1463] Engine sound inspections follow similar steps, but use a smartphone's microphone instead of a camera to analyze the recorded audio data. Specifically, the engine sound is recorded, the recorded data is sent to a server, analyzed by a generative AI model, and the user is notified if any abnormalities are detected. In this way, the system is designed to enable users to easily perform high-precision vehicle inspections.

[1464] Example 1

[1465] 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."

[1466] Conventional vehicle inspection systems require specialized knowledge and advanced equipment, making it difficult for general users to easily perform pre-inspections of their vehicles. Furthermore, they are limited to simply checking inspection items, and even if a problem is discovered, it is difficult to obtain analysis results that lead to details and countermeasures. This has led to many vehicle owners neglecting daily inspections, resulting in an increased risk of accidents and breakdowns.

[1467] 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.

[1468] In this invention, the server includes means for allowing a user to select vehicle inspection items, means for capturing images of the vehicle using a camera of a mobile device, means for capturing audio data of the vehicle using a microphone of the mobile device, means for transmitting the captured image and audio data to a remote computer system, means for analyzing the transmitted image and audio data using a generative AI model in the remote computer system, means for guiding the user to appropriate shooting positions and angles according to the inspection items, and means for notifying the user of the analysis results upon completion of the analysis. This enables general users to easily perform high-precision pre-inspections of their vehicles using their smartphones.

[1469] "User" refers to an individual who operates a mobile terminal to perform an automobile inspection.

[1470] "Mobile device" means a mobile electronic device containing a camera and microphone used for motor vehicle inspections.

[1471] "Camera" refers to a device for taking images and acquiring the data.

[1472] A "microphone" refers to a device for recording sound and acquiring that data.

[1473] "Server" refers to a remote computer system for receiving and analyzing data, generating results and notifying the user.

[1474] "Generative AI model" refers to an algorithm that uses machine learning to analyze transmitted image and audio data.

[1475] "Inspection item" refers to an action that the user can select to inspect a specific part of the vehicle.

[1476] A "prompt sentence" refers to a sentence that indicates the next operation or instruction to the user.

[1477] "Analysis results" refers to the diagnostic information obtained after data analysis is performed by a generative AI model.

[1478] "Remote computer system" refers to a computer system at a remote location that is used to receive and analyze data transmitted from a mobile device.

[1479] MODE FOR CARRYING OUT THE INVENTION

[1480] A specific embodiment for carrying out the present invention will be described in detail. This system allows a user to perform a pre-ride inspection of a vehicle using a mobile device. This system uses the camera and microphone of the mobile device, and transmits the acquired data to a server for analysis, thereby achieving highly accurate vehicle inspections.

[1481] System Components

[1482] The main components of the system are:

[1483] User: The individual who operates the mobile device and performs the vehicle inspection.

[1484] Terminal: A mobile terminal used for vehicle inspections, equipped with a camera and microphone.

[1485] Server: A remote computer system that analyzes the acquired data using generative AI models.

[1486] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[1487] Program processing overview

[1488] 1. The user launches the dedicated app on their mobile device and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[1489] 2. The device uses the camera to capture images for each inspection item. For example, if inspecting tires, the app will guide the user on the shooting position and angle, and the user will follow the instructions to take a photo of the tires. The captured image is temporarily stored on the device and then sent to the server.

[1490] 3. The device uses a microphone to capture audio data. For example, if you are checking the engine sound, it will record the sound when the engine starts, store the data temporarily on the device, and then send it to the server.

[1491] 4. The server inputs the received image and audio data into a generative AI model, which analyzes tire pressure, loose screws, distortions, scratches on the body, cracked glass, dangerous distortions, and abnormal engine start-up sounds.

[1492] 5. The server notifies the user of the analysis results, for example, sending a message such as "There is a loose screw in the left front tire" or "There is something unusual about the engine start-up sound."

[1493] Examples of concrete examples and prompts

[1494] Consider the following scenario:

[1495] 1. The user launches the app and selects "Tire Inspection."

[1496] Example prompt: "Take a photo of the left front tire."

[1497] 2. Following the prompts from the app, the user takes a photo of the left front tire using their smartphone camera.

[1498] 3. The photos are sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[1499] 4. The server notifies the user with the message "There is a loose screw in the left front tire."

[1500] Also, specific examples of engine sound checks include:

[1501] 1. The user launches the app and selects "Check Engine Sound."

[1502] Example prompt: "Start the engine and record the sound."

[1503] 2. The user starts the engine and records the sound.

[1504] 3. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[1505] 4. The server notifies the user that "there is something wrong with the engine start-up sound."

[1506] As explained above, users can perform highly accurate vehicle inspections with simple operations. This allows general users to know the condition of their vehicles in real time, enabling safe and efficient vehicle management.

[1507] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1508] Program processing flow

[1509] Step 1:

[1510] The user launches the dedicated app on their mobile device and taps the "Start Inspection" button from the main menu. The input here is the user's operation, and the output is the display of a screen for selecting inspection items.

[1511] Step 2:

[1512] The user selects the desired inspection item from the displayed list of inspection items, such as "tire inspection," "body inspection," or "engine sound inspection." The input is the selection of the inspection item, and the output is the next instruction screen based on the selected item.

[1513] Step 3:

[1514] The terminal displays a prompt corresponding to the selected inspection item. For example, if "Tire Inspection" is selected, the prompt "Please take a photo of the left front tire" is displayed. The input is the selected inspection item, and the output is the display of instructions to the user.

[1515] Step 4:

[1516] The user uses the camera on the mobile device to take a picture of the specified area according to the prompt. The input is the camera operation, and the output is the captured image data.

[1517] Step 5:

[1518] The device temporarily stores the captured image data and prepares it for transmission to the server. The input is the image data, and the output is the temporarily stored data and subsequent preparation for data transmission.

[1519] Step 6:

[1520] The terminal sends the temporarily stored image data to the server. The input is the stored image data, and the output is the data sent to the server.

[1521] Step 7:

[1522] The server inputs the received image data into a generative AI model to analyze tire pressure, loose screws, and distortion. The input is image data, and the output is the analysis results.

[1523] Step 8:

[1524] The server generates the analysis results and creates a notification message such as "There is a loose screw on the left front tire." The input is the analysis results, and the output is the notification message.

[1525] Step 9:

[1526] The server sends the generated notification message to the user's mobile terminal. The input is the notification message, and the output is the message displayed on the user's terminal.

[1527] Engine sound inspection procedure

[1528] Step 1:

[1529] The user launches the app and selects "Check Engine Sound." The input is the user's operation, and the output is the display of a screen instructing the user to record the engine sound.

[1530] Step 2:

[1531] The terminal displays the prompt "Start the engine and record the sound." The input is the selected inspection item, and the output is the display of instructions to the user.

[1532] Step 3:

[1533] The user starts the engine and records the sound. The input is the microphone operation, and the output is the recorded audio data.

[1534] Step 4:

[1535] The terminal temporarily stores the recorded voice data and prepares it to be sent to the server. The input is the voice data, and the output is the temporarily stored data and the preparation for subsequent data transmission.

[1536] Step 5:

[1537] The terminal transmits the temporarily stored voice data to the server. The input is the stored voice data, and the output is the data transmitted to the server.

[1538] Step 6:

[1539] The server inputs the received audio data into the generative AI model and analyzes engine sound abnormalities. The input is the audio data, and the output is the analysis result.

[1540] Step 7:

[1541] The server generates the analysis result and creates a notification message saying, "There is something wrong with the engine start sound." The input is the analysis result, and the output is the notification message.

[1542] Step 8:

[1543] The server sends the generated notification message to the user's mobile terminal. The input is the notification message, and the output is the message displayed on the user's terminal.

[1544] The detailed processing in each step above allows the user to properly perform various inspections of the vehicle, allowing the user to grasp the condition of the vehicle in real time and manage it safely and efficiently.

[1545] (Application example 1)

[1546] 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."

[1547] Periodic or reactive diagnosis of vehicle conditions is important for operational safety and performance maintenance. However, conventional methods require specialized knowledge for many inspection tasks, making it difficult for users to easily perform self-diagnosis. Furthermore, autonomous vehicles also require methods for quickly and accurately detecting abnormalities in each part of the vehicle, but this requires advanced functionality and analytical capabilities.

[1548] 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.

[1549] In this invention, the server includes means for allowing a user to select vehicle inspection items, means for capturing images of the vehicle using a camera of the smart device, means for capturing audio data of the vehicle using a microphone of the smart device, means for transmitting the captured image and audio data to the server, means for analyzing the transmitted image and audio data using a generative AI model in the server, means for notifying the user of the analysis results, and means for periodically or reactively diagnosing the vehicle condition so that the autonomous vehicle can perform self-diagnosis. This allows users to easily diagnose the condition of the vehicle without requiring specialized knowledge, and the autonomous vehicle's self-diagnosis function allows it to quickly and accurately detect vehicle abnormalities, thereby maintaining safety and performance.

[1550] A "user" is an individual who operates a smart device to perform an automobile inspection.

[1551] A "smart device" is an electronic device that has a built-in camera and microphone and has the ability to acquire data and send it to a server.

[1552] A "camera" is an optical device for acquiring image data.

[1553] A "microphone" is an acoustic device for acquiring audio data.

[1554] A "server" is a remote computer system that analyzes the acquired data and notifies the user of the results.

[1555] A "generative AI model" is a machine learning model used to analyze captured image and audio data.

[1556] "Analysis" is the process of extracting information based on the acquired data and identifying abnormalities or problems.

[1557] "Notification" is the process of informing the user of the analysis results.

[1558] An "autonomous vehicle" is a vehicle that does not require human operation and has self-diagnostic capabilities.

[1559] "Self-diagnosis" is a function that allows the vehicle itself to check its condition and detect abnormalities.

[1560] "Periodic" means repeatedly at a series of intervals.

[1561] "Reactive" means responding immediately to events that occur.

[1562] "Condition" refers to the current state of each part and function of the vehicle.

[1563] An "image" is visual data captured by a camera.

[1564] "Audio data" is acoustic data acquired by a microphone.

[1565] "Data transmission" is the process of sending the acquired data over the network to the server.

[1566] "Safety" refers to the reliability of vehicles to ensure safe operation.

[1567] "Performance retention" means that the vehicle maintains good performance over a long period of time.

[1568] The present invention provides a system for easily diagnosing the condition of an automobile, and in particular for enhancing the self-diagnosis function of an autonomous vehicle. Specific embodiments for carrying out the present invention will be described in detail below.

[1569] System configuration

[1570] The main components of the system are:

[1571] User: An individual who operates a smart device to inspect a vehicle. In the case of autonomous vehicles, the vehicle itself performs self-diagnosis.

[1572] Smart device: An electronic device used for vehicle inspections that has a built-in camera and microphone. The camera captures image data, and the microphone captures audio data.

[1573] Server: A remote computer system that uses generative AI models to analyze the acquired data and notify the user of the results.

[1574] Generative AI model: Performs data analysis as a machine learning model to analyze the condition of each part of the car.

[1575] Data acquisition and analysis

[1576] Tire Diagnosis

[1577] The user captures an image of the tire using the camera on their smart device. The image is then sent to a server, where it is analyzed using a generative AI model to detect tire pressure, loose screws, and distortion. The results of the analysis are then reported to the user.

[1578] Body diagnostics

[1579] The user uses the camera on their smart device to capture images of the vehicle, which are then sent to a server that analyzes them using a generative AI model to detect scratches on the vehicle body, cracks in the glass, and dangerous distortions. The results of the analysis are then reported to the user.

[1580] Engine sound diagnosis

[1581] The user records the engine sound using the microphone on their smart device. The captured audio data is sent to the server, which then analyzes the engine sound using a generative AI model. If an abnormality is detected, the user is notified of the details.

[1582] Self-diagnosis for autonomous vehicles

[1583] In autonomous vehicles, the system performs self-diagnosis periodically or reactively. It uses cameras, microphones, and other sensors built into the vehicle to collect data, which is then sent to a server. The server then analyzes the data using generative AI models, and if an abnormality is detected, a notification is sent to the vehicle's infotainment system or the driver.

[1584] Hardware and software used

[1585] Hardware:

[1586] Smart device (with built-in camera and microphone)

[1587] Built-in cameras, microphones, and various sensors in autonomous vehicles

[1588] software:

[1589] OpenCV: Camera control and image acquisition

[1590] sounddevice library: audio recording

[1591] The requests library: data transmission and server communication

[1592] Generative AI Models: Data Analysis

[1593] Specific examples

[1594] Example prompt sentence:

[1595] "Take a photo of the left front tire and automatically transfer it."

[1596] "Start the engine, record the audio, and automatically transmit it."

[1597] Example of operation steps:

[1598] The user opens the smart device app and selects the tire diagnosis item.

[1599] The user points the smart device at the front wheel of the vehicle, activates the camera, and captures an image.

[1600] The captured images are sent to a server and analyzed by a generative AI model.

[1601] The analysis results are notified to the user, displaying the message "Loose screws have been detected in the left front tire."

[1602] In this way, the present invention aims to enable users to easily diagnose the condition of their vehicle without requiring specialized knowledge. Furthermore, by strengthening the self-diagnosis function of autonomous vehicles, it is possible to quickly and accurately detect vehicle abnormalities, thereby realizing safety and maintaining performance.

[1603] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1604] Step 1:

[1605] The user launches the app on their smart device and selects an inspection item. The user's operation is input, the inspection item selection is output, and the system proceeds to the next data acquisition step.

[1606] Step 2:

[1607] The terminal uses the smart device's camera to capture images corresponding to the selected inspection item. Specifically, the user points the smart device at the relevant part of the vehicle (e.g., tire or body) and takes a photo with the camera. The input is video data from the camera, and the captured image is output.

[1608] Step 3:

[1609] When the terminal uses the microphone of the smart device to acquire voice data corresponding to the selected inspection item, the user records the engine sound according to the instructions. The input is the voice data from the microphone, and the acquired voice is output.

[1610] Step 4:

[1611] The image and audio data acquired by the device is sent to the server. Specifically, a network request is used to upload the acquired data files to the server. The input is the image and audio data files, and the output is the completion of data transmission to the server.

[1612] Step 5:

[1613] The image and audio data received by the server is input into the generative AI model for analysis. Specifically, the server inputs the data into the generative AI model, which then performs image and audio analysis. The input is image data and audio data, and the analysis results are output.

[1614] Step 6:

[1615] The server notifies the user of the analysis results. Specifically, the analysis results (for example, abnormal tire pressure, loose screws, abnormal engine noise, etc.) are generated and sent to the user's smart device as a notification message. The input is the analysis results, and the output is the completion of notification to the user.

[1616] Step 7:

[1617] In the case of self-diagnosis in an autonomous vehicle, the vehicle automatically performs steps 1 to 6 periodically or as needed, without requiring user intervention. The input is the vehicle's automatic diagnostic system, and the output is notification of the self-diagnosis results.

[1618] 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.

[1619] A specific embodiment for carrying out the present invention will be described in detail. The system described below allows a user to use a smartphone to perform a pre-ride inspection of a vehicle, and uses an emotion engine to recognize the user's emotions and provide appropriate feedback. This system transmits data acquired using the smartphone's camera and microphone to a server, and notifies the user of the analysis results based on the user's emotions.

[1620] System configuration

[1621] The main components of the system are:

[1622] User: The individual who operates the smartphone and performs the vehicle inspection.

[1623] Device: A smartphone used for vehicle inspections, equipped with a built-in camera and microphone.

[1624] Server: A remote computer system that analyzes the acquired data using a generative AI model and emotion engine.

[1625] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[1626] Emotion engine: A model that recognizes emotions from user voice and text data and generates appropriate feedback based on those emotions.

[1627] Explanation of program processing

[1628] 1. User operations and data acquisition

[1629] The user starts the dedicated app on their smartphone and begins the inspection. From the app's main screen, they select the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection, etc.) and follow the data acquisition procedure.

[1630] 2. Check your tires

[1631] The device uses the camera to take photos of each tire to check its condition. When taking photos, the app guides the user on the shooting position and angle. The photos are temporarily saved on the smartphone and then automatically sent to the server.

[1632] The server inputs the received photos into a generative AI model to analyze tire pressure, loose screws, and distortions. The analysis results are then sent to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[1633] The server generates a feedback message based on the user's sentiment, including specific advice such as "A slight looseness has been detected, but it can be easily corrected with a specific tool."

[1634] 3. Inspect the vehicle body

[1635] To check the overall condition of the vehicle, the user takes a photo of the vehicle using the smartphone camera. The app guides the user to take an appropriate photo by specifying the shooting position and angle. The captured photo of the vehicle is temporarily saved on the smartphone and then sent to the server.

[1636] The server inputs the received photos of the car body into a generative AI model, which analyzes scratches on the car body, cracks in the glass, and dangerous distortions.The analysis results are then sent to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[1637] The server generates a feedback message based on the user's sentiment, including specific advice such as "I found a small scratch on the car body, but it's not a serious problem."

[1638] 4. Check the sound when starting the engine

[1639] The user follows the app's instructions to record the engine sound using the smartphone's microphone. The recorded audio data is temporarily stored on the smartphone and then sent to the server.

[1640] The server inputs the received voice data into a generative AI model to analyze any abnormalities in the engine start-up sound.Then, it sends the analysis results to an emotion engine, which recognizes emotions from the user's voice data and generates appropriate feedback based on the analysis results.

[1641] The server generates a feedback message based on the user's emotions, including specific advice such as "An abnormality has been detected in the engine start-up sound. We recommend that you repair it immediately."

[1642] Specific examples

[1643] Examples of tire inspections:

[1644] 1. The user launches the app and selects "Tire Inspection."

[1645] 2. The app will prompt you to take a photo of the left front tire.

[1646] 3. The user uses their smartphone to take a photo of the left front tire.

[1647] 4. The photo is sent to a server, where a generative AI model analyzes tire pressure, loose screws, and distortion.

[1648] 5. The analysis results are sent to the emotion engine.

[1649] 6. The emotion engine recognizes emotions from the user's voice data and generates a feedback message.

[1650] 7. The server notifies the user of the analysis results and a feedback message, such as "There is a loose screw on the left front tire, but this can be easily fixed."

[1651] Examples of engine sound checks:

[1652] 1. The user launches the app and selects "Check Engine Sound."

[1653] 2. The app will prompt you to "Start the engine and record the sound."

[1654] 3. The user starts the engine and records the sound.

[1655] 4. The recording data is sent to a server, where a generative AI model analyzes the sound of the engine starting.

[1656] 5. The analysis results are sent to the emotion engine.

[1657] 6. The emotion engine recognizes emotions from the user's voice data and generates a feedback message.

[1658] 7. The server notifies the user of the analysis results and a feedback message, such as "There is something wrong with the engine start-up sound. Repairs are recommended."

[1659] As described above, the user can perform highly accurate vehicle inspections with simple operations and can also receive appropriate feedback according to their emotions.

[1660] The processing flow will be explained below.

[1661] Step 1:

[1662] The user launches the dedicated app on their smartphone. The app's main screen appears, and they can select an inspection item (tire inspection, vehicle body inspection, engine sound inspection).

[1663] Step 2:

[1664] The app will then display specific instructions based on the inspection item the user selects. For example, if the user selects a tire inspection, the app will prompt the user to "take a photo of the left front tire."

[1665] Step 3:

[1666] The user uses the smartphone camera to take a photo of the specified area (e.g., the left front tire).

[1667] Step 4:

[1668] The device temporarily stores the captured photos in its internal storage.

[1669] Step 5:

[1670] The device transmits the stored photo data to a server via the Internet.

[1671] Step 6:

[1672] The server receives the transmitted photo data and inputs it into the generative AI model.

[1673] Step 7:

[1674] The server uses a generative AI model to analyze the photo data and detect, for example, tire pressure, loose screws, and distortions.

[1675] Step 8:

[1676] The server sends the analysis results to the emotion engine.

[1677] Step 9:

[1678] In order for the emotion engine to recognize emotions from the user's voice data, it asks the user a question (e.g., "Are you okay?") and acquires the voice data.

[1679] Step 10:

[1680] The emotion engine analyzes the voice data and recognizes the user's emotions, such as anxiety, relief, and surprise.

[1681] Step 11:

[1682] The server generates an appropriate feedback message based on the analysis results and the user's emotions. For example, if the user is feeling anxious, it creates a message saying, "A loose screw has been detected, but don't worry, it can be easily fixed."

[1683] Step 12:

[1684] The server sends the generated feedback message to the terminal.

[1685] Step 13:

[1686] The device notifies the user of the received feedback message, which includes the analysis results and advice based on the user's emotions.

[1687] Step 14:

[1688] The user checks the notification and takes appropriate measures as instructed, if necessary (e.g., check the tire screws and correct any looseness).

[1689] Specific examples

[1690] Examples of tire inspections:

[1691] Step 1:

[1692] The user launches the app and selects "Tire Inspection."

[1693] Step 2:

[1694] The app will then prompt you to "Take a photo of the left front tire."

[1695] Step 3:

[1696] The user uses a smartphone to take a photo of the left front tire.

[1697] Step 4:

[1698] The photos you take will be saved on your device.

[1699] Step 5:

[1700] The saved photo data is sent to the server.

[1701] Step 6:

[1702] The server receives the photo data and analyzes it using a generative AI model.

[1703] Step 7:

[1704] The server detects tire pressure, loose screws, and distortion.

[1705] Step 8:

[1706] The analysis results are sent to the emotion engine.

[1707] Step 9:

[1708] The emotion engine asks the user for their reaction and tells them, "Loose screws detected."

[1709] Step 10:

[1710] The user responds and asks, "What do I do?"

[1711] Step 11:

[1712] The emotion engine recognizes anxiety from the user's voice data and combines it with the analysis results to generate appropriate feedback.

[1713] Step 12:

[1714] The server creates a message saying, "Loose screws have been detected, but don't worry, they can be easily fixed with a specific tool."

[1715] Step 13:

[1716] The generated message is sent to the terminal.

[1717] Step 14:

[1718] The device will then send a message to the user, containing the tire analysis results and instructions on how to fix the threads.

[1719] Through these steps, users can not only perform highly accurate inspections of their vehicles, but also receive appropriate support tailored to their emotions.

[1720] Example 2

[1721] 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."

[1722] Conventional vehicle inspection methods require specialized knowledge and tools, making it difficult for ordinary users to perform inspections themselves. In addition, since feedback that takes into account the user's emotions is not provided, there is a risk that the user may not understand or respond well to the inspection results.

[1723] 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.

[1724] In this invention, the server includes means for analyzing the transmitted image and audio data using a generative AI model, means for sending the analysis results to an emotion recognition engine and generating feedback based on the user's emotions, and means for notifying the user of the analysis results and feedback. This allows even ordinary users to easily inspect their vehicles and receive appropriate feedback according to the user's emotions.

[1725] "User" refers to an individual who uses a mobile information terminal to perform an automobile inspection.

[1726] A "mobile information terminal" refers to a device such as a smartphone or tablet that has a built-in camera and microphone and can run dedicated apps.

[1727] "Server" refers to a remote computer system that uses a generative AI model and an emotion recognition engine to analyze the received data and notify the user of the analysis results.

[1728] A "generative AI model" refers to a model that uses machine learning technology to analyze the condition of each part of a car.

[1729] An "emotion recognition engine" refers to a model that recognizes emotions from a user's voice or text data and generates appropriate feedback based on that.

[1730] "Analysis results" refers to information analyzed by the generative AI model, such as tire pressure, loose screws, distortions, scratches on the body, cracks in the glass, and abnormal engine sounds.

[1731] "Feedback" refers to specific advice or notification messages generated based on the analysis results and the user's emotions.

[1732] "Inspection items" refer to vehicle inspection items that can be selected by the user, such as tire inspection, body inspection, and engine sound inspection.

[1733] "Data acquisition means" refers to a means for acquiring images and audio data of a vehicle using a camera or microphone of a mobile information terminal.

[1734] The "data transmission means" refers to a means for transmitting image and audio data acquired by the mobile information terminal to the server.

[1735] This invention is a system that allows a user to inspect a vehicle using a mobile information terminal, and uses a generative AI model and an emotion recognition engine to recognize the user's emotions and provide appropriate feedback. This system acquires data using the mobile information terminal's camera and microphone, sends it to a server, and generates and notifies feedback based on the analysis results.

[1736] System Components

[1737] The main components of the system are:

[1738] User: An individual who operates a mobile information terminal and performs a vehicle inspection.

[1739] Terminal: A personal digital assistant used for vehicle inspections, equipped with a camera and microphone.

[1740] Server: A remote computer system that analyzes acquired data using a generative AI model and emotion recognition engine.

[1741] Generative AI model: A machine learning model for analyzing the condition of each part of a car.

[1742] Emotion recognition engine: A model that recognizes emotions from the user's voice and text data and generates appropriate feedback based on that.

[1743] Data Acquisition and Transmission

[1744] The user starts the dedicated app on their mobile device and begins the inspection. They select the desired inspection item from the app's main screen and follow the data acquisition procedure. Inspection items include tire inspection, vehicle body inspection, and engine sound inspection.

[1745] In the case of tire inspections, the device uses the camera to take a photo of each tire. The app guides the user on the shooting position and angle, and the photos are temporarily stored on the mobile information device before being sent to the server. As a concrete example, the user may be instructed to "take a photo of the left front tire" and follow that instruction.

[1746] During a vehicle inspection, the user uses the camera on their mobile device to take a photo of the vehicle. The app instructs the user on the best shooting position and angle. The photos are temporarily stored on the device and later sent to the server. A specific example is a procedure where the user is guided to "take a photo of the entire vehicle."

[1747] To check the engine sound, the user records the engine sound using the microphone on the mobile information terminal. The recorded audio data is temporarily stored in the terminal and then sent to the server. As a concrete example, the user is instructed to "start the engine and record the sound."

[1748] Data analysis and feedback

[1749] The server receives the transmitted image and audio data and analyzes it using a generative AI model. For example, tire images can be used to detect air pressure, loose screws, and distortions. Images of the car body can be analyzed for scratches, cracked glass, and dangerous distortions. Engine sound data can be used to detect abnormal sounds.

[1750] The analysis results are sent to an emotion recognition engine on the server, which recognizes the user's emotional state from their voice and text data. Specific and appropriate feedback is generated based on the analysis results and emotional data. For example, it may include advice such as, "There's a loose screw on the left front tire, but that can be easily fixed."

[1751] Notifications and Feedback

[1752] The server notifies the user of the generated feedback message. For example, when the user receives the analysis result, the server notifies the user that "a small scratch was found on the car body, but it is not a serious problem."

[1753] In this way, the system of the present invention allows even ordinary users to easily inspect their vehicles and provides appropriate feedback according to the user's emotions. By using this system, users can easily obtain highly accurate inspection results and can quickly take appropriate action.

[1754] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1755] Step 1:

[1756] The user launches a dedicated app on their mobile information terminal and begins the inspection.

[1757] Input: Launching an app on a mobile device

[1758] Output: The main screen of the app is displayed, and the Start Inspection button is available.

[1759] Specific operation: The user taps the icon to launch the app. After launching, a "Start inspection" button appears on the main screen.

[1760] Step 2:

[1761] The user selects the desired inspection item (tire inspection, vehicle body inspection, engine sound inspection).

[1762] Input: User taps to select an inspection item

[1763] Output: A screen corresponding to the selected inspection item will be displayed.

[1764] Specific operation: The user taps the desired item from "Tire Inspection," "Body Inspection," or "Engine Sound Inspection" on the main screen. Depending on the selection, a guide screen for the next step will be displayed.

[1765] Step 3:

[1766] The terminal displays instructions to the user to retrieve the data.

[1767] Input: Selected inspection items

[1768] Output: A guide message for data acquisition is displayed.

[1769] Specific actions: Instructions such as "Take a photo of the left front tire" and "Start the engine and record the sound" will appear on the device screen.

[1770] Step 4:

[1771] The user captures the data using the camera or microphone of the mobile information terminal.

[1772] Input: User performs data capture operations (photographs and audio recordings)

[1773] Output: Captured image or audio data

[1774] Specific operation: The user uses the camera to take photos of the tires and vehicle body, and uses the microphone to record the engine sound. The acquired data is temporarily stored on the device.

[1775] Step 5:

[1776] The terminal transmits the acquired data to the server.

[1777] Input: Captured image or audio data

[1778] Output: The data sent.

[1779] Specific operation: The device automatically uploads images and audio data stored internally to the server.

[1780] Step 6:

[1781] The server inputs the received data into the generative AI model and analyzes it.

[1782] Input: Transmitted image or audio data

[1783] Output: Analysis results (tire pressure, loose screws, scratches on the car body, abnormal engine sounds, etc.)

[1784] Specific operation: The server inputs the received data into the generative AI model and performs analytical processing to identify abnormalities and conditions.

[1785] Step 7:

[1786] The server sends the analysis results to an emotion recognition engine to recognize the user's emotions.

[1787] Input: Analysis results and user voice data

[1788] Output: User's emotional state

[1789] Specific operation: The server inputs the analysis results into an emotion recognition engine, analyzes the user's voice and text data, and recognizes major emotions such as joy, anger, sadness, and happiness.

[1790] Step 8:

[1791] The server generates a feedback message based on the analysis results and the user's emotions.

[1792] Input: Analysis results and emotion data

[1793] Output: Feedback message (e.g. "There is a loose screw in the left front tire, but this is an easy fix.")

[1794] Specific behavior: The server combines the analysis results with the user's emotions to generate specific and appropriate feedback.

[1795] Step 9:

[1796] The server notifies the user of the feedback message.

[1797] Input: Feedback message

[1798] Output: Notification message sent to the user

[1799] Specific operation: The server sends the generated feedback message to the mobile information terminal and displays it on the terminal screen.

[1800] (Application example 2)

[1801] 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."

[1802] In conventional vehicle inspection systems, it is difficult for users to accurately grasp the situation when performing the inspection themselves, resulting in the risk of making inappropriate decisions.Furthermore, they often provide uniform feedback without considering the user's emotional state, which has the problem of not being able to reduce user stress.

[1803] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring images of the vehicle using a camera of the communication terminal, means for acquiring voice data of the vehicle using a microphone of the communication terminal, means for analyzing the transmitted image and voice data using a generative AI model, means for generating a feedback message based on the analysis result by the generative AI model and the user's emotion using an emotion recognition engine, and means for notifying the user of the feedback message. This allows the user to obtain accurate vehicle inspection results and, further, to receive appropriate feedback according to the user's emotional state, thereby reducing stress.

[1804] A "user" is an individual or group that operates a communication terminal to inspect a vehicle.

[1805] A "communication terminal" is a device that has a built-in camera and microphone and is used by a user to inspect a vehicle. Examples include smartphones.

[1806] "Camera" means an optical instrument used to capture images of a vehicle.

[1807] A "microphone" is an acoustic device used to capture audio data from a vehicle.

[1808] A "server" is a remote computer system that analyzes data sent by a communication terminal and generates appropriate feedback messages.

[1809] A "generative AI model" is a machine learning model that analyzes acquired image and audio data to determine the vehicle's condition.

[1810] An "emotion recognition engine" is a software model for identifying emotions from a user's voice or text data and adjusting feedback messages accordingly.

[1811] A "feedback message" is a message that the server generates based on the analysis results and that includes advice or warning information to notify the user.

[1812] A "vehicle" is a machine used as a means of transportation, and specific examples include automobiles and self-driving vehicles.

[1813] To implement this invention, a system is required in which users, communication terminals, servers, generative AI models, and emotion recognition engines work together seamlessly. The detailed configuration of this system and the role of each element are described below.

[1814] Key components of the system

[1815] User: An individual or organization that inspects a vehicle and operates a communication terminal.

[1816] Communication terminal: A device with a built-in camera and microphone that allows users to obtain vehicle inspection data. Specific examples include smartphones.

[1817] Server: A high-performance computer system that receives data sent from communication devices and analyzes and provides feedback using a generative AI model and emotion recognition engine.

[1818] Generative AI model: A model that uses machine learning techniques to analyze transmitted image and audio data.

[1819] Emotion recognition engine: A software model that recognizes emotions from user voice and text data and adjusts the content of feedback messages.

[1820] Program processing overview

[1821] The user launches a dedicated app on the communication device and selects an inspection item. The communication device uses a camera to capture images of the vehicle and a microphone to capture audio data from the vehicle. This data is temporarily stored on the device and then sent to the server.

[1822] The server inputs the received image and voice data into a generative AI model to analyze the condition of each part of the vehicle. The analysis results are then transferred to an emotion recognition engine, which recognizes emotions from the user's voice data and generates appropriate feedback messages based on that.

[1823] Hardware and software used

[1824] Hardware: Smartphone (camera, built-in microphone), server (high-performance computer)

[1825] Software: Python, OpenCV (image processing library), requests (HTTP request library), emotion_recognition (emotion recognition library), ai_model (generative AI model)

[1826] Data processing and calculation

[1827] Image and audio data captured using the communication device's camera and microphone are sent to the server via HTTP requests. On the server, a generative AI model analyzes the image data to determine the condition of each part of the vehicle. An emotion recognition engine also evaluates the user's emotions from the audio data and uses the results to generate feedback messages that are optimal for the analysis results.

[1828] Specific examples

[1829] When selecting "tire inspection" as an inspection item, the user uses the camera on their communication device to take sequential images of the tires. The communication device then sends this image data to the server, which then uses a generative AI model to analyze the tire's air pressure, loose screws, and distortion. Based on the analysis results and the user's emotion recognition results, a feedback message containing specific advice is generated.

[1830] Example prompts to input to the generative AI model

[1831] "Please analyze images taken from the front of the vehicle to check the status of the front sensors. Also, please detect any abnormalities based on the recorded engine sound data."

[1832] In this way, the present invention enables users to easily perform highly accurate vehicle inspections, and further reduces stress for users by providing appropriate feedback based on emotion recognition.

[1833] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1834] Step 1: The user launches the dedicated app on the communication device and selects an inspection item. This allows the user to begin operations to inspect specific vehicle parts, such as tires, the body, or engine noise. The input is the inspection item selected by the user, and the output is the next guideline for the inspection item.

[1835] Step 2: The user acquires images of the vehicle using the camera on the communication device. For example, if the user selects tire inspection, the user takes a photo of each tire with the smartphone camera. The app displays guidelines to guide the user to take photos from the appropriate position and angle. The input is the image data captured by the user, and the output is the image data temporarily stored in the communication device.

[1836] Step 3: The user acquires vehicle audio data using the microphone on the communication device. For example, if the user selects engine sound inspection, the user records the engine start-up sound using the microphone on their smartphone. The input is the recorded audio data, and the output is the audio data temporarily stored in the communication device.

[1837] Step 4: The captured image and audio data are sent to the server via an HTTP request. The communication device combines the image and audio data into a single request and sends it to the server's data receiving endpoint. The input is the image and audio data stored in the communication device, and the output is the data sent to the server.

[1838] Step 5: The server uses the generative AI model to analyze the received image data and determine the condition of each part of the vehicle. For example, if it is an image of a tire, it will analyze the air pressure, loose screws, and distortion. The input is the image data sent to the server, and the output is the tire condition data as the analysis result.

[1839] Step 6: The server similarly analyzes the received audio data using the generative AI model to check for abnormalities in the vehicle's engine sound. The input is the audio data sent to the server, and the output is the engine sound status data as the analysis result.

[1840] Step 7: The analysis results are passed to the emotion recognition engine in the server, where the process of recognizing emotions from the user's voice data is carried out. The input is the user's voice data, and the output is the recognized user's emotion data.

[1841] Step 8: The server generates an appropriate feedback message based on the analysis results and the user's emotional data. For example, if the user is nervous, the feedback message can use gentler language or include more detailed explanations. The input is the analysis results and emotional data, and the output is the feedback message.

[1842] Step 9: The feedback message is sent to the communication terminal as an HTTP response and notified to the user. The communication terminal receives this and displays the message to the user in the app. The input is the feedback message from the server, and the output is the feedback message notified to the user.

[1843] 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.

[1844] 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.

[1845] 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.

[1846] 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.

[1847] 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.

[1848] 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.

[1849] 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).

[1850] 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.

[1851] 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."

[1852] 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.

[1853] 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).

[1854] 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.

[1855] 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.

[1856] 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.

[1857] 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.

[1858] 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.

[1859] 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.

[1860] 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.

[1861] 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.

[1862] 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.

[1863] 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.

[1864] The following is further disclosed regarding the above embodiment.

[1865] (Claim 1)

[1866] means for allowing a user to select inspection items for a vehicle;

[1867] A means for acquiring an image of a vehicle using a smartphone camera;

[1868] A means for acquiring voice data from a vehicle using a microphone of a smartphone;

[1869] means for transmitting the captured image and audio data to a server;

[1870] a means for analyzing the transmitted image and audio data using a generative AI model in the server;

[1871] a means for notifying the user of the analysis results;

[1872] A system including:

[1873] (Claim 2)

[1874] The system of claim 1 analyzes images of tires to detect air pressure, loose screws, and distortion.

[1875] (Claim 3)

[1876] 10. The system of claim 1, which analyzes images of the vehicle body to detect scratches, cracked glass, and dangerous distortions.

[1877] "Example 1"

[1878] (Claim 1)

[1879] means for allowing a user to select inspection items for a vehicle;

[1880] means for acquiring an image of the vehicle using a camera of the mobile terminal;

[1881] means for acquiring voice data of the vehicle using a microphone of the mobile terminal;

[1882] means for transmitting the captured image and audio data to a remote computer system;

[1883] means at the remote computer system for analyzing the transmitted image and audio data using a generative AI model;

[1884] A means for guiding the user to the appropriate shooting position and angle depending on the inspection item;

[1885] a means for notifying a user of the analysis result after the analysis is completed;

[1886] A system including:

[1887] (Claim 2)

[1888] The system of claim 1 analyzes images of tires to detect air pressure, loose screws, and distortion.

[1889] (Claim 3)

[1890] 10. The system of claim 1, which analyzes images of the vehicle body to detect scratches, cracked glass, and dangerous distortions.

[1891] "Application Example 1"

[1892] (Claim 1)

[1893] means for allowing a user to select inspection items for a vehicle;

[1894] means for acquiring an image of the vehicle using a camera of the smart device;

[1895] A means for acquiring voice data from a vehicle using a microphone of a smart device;

[1896] means for transmitting the captured image and audio data to a server;

[1897] a means for analyzing the transmitted image and audio data using a generative AI model in the server;

[1898] a means for notifying the user of the analysis results;

[1899] A means for periodically or reactively diagnosing the state of the vehicle so that the autonomous vehicle can perform self-diagnosis;

[1900] A system including:

[1901] (Claim 2)

[1902] The system of claim 1 analyzes images of tires to detect air pressure, loose screws, and distortion.

[1903] (Claim 3)

[1904] 10. The system of claim 1, which analyzes images of the vehicle body to detect scratches, cracked glass, and dangerous distortions.

[1905] "Example 2: Combining Emotion Engines"

[1906] (Claim 1)

[1907] means for allowing a user to select inspection items for a vehicle;

[1908] means for acquiring an image of the vehicle using a camera of the mobile information terminal;

[1909] means for acquiring voice data of the vehicle using a microphone of the mobile information terminal;

[1910] means for transmitting the captured image and audio data to a server;

[1911] a means for analyzing the transmitted image and audio data using a generative AI model in the server;

[1912] A means for sending the analysis results to an emotion recognition engine and generating feedback based on the user's emotions;

[1913] a means for notifying the user of the analysis results and feedback;

[1914] A system including:

[1915] (Claim 2)

[1916] The system of claim 1 analyzes images of tires to detect air pressure, loose screws, and distortion.

[1917] (Claim 3)

[1918] 10. The system of claim 1, which analyzes images of the vehicle body to detect scratches, cracked glass, and dangerous distortions.

[1919] "Application example 2 when combining emotion engines"

[1920] (Claim 1)

[1921] means for allowing a user to select inspection items for a vehicle;

[1922] means for acquiring an image of the vehicle using a camera of the communication terminal;

[1923] means for acquiring voice data of the vehicle using a microphone of the communication terminal;

[1924] means for transmitting the captured image and audio data to a server;

[1925] a means for analyzing the transmitted image and audio data using a generative AI model in the server;

[1926] A means for generating a feedback message based on the user's emotions using an emotion recognition engine based on the analysis results of the generative AI model;

[1927] a means for notifying a user of a feedback message;

[1928] A system including:

[1929] (Claim 2)

[1930] The system of claim 1 analyzes images of tires to detect air pressure, loose screws, and distortion.

[1931] (Claim 3)

[1932] 10. The system of claim 1, which analyzes images of the vehicle body to detect scratches, cracked glass, and dangerous distortions. [Explanation of symbols]

[1933] 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 allowing a user to select inspection items for a vehicle; A means for acquiring an image of a vehicle using a smartphone camera; A means for acquiring voice data from a vehicle using a microphone of a smartphone; means for transmitting the captured image and audio data to a server; a means for analyzing the transmitted image and audio data using a generative AI model in the server; a means for notifying the user of the analysis results; A system including:

2. 10. The system of claim 1, wherein the system analyzes images of the tire to detect air pressure, loose screws, and distortion.

3. 10. The system of claim 1, wherein the system analyzes images of the vehicle body to detect scratches, cracked glass, and dangerous distortions.

Images