System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting operational data; means for obtaining external information; means for predicting wear of a part based on the operational data and the external information; means for suggesting a maintenance time to a user based on the predicted wear of the part; means for suggesting a service station based on a current fuel level and fuel consumption; and means for providing feedback to a maintenance company or a dealer according to a need for maintenance.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] Modern cars have the ability to accumulate a wide variety of data, but it is currently difficult to effectively utilize this data to predict the deterioration of vehicle consumables and parts. In particular, it is difficult for car owners to determine when maintenance is required, which requires specialized knowledge, and to refuel at the appropriate time. For this reason, there is a demand for a system that can predict the deterioration of consumables in advance and suggest the optimal timing for maintenance. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting driving data, a means for acquiring external information, a means for predicting part wear based on the driving data and external information, a means for suggesting maintenance times to the user based on the part wear prediction results, a means for suggesting gas stations based on the current remaining fuel level and consumption, and a means for providing feedback to maintenance companies and dealers based on the degree of maintenance necessity. This allows the user to know the optimal maintenance times and refueling timings based on driving information, making regular maintenance easier. Furthermore, by using artificial intelligence to predict part wear, more accurate maintenance suggestions are possible. Furthermore, by combining external information such as weather information and road surface conditions in the predictions, a more reliable system is provided.

[0006] "Driving data" refers to data that includes information such as the number of times the vehicle's engine is started and stopped, the duration of time the lights are on, the duration of time the wipers are operated, the number of times / time the accelerator and brake are used, the distance traveled, and the route traveled.

[0007] "External information" refers to data provided from outside, such as weather information obtained via the Internet, road surface conditions, and traffic information.

[0008] "Parts wear prediction" involves estimating the degree of deterioration and wear of each vehicle part based on driving data and external information, and predicting when replacement or maintenance will be necessary.

[0009] "Artificial intelligence" refers to an intelligent system that can perform tasks such as predicting part wear using machine learning and deep learning techniques based on large amounts of data.

[0010] "Maintenance timing suggestions" refers to notifying the vehicle owner or user of the appropriate time to replace or inspect each part based on the results of part wear predictions.

[0011] "Fuel level" refers to the amount of gasoline or diesel fuel remaining in a vehicle's fuel tank.

[0012] "Consumption" refers to the amount of fuel consumed by a vehicle over a given period of time or distance.

[0013] "Fuel station suggestion" refers to informing the vehicle owner or user of an appropriate fuel station when it is determined that refueling is necessary along the way, taking into account the current fuel level and the distance to the destination.

[0014] A "maintenance company" is a business that specializes in vehicle repair and maintenance.

[0015] A "dealer" is a company or store that specializes in selling automobiles and automobile parts.

[0016] "Feedback" refers to information provided to vehicle owners, maintenance companies, and dealers based on predicted maintenance needs, encouraging them to take appropriate action. [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] This invention is a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that performs wear prediction, and means for suggesting maintenance and gas stations to users. The program processing of this system is explained below in natural language.

[0039] Data collection

[0040] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are in operation, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.

[0041] Example: The device records that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance traveled was 1500 km.

[0042] Obtaining external information

[0043] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[0044] Example: A server receives information that the current local weather is rainy and road conditions are slippery.

[0045] Wear prediction

[0046] The server uses an AI model to predict wear and tear on each part based on collected driving data and external information. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when to replace each part (e.g., engine oil, brake pads, tires).

[0047] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that the oil is due for replacement. It also determines that tires are worn out as a result of driving on slippery roads.

[0048] Maintenance schedule suggestions

[0049] The server then recommends maintenance times to the user based on the wear prediction results, and a notification message is sent to the smartphone app or on the in-car display.

[0050] Example: The server notifies the user that "it is recommended to change the engine oil" and also that "it is recommended to check the tires after the next 1000 km of driving."

[0051] Refueling point suggestions

[0052] The server calculates the distance to the destination based on the current amount of gasoline remaining and consumption, and if refueling is required along the way, it suggests appropriate gas stations.

[0053] Example: The server determines that the user's next destination is 200 km away and suggests suitable refueling points since the current amount of gasoline is insufficient.

[0054] Providing Feedback

[0055] The server provides the results of wear predictions to maintenance companies and dealers, allowing them to prepare the necessary parts and maintenance in advance.

[0056] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides the service.

[0057] summary

[0058] This system collects and analyzes vehicle driving data and external information to predict wear and tear on each part, and by suggesting appropriate maintenance and refueling times to the user and providing feedback to maintenance companies, it supports efficient maintenance and safe driving.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The device collects driving data.

[0062] Specifically, the data collected includes the number of times the engine is started and stopped, the duration of time the lights are on, the duration of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, the route traveled, etc. This data is collected automatically via on-board sensors and GPS.

[0063] Step 2:

[0064] The driving data collected by the terminal is periodically sent to the server.

[0065] The data is uploaded to a server over the internet using a secure communication protocol, with precise timestamps attached to the data and the order in which it was collected maintained.

[0066] Step 3:

[0067] The server obtains external information via the Internet.

[0068] Specifically, weather information is obtained from a weather API, and road surface and traffic conditions are obtained from a traffic information API. The obtained external information is also saved with a timestamp.

[0069] Step 4:

[0070] The server receives and integrates driving data and external information.

[0071] The acquired data is mapped onto the same time axis and preprocessed, for example, by filling in missing data and normalizing the data.

[0072] Step 5:

[0073] The server inputs the preprocessed data into the AI ​​model.

[0074] The AI ​​model predicts the wear and tear of each part based on a machine learning algorithm, which has been trained in advance using a large amount of learning data.

[0075] Step 6:

[0076] The server analyzes the prediction results from the AI ​​model and calculates the wear and tear and replacement time for each part.

[0077] For example, the deterioration level of engine oil and the state of tire wear are output as numerical values, and the next maintenance schedule is determined based on these.

[0078] Step 7:

[0079] The server will suggest maintenance times and necessary part replacements to the user.

[0080] The recommendations are sent to a smartphone app or on the in-car display, and include specific replacement times and the recommended date and time for the next inspection.

[0081] Step 8:

[0082] The user confirms the proposed maintenance.

[0083] The user checks the maintenance schedule and makes a reservation if necessary.

[0084] Step 9:

[0085] The server calculates the distance to the destination based on the current fuel level and consumption.

[0086] This uses historical fuel consumption data and current fuel remaining data.

[0087] Step 10:

[0088] The server suggests gas stations.

[0089] Taking into consideration the route to the destination, if refueling is required along the way, appropriate refueling stations are suggested to the user.

[0090] Step 11:

[0091] The server provides feedback to the repair company or dealer.

[0092] It provides advance notification of predicted maintenance and required parts, allowing maintenance companies to make appropriate preparations.

[0093] Step 12:

[0094] A maintenance company prepares parts based on the notified feedback, and provides the user with prompt maintenance.

[0095] The maintenance company checks the parts inventory and arranges for the necessary parts.

[0096] summary

[0097] The system's processing steps collect and analyze driving data and external information, and use an AI model to predict the wear and tear of each part. Optimal maintenance and refueling times are suggested to users, and necessary information is provided to maintenance companies in advance. This ensures efficient and safe vehicle maintenance.

[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 technology did not offer a system that efficiently collected vehicle driving data and external information, analyzed them, and then suggested appropriate maintenance and refueling timings. This made it difficult for users to perform maintenance at the appropriate time, resulting in increased wear and tear on the vehicle and increased risk of breakdowns. Furthermore, it was difficult for repair companies and dealers to prepare the necessary parts and services in advance, creating a need for more efficient maintenance.

[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 collecting driving data, means for acquiring external information, means for preprocessing data based on the driving data and the external information, means for predicting wear based on the results of the data preprocessing, means for suggesting maintenance times to the user based on the results of the part wear prediction, means for suggesting refueling locations based on the remaining amount of fuel and the amount of fuel consumed, and means for providing feedback to repair companies and dealers according to the degree of maintenance necessity. This allows the user to perform maintenance and refueling at the appropriate time, reducing wear and tear on the vehicle and the risk of breakdown, and also allows repair companies and dealers to prepare necessary parts in advance, thereby improving maintenance efficiency.

[0103] "Driving data" refers to information relating to the vehicle's driving state and operating conditions.

[0104] "External information" refers to information about the external environment of the vehicle, such as weather and traffic conditions.

[0105] "Data preprocessing" refers to the process of analyzing and normalizing collected operational data and external information, and converting them into a format suitable for analysis and predictive models.

[0106] "Wear prediction" is the prediction of the deterioration state and replacement time of each vehicle part based on processed data.

[0107] The "means for proposing the timing of maintenance" is to notify the user of the appropriate timing of maintenance based on the predicted wear data.

[0108] The "means for suggesting a refueling location" is to suggest the most suitable refueling location to the user based on the current remaining amount of fuel and the predicted fuel consumption.

[0109] The "means for providing feedback" refers to providing the results of wear prediction to maintenance companies and dealers, enabling them to prepare the necessary parts and services in advance.

[0110] An "artificial intelligence model" is a computer algorithm that analyzes and learns from multiple data sets to recognize and predict patterns.

[0111] MODE FOR CARRYING OUT THE INVENTION

[0112] This invention is a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables. This system includes a terminal for collecting driving data, a server for acquiring external information, an AI model for predicting wear, a means for making maintenance suggestions to users, and a means for suggesting gas stations.

[0113] Data collection

[0114] The device collects driving data from the vehicle's engine control unit (ECU) and various sensors, including the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. The collected data is then stored on the vehicle's onboard storage media.

[0115] Example: The device connects to the vehicle's ECU and records 50 engine starts and stops, 120 minutes of headlight time, 30 minutes of windshield wiper time, and 1,500 km of driving distance.

[0116] Obtaining external information

[0117] The server obtains the necessary external information from weather information APIs and traffic information APIs via the Internet. This includes weather information, road surface conditions, traffic information, etc. Specifically, data can be obtained using the OpenWeatherMap API and Google (registered trademark) Maps Traffic API.

[0118] Example: A server receives information that the current local weather is rainy and road conditions are slippery.

[0119] Data Preprocessing

[0120] The server receives driving data sent from the terminal and external information it acquires, and preprocesses them. Data preprocessing involves analyzing and normalizing the collected data and converting it into a format suitable for analysis and predictive models.

[0121] Example: The server normalizes each item of driving data (e.g., number of engine starts and distance traveled) to a uniform scale, and similarly normalizes weather and traffic data.

[0122] Wear prediction

[0123] The server inputs the preprocessed data into a generative AI model (e.g., a model trained with TENSORFLOW® or PyTorch) to predict wear and tear for each part. The AI ​​model predicts wear and tear based on the collected data and returns the results to the server.

[0124] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that the oil is due for replacement. It also determines that tires are worn out as a result of driving on slippery roads.

[0125] Maintenance schedule suggestions

[0126] The server notifies the user of the need for maintenance based on the wear prediction results received from the AI ​​model, and the notification message is sent to a smartphone app or an in-car display.

[0127] Example: The server notifies the user that "it is recommended to change the engine oil" and also that "it is recommended to check the tires after the next 1000 km of driving."

[0128] Refueling point suggestions

[0129] The server calculates the current amount of gasoline remaining and the predicted consumption, and suggests appropriate refueling points based on the remaining distance to the destination.

[0130] Example: The server determines that the user's next destination is 200 km away and suggests refueling stops along the way, since the current amount of gasoline is insufficient.

[0131] Providing Feedback

[0132] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare for necessary parts and maintenance in advance.

[0133] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides the service.

[0134] Prompt Sentence Examples

[0135] Here are some example prompts to input to a generative AI model:

[0136] Please explain in detail the step-by-step program process for a system that predicts the deterioration status of a vehicle's consumables based on the following information:

[0137] Engine start / stop count: 50 times

[0138] Light duration: 120 minutes

[0139] Wiper operation time: 30 minutes

[0140] Mileage: 1500km

[0141] Weather information: rain

[0142] Road Condition: Slippery

[0143] Based on this information, please explain in detail the process of predicting when to change engine oil or tires and providing maintenance suggestions to the user.

[0144] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0145] Step 1: Collect driving data

[0146] The device collects driving data from the vehicle's engine control unit (ECU) and various sensors. The device is connected to the vehicle's ECU and obtains data such as the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.

[0147] Input: Raw data from various vehicle sensors and ECUs.

[0148] Output: A set of collected driving data (e.g., 50 engine starts, 120 minutes with the lights on, 1500 km driven, etc.).

[0149] Specific operation: The terminal is installed in the vehicle, collects data from the ECU and sensors in real time, and stores it on the vehicle's storage media.

[0150] Step 2: Obtaining external information

[0151] The server obtains external information from weather information APIs and traffic information APIs via the Internet. Specifically, it collects data using the OpenWeatherMap API and Google Maps Traffic API.

[0152] Input: Requests to the Weather and Traffic APIs.

[0153] Output: Captured weather and traffic data.

[0154] Specific operation: The server periodically accesses the API to obtain current weather information (e.g., rain, slippery roads) and traffic information, and stores it as well-formatted data.

[0155] Step 3: Preprocessing the data

[0156] The server receives driving data sent from the device and external information it acquires, normalizes and preprocesses this data, adjusting each item of driving data to a uniform scale and converting it into a format used by the AI ​​model.

[0157] Input: Collected driving and external information data.

[0158] Output: A normalized dataset.

[0159] Specific operation: The server scales the data and performs processes such as "normalizing the number of engine starts to a range of 0 to 1" and "converting weather data into a numerical format."

[0160] Step 4: Wear and tear prediction

[0161] The server inputs the preprocessed data into a generative AI model to predict wear and tear for each part. The AI ​​model analyzes the wear and tear status based on the input data and returns the results to the server.

[0162] Input: The normalized dataset.

[0163] Output: Wear prediction results for each part.

[0164] Specific operation: An AI model trained with TensorFlow predicts the degree of engine oil deterioration, the degree of tire wear, etc., and calculates when to replace them.

[0165] Step 5: Maintenance schedule suggestions

[0166] The server notifies the user of the need for maintenance based on the wear prediction results received from the AI ​​model, and the notification message is sent to a smartphone app or an in-car display.

[0167] Input: Wear prediction results for each part.

[0168] Output: Maintenance suggestion notification to user.

[0169] Specific operation: The server generates a message such as "It is recommended to change the engine oil" and sends a push notification to the user's smartphone. The same information is also displayed on the car's display.

[0170] Step 6: Propose refueling points

[0171] The server calculates the current amount of gasoline remaining and the predicted consumption, and suggests the optimal refueling location to the user. The server also determines the need for refueling based on the distance to the destination.

[0172] Input: Current gasoline level, predicted consumption data.

[0173] Output: Refueling point suggestions to the user.

[0174] Specific operation: Based on the information that "the remaining distance to the next destination is 200 km and the current amount of gasoline is insufficient," the server suggests refueling points along the way.

[0175] Step 7: Provide feedback

[0176] The server provides the results of wear predictions to maintenance companies and dealers, allowing them to prepare the necessary parts and services in advance.

[0177] Input: Wear prediction results for each part.

[0178] Output: Feedback notification to maintenance companies and dealers.

[0179] Specific operation: The server sends a message to the repair shop saying "User XX's vehicle needs an engine oil change," and the repair shop prepares the parts and gets ready to provide service.

[0180] (Application example 1)

[0181] 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."

[0182] Conventional automobile maintenance systems often fail to fully utilize driving data and external information, resulting in inappropriate prediction of part wear and inappropriate suggestions for maintenance timing. Furthermore, the system's ability to suggest appropriate gas stations based on remaining fuel levels is insufficient, resulting in low user convenience. Furthermore, feedback provided to repair companies and dealers is ineffective, resulting in low maintenance efficiency. The present invention aims to solve these problems and support users in driving safely and efficiently.

[0183] 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.

[0184] In this invention, the server includes a means for collecting driving data, a means for acquiring external information, a means for predicting part wear based on the driving data and the external information, a means for suggesting maintenance times to the user based on the part wear prediction results, a means for suggesting gas stations based on the current fuel level and consumption, a means for providing feedback to maintenance companies and dealers based on the degree of maintenance necessity, a data normalization means for predicting wear using a generative AI model, and a means for notifying the user based on a prompt sentence. This makes it possible to appropriately utilize driving data and external information to predict part wear and accurately suggest maintenance times and gas stations to the user. Furthermore, by providing prompt and accurate feedback to maintenance companies and dealers, maintenance efficiency can be improved.

[0185] "Means for collecting driving data" refers to devices and systems for obtaining data related to the driving conditions of a vehicle.

[0186] "Means for acquiring external information" refers to techniques and methods for collecting information about the external environment, such as weather information, road surface conditions, and traffic information.

[0187] "Means for predicting part wear based on driving data and external information" refers to technology that uses driving data and collected external information to predict the deterioration and replacement timing of automobile parts.

[0188] "Means for proposing maintenance timing to users based on the results of part wear prediction" refers to technology that notifies and suggests appropriate maintenance timing to users based on the results of wear prediction.

[0189] "Means for suggesting gas stations based on the current remaining fuel amount and consumption amount" refers to technology that guides the user to the most suitable gas station based on the remaining fuel amount and the rate at which it is consumed.

[0190] "Means for providing feedback to repair companies and dealers based on the degree of maintenance required" refers to technology that provides necessary information to repair companies and dealers when the need for maintenance increases.

[0191] "Data normalization method for wear and tear prediction using generative AI models" refers to a technique that converts input data into a unified format so that the AI ​​model can function efficiently.

[0192] "User notification means based on prompt sentences" refers to a technology that appropriately notifies the user of necessary information based on defined questions or instruction sentences.

[0193] This invention is a system that collects and analyzes operational data and external information to predict the deterioration status of consumables and the timing of maintenance. A detailed description of this system is provided below.

[0194] Data collection

[0195] The device collects driving data from the vehicle's sensors. This data includes the number of times the engine was started and stopped, the duration the lights were on, the duration the wipers were on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. The device transmits this data in real time, for example, via Bluetooth or Wi-Fi. For example, the device can record that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance traveled was 1,500 km.

[0196] Obtaining external information

[0197] The server obtains external information via the Internet. This information includes weather information, road surface conditions, and traffic information. The server uses the OpenWeatherMap API for weather information and the Google Maps API for traffic information. For example, the server can obtain information that the current weather in the area is rainy and the roads are slippery.

[0198] Wear prediction

[0199] The server uses a generative AI model to predict wear and tear on each part based on collected driving data and external information. The data is normalized and input into an AI model using, for example, TensorFlow or PyTorch. This predicts when each part (e.g., engine oil, brake pads, tires) needs to be replaced. For example, the server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that it is soon time to replace the oil. It may also determine that tires are wearing out as a result of driving on slippery roads.

[0200] Maintenance schedule suggestions

[0201] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. For example, a message such as "We recommend changing your engine oil" or "We recommend checking your tires after the next 1000km of driving" is sent.

[0202] Refueling point suggestions

[0203] The server calculates the distance to the destination based on the current fuel remaining and consumption, and if refueling is required along the way, suggests an appropriate gas station. Based on the distance to the destination and the current location information, the server uses the Google Maps API to guide the user to nearby gas stations. As a specific example, if the user confirms that the next destination is 200 km away and the current gas level is insufficient, the server suggests an appropriate refueling point.

[0204] Providing Feedback

[0205] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare the necessary parts and maintenance in advance. For example, the server notifies a repair company that "User XX's vehicle needs an engine oil change," and the repair company prepares the necessary parts based on this information and provides the service.

[0206] Prompt Sentence Examples

[0207] "To predict vehicle maintenance, please predict engine oil deterioration based on the following driving data and external information: Number of engine starts: 50, Lights on for: 120 minutes, Wiper operation time: 30 minutes, Mileage: 1500 km, Weather information: Rain, Road conditions: Slippery. For output, please display the recommended engine oil change interval in Japanese."

[0208] In this way, the present invention provides a system that combines driving data and external information to predict the deterioration status of each part and notify the user of the appropriate maintenance timing. In addition, by providing the wear prediction results to maintenance companies, maintenance efficiency can be improved.

[0209] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0210] Step 1:

[0211] The terminal collects driving data from the vehicle. This driving data includes the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are operated, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Specifically, the terminal obtains this data from the vehicle's sensors using Bluetooth or Wi-Fi and transmits the data to the server in real time. The input data is the readings from the various sensors, and the output is the driving data sent to the server.

[0212] Step 2:

[0213] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. For example, the server obtains current weather information using the OpenWeatherMap API and traffic conditions using the Google Maps API. The input is a data request from the weather API or traffic information API, and the output is the obtained external information.

[0214] Step 3:

[0215] The server uses a generative AI model to predict wear and tear on each part based on the collected driving data and external information. Specifically, the driving data and external information are normalized and input into an AI model using TensorFlow and PyTorch. The AI ​​model uses this data to predict when to replace consumables such as engine oil, brake pads, and tires. The input is the normalized driving data and external information, and the output is the predicted replacement times for consumables.

[0216] Step 4:

[0217] The server will suggest maintenance times to the user based on the results of the wear prediction. Specifically, if it determines that maintenance is necessary based on the results of the wear prediction, it will send a notification message to the user using the smartphone's push notification function. The input is the wear prediction result, and the output is the notification message to the user.

[0218] Step 5:

[0219] The server calculates the distance to the destination based on the current fuel level and consumption, and if refueling is required along the way, suggests suitable gas stations. Specifically, it uses the Google Maps API to guide the driver to nearby gas stations based on the distance to the destination and the current location. The input is the current fuel level, consumption, location, and distance to the destination, and the output is information about suggested gas stations.

[0220] Step 6:

[0221] The server provides the results of wear prediction to maintenance companies and dealers. Specifically, it uses a REST API to send information about users who need to replace consumables to maintenance companies. The input is the wear prediction results and user information, and the output is a notification to the maintenance company. This allows maintenance companies to prepare the necessary parts in advance and provide services efficiently.

[0222] 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.

[0223] This invention combines a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance schedule of consumables with an emotion engine that recognizes user emotions. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that predicts wear and tear, a means for suggesting maintenance and gas stations to the user, and an emotion engine that recognizes user emotions and provides appropriate feedback. The program processing of this system is explained below in natural language.

[0224] Data collection

[0225] The device collects driving data from the vehicle, such as the number of engine starts and stops, the duration of headlights, the duration of wiper operation, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[0226] Example: The device records that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance driven was 1500 km. Furthermore, the device recognizes that the user is stressed while driving.

[0227] Obtaining external information

[0228] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[0229] Example: The server receives information that the current weather in the area is rainy and the roads are slippery. The server collects the user's emotional state as feedback and considers appropriate countermeasures.

[0230] Wear prediction

[0231] The server uses an AI model to predict wear and tear on each part based on collected driving data, external information, and the user's emotional state. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when each part (e.g., engine oil, brake pads, tires) should be replaced.

[0232] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that it is time to change the oil. It also determines that tires are wearing out as a result of driving on slippery roads. Furthermore, if the user's stress level is affecting the vehicle's wear and tear, the server will provide special attention.

[0233] Maintenance schedule suggestions

[0234] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. The emotion engine makes suggestions that take into account the user's emotional state.

[0235] Example: The server notifies the user that "It is recommended to change the engine oil." At the same time, it also notifies that "It is recommended to check the tires after the next 1000 km of driving." Furthermore, if the user is feeling stressed, it adds a suggestion that "It is recommended to take a break in a place where you can drive in a relaxed manner."

[0236] Refueling point suggestions

[0237] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[0238] Example: The server confirms that the user's next destination is 200 km away, and suggests an appropriate refueling point since the current amount of gasoline is insufficient. If the user feels impatient or anxious, the server suggests "We recommend refueling at the next safe location."

[0239] Providing Feedback

[0240] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare for necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[0241] Example: The server notifies the maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides service. If the user is feeling stressed, the server considers providing special service.

[0242] summary

[0243] The system's processing steps collect and analyze driving data and external information, and use an AI model to predict the wear and tear of each part. The system suggests optimal maintenance and refueling times to users, and provides necessary information to maintenance companies in advance. The integration of an emotion engine provides a safe and comfortable driving environment that takes into account the user's emotional state.

[0244] The processing flow will be explained below.

[0245] Step 1:

[0246] The device collects driving data.

[0247] Specifically, it automatically collects data from each sensor, such as the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.In addition, it uses an emotion engine to analyze the user's voice and recognize their face, and recognizes their emotional state (e.g., stress, anxiety, relaxation, etc.) in real time.

[0248] Example: The device records that the engine has been started 50 times, the lights have been on for 120 minutes, the wipers have been on for 30 minutes, and the distance traveled is 1500 km. In addition, the emotion engine recognizes that the user is feeling stressed while driving.

[0249] Step 2:

[0250] The terminal transmits the collected driving data and user emotion data to the server.

[0251] The data is periodically uploaded to a server using a secure communication protocol and is time-stamped to record the exact time of collection.

[0252] Example: The device sends the collected driving data and user emotion data on "stress state" to the server.

[0253] Step 3:

[0254] The server obtains external information via the Internet.

[0255] Specifically, weather information is obtained from a weather API, and road surface conditions and traffic information are obtained from a traffic information API. The obtained external information is also saved with a timestamp.

[0256] Example: The server retrieves the weather information for the current location, indicating that it is raining and the roads are slippery.

[0257] Step 4:

[0258] The server integrates driving data, external information, and user emotion data.

[0259] The acquired data is mapped onto the same time axis and preprocessed, specifically by filling in missing data, normalizing the data, and calculating correlations.

[0260] Example: A server integrates driving data, weather information, road information, and user sentiment data and prepares it for analysis.

[0261] Step 5:

[0262] The server inputs the preprocessed data into an AI model to predict part wear.

[0263] The AI ​​model uses machine learning algorithms to predict the wear and tear of each part. The model is pre-trained with a large amount of learning data. The prediction results include the wear and tear and replacement times for parts such as engine oil, brake pads, and tires.

[0264] Example: The server predicts that the engine oil is deteriorating quickly and needs to be replaced soon, and determines that the brake pads are wearing out due to frequent braking.

[0265] Step 6:

[0266] The server analyzes the prediction results from the AI ​​model and provides detailed feedback while taking into account the user's emotional state.

[0267] Based on the predicted replacement times for parts and user sentiment, an appropriate maintenance schedule is created and notified to the user.

[0268] Example: The server notifies the user that "it is recommended to change the engine oil" and also advises that "it is recommended to check the tires after the next 1000 km of driving." In addition, because the user is in a stressed state, it makes an additional suggestion that "it is recommended to take a break in a relaxing place."

[0269] Step 7:

[0270] The server calculates the distance to the destination based on the current fuel level and consumption.

[0271] It does this by using historical fuel consumption data and current fuel level data, and also takes into account the user's emotional state.

[0272] Example: The server recognizes that the user is heading to a destination 200 km away, and determines that the current fuel level is insufficient and that refueling is necessary along the way. If the user is feeling anxious or anxious, the server suggests safe refueling points.

[0273] Step 8:

[0274] The server suggests gas stations to the user.

[0275] The suggestions are displayed on a smartphone app or on an in-car display, and change depending on the user's emotional state.

[0276] Example: The server suggests "Please fill up at a gas station within the next 100 km" or, if the user is feeling impatient, notifies "Searching for a safe gas station."

[0277] Step 9:

[0278] The server provides feedback on the wear prediction results and user emotion data to maintenance companies and dealers.

[0279] This allows necessary parts and maintenance to be prepared in advance.

[0280] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change and the user is currently feeling stressed." The maintenance company uses this information to provide prompt and appropriate service.

[0281] Step 10:

[0282] The maintenance company prepares parts based on the feedback and provides the user with prompt maintenance.

[0283] The repair company will check the parts inventory and arrange for parts as needed, and will also respond appropriately depending on the user's emotional state.

[0284] Example: A maintenance company prepares engine oil and has all the necessary information ready before the user arrives. When the user arrives, they receive special treatment, such as a relaxing environment.

[0285] summary

[0286] The system's processing steps collect and analyze driving data, external information, and user emotional data, and use an AI model to predict the wear and tear of each part. The system suggests appropriate maintenance and refueling times to users, and provides necessary information to maintenance companies in advance. The integration of an emotional engine takes the user's emotional state into consideration, creating a safe and comfortable driving environment.

[0287] Example 2

[0288] 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."

[0289] Modern cars are equipped with many sensors and can collect a wide variety of data, but systems that effectively utilize this data and appropriately notify users of optimal maintenance and refueling times are not widely available. Furthermore, conventional systems do not take user emotions into account and do not provide appropriate feedback based on changes in stress and emotion. This can compromise user safety and comfort.

[0290] 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.

[0291] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for predicting parts wear based on the driving data, the external information, and the user's emotions, means for suggesting maintenance times to the user based on the parts wear prediction results, means for suggesting gas stations based on the current remaining fuel amount and consumption amount, and means for providing feedback to repair companies and dealers according to the degree of necessity for maintenance and the user's emotions. This makes it possible to propose optimal maintenance and refueling timings that take into account the user's emotions while utilizing the driving data and external information.

[0292] "Driving data" refers to data relating to the vehicle's operating state and driving conditions, and specifically includes the number of times the engine is started and stopped, the length of time the lights are on, the length of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, and the route traveled.

[0293] "External information" refers to information obtained via the Internet or external APIs, and specifically includes weather information, road surface conditions, traffic information, etc.

[0294] An "emotion engine" is a system that analyzes emotions from the user's voice, facial expressions, etc., and recognizes stress levels and changes in emotions.

[0295] "Wear prediction" involves predicting the deterioration status and replacement timing of vehicle parts (e.g., engine oil, brake pads, tires) based on collected driving data, external information, and the user's emotional state.

[0296] "Maintenance timing suggestion" means notifying the user when maintenance such as replacement or inspection of each vehicle part is required based on the wear prediction results.

[0297] "Fuel station suggestion" calculates the distance to the destination based on the current fuel remaining and consumption, and recommends appropriate fuel stations if refueling is required along the way.

[0298] "Providing feedback" means providing information to repair companies and dealers regarding vehicle maintenance and preparation of necessary parts based on wear prediction results and user emotion data.

[0299] An "AI model" refers to an artificial intelligence system that receives collected data as input and uses a learning algorithm to predict wear and tear.

[0300] "Data normalization" refers to converting collected data to a certain scale or format, making it suitable for input into an AI model.

[0301] This invention combines a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables with an emotion engine that recognizes user emotions. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that performs wear prediction, a means for suggesting maintenance and gas stations to the user, and an emotion engine that recognizes user emotions and provides appropriate feedback.

[0302] The device collects driving data from the vehicle in real time. The device is connected to a GPS module, engine control unit (ECU), and sensor array, and acquires data from these. Specifically, the device collects data such as the number of engine starts and stops, the duration of headlight illumination, the duration of wiper operation, the number and duration of accelerator and brake operation, mileage, and driving route. The device is also equipped with a camera and microphone, which are used to analyze the user's voice and facial expressions and activate an emotion engine that recognizes emotions. For example, the device acquires the number of engine starts from the engine control unit (ECU) and measures the mileage using the GPS module. The camera also captures the user's facial expressions in real time, and the emotion engine analyzes the user's stress level.

[0303] The server obtains external information via the Internet. This includes weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data. For example, the server sends a request to the weather forecast API to obtain weather information for the current location and destination. At the same time, it obtains information from the road API that the current road surface conditions have been updated to "slippery."

[0304] The server inputs collected driving data, external information, and the user's emotional state into the AI ​​model. The AI ​​model uses a wear prediction algorithm based on deep learning to predict the deterioration status and replacement timing of each part, such as engine oil, brake pads, and tires. At this time, the data is normalized and input into the AI ​​model. For example, the server supplies data to the AI ​​model, which predicts that "the engine oil needs to be changed in 500 km." It also takes into account road condition data and determines that the remaining mileage of the tires may be shortened.

[0305] The server notifies the user of the optimal maintenance timing based on the wear prediction results. This notification is sent to the smartphone app or in-car display. The emotion engine also makes suggestions that take the user's emotional state into account. For example, the server may notify the user's smartphone app, "It's almost time to change your engine oil. We recommend changing it within the next 500 km." Furthermore, if the server recognizes that the user is feeling stressed, it adds a message saying, "We also recommend taking a break in a relaxing place."

[0306] The server calculates the remaining distance to the destination based on the current amount of gasoline remaining and consumption, and suggests suitable gas stations if refueling is required along the way. This is also done by analyzing GPS data and route information to select the most efficient and safe refueling point. For example, based on the user's current location and remaining gasoline, the server might suggest, "You will run out of gas in the next 150 km. We recommend that the next refueling point be a service area 30 km away." If the user is in a hurry, it adds a comment saying, "We recommend refueling at the shortest distance."

[0307] Based on the wear prediction results and the user's emotional data, the server provides repair companies and dealers with information about vehicle maintenance and the preparation of necessary parts. This allows necessary parts and maintenance to be prepared in advance, allowing the user to receive service smoothly. For example, the server may notify a repair company that "User A's vehicle is nearing the time for an engine oil change. Please prepare the parts." Furthermore, based on the user's emotional data, the server may suggest that "The user is feeling stressed, so please consider providing service in a relaxed environment."

[0308] By utilizing this system, it is possible to effectively analyze driving data and external information, provide users with optimal maintenance and refueling timings, and improve services that reflect the user's emotional state.

[0309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0310] Step 1: Data collection

[0311] The device collects various driving data from the vehicle in real time. It is connected to a GPS module, engine control unit (ECU), and various sensors, and acquires data from these devices. Specifically, it collects the number of engine starts and stops, the duration of headlight illumination, the duration of wiper operation, the number and duration of accelerator and brake operation, the distance traveled, and the route traveled. It also uses a camera and microphone to analyze the user's voice and facial expressions, and an emotion engine detects the user's stress level.

[0312] Input: In-vehicle devices (GPS module, ECU, various sensors), camera, microphone

[0313] Output: Driving data (mileage, number of engine starts, etc.), emotional data (stress level, etc.)

[0314] Specific operation: The device obtains the number of engine starts from the ECU, measures the mileage using the GPS module, captures the user's facial expressions in real time using the camera, and analyzes the user's stress level using the emotion engine.

[0315] Step 2: Obtaining external information

[0316] The server uses external APIs to obtain weather information, road surface conditions, and traffic information. Data is collected in real time using weather APIs and traffic information APIs.

[0317] Input: Weather API, Road API, Traffic API

[0318] Output: External information (weather information, road surface conditions, traffic conditions)

[0319] Specific operation: The server sends a request to the weather forecast API to obtain weather information for the current location and destination. At the same time, it obtains information from the road API that the current road conditions have been updated to "slippery."

[0320] Step 3: Wear and tear prediction

[0321] The server inputs the driving data collected in step 1, the external information obtained in step 2, and the user's emotional data into the AI ​​model. The AI ​​model uses deep learning to execute a wear prediction algorithm and predict the deterioration status and replacement timing of each part. The data is normalized and input into the AI ​​model.

[0322] Input: driving data, external information, emotion data

[0323] Output: Wear prediction results (engine oil change timing, tire wear status, etc.)

[0324] Specific operation: The server normalizes the collected data and inputs it into the AI ​​model. The AI ​​model analyzes the data and outputs a prediction result: "It's time to change the engine oil in 500 km."

[0325] Step 4: Maintenance schedule suggestions

[0326] The server notifies the user of the optimal maintenance period based on the wear prediction results. Maintenance suggestions are sent to the user's smartphone app or the in-car display. The emotion engine makes suggestions that take the user's emotional state into consideration.

[0327] Input: Wear prediction results, user emotion data

[0328] Output: Maintenance notification (smartphone app, in-car display)

[0329] Specific operation: The server notifies the user's smartphone app that "It's almost time to change the engine oil. We recommend changing it within the next 500 km." If the user is feeling stressed, the server adds a suggestion that "We also recommend taking a break in a relaxing place."

[0330] Step 5: Propose refueling points

[0331] The server calculates the remaining distance to the destination based on the current fuel level and consumption, and suggests suitable gas stations if refueling is required along the way. It analyzes GPS data and route information to select the optimal refueling point.

[0332] Input: Fuel level, consumption, GPS data, route information

[0333] Output: Refueling suggestion (location information of gas stations)

[0334] Specific operation: Based on the current location and remaining gasoline of the user's vehicle, the server suggests, "You will run out of gas in the next 150 km. We recommend that the next refueling point be a service area 30 km away." If the user is in a hurry, it adds a comment saying, "We recommend refueling at the shortest distance."

[0335] Step 6: Provide feedback

[0336] The server provides repair companies and dealers with information on maintenance and the preparation of necessary parts based on the wear prediction results and user emotion data, allowing the necessary parts and maintenance to be prepared in advance, ensuring smooth service for users.

[0337] Input: Wear prediction results, user emotion data

[0338] Output: Feedback information (notification to maintenance companies and dealers)

[0339] Specific operation: The server notifies the maintenance company that "User A's vehicle's engine oil is due for a change soon. Please prepare the parts." It also suggests that "The user is feeling stressed, so please consider providing the service in a relaxed environment."

[0340] (Application example 2)

[0341] 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."

[0342] Conventional car maintenance systems can predict part wear and suggest maintenance times based on driving data and external information, but they have the problem of not being able to provide feedback that takes into account the user's emotional state. This makes it difficult to reduce the user's stress and anxiety, and to provide a safe and comfortable driving environment.

[0343] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0344] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for predicting parts wear based on the driving data and the external information, means for suggesting maintenance times to the user based on the results of the parts wear prediction, means for suggesting gas stations based on the current remaining fuel level and fuel consumption, means for providing feedback to a maintenance company or dealer according to the degree of need for maintenance, and means for recognizing the user's emotional state and providing appropriate feedback. This provides feedback that takes the user's emotional state into consideration, enabling a safe and comfortable driving environment.

[0345] "Driving data" refers to information about the driving conditions of a vehicle, such as the number of times the engine is started and stopped, the length of time the lights are on, the length of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, and the route traveled.

[0346] "External information" refers to information related to the driving environment of the vehicle, specifically weather information, road surface conditions, traffic information, and the like.

[0347] "Parts wear prediction" refers to predicting the deterioration status and replacement timing of each part of a vehicle (e.g., engine oil, brake pads, tires, etc.) based on driving data and external information.

[0348] "Maintenance timing suggestion" refers to the process of notifying the user of the timing for replacement or inspection of each part of the car based on the results of part wear prediction.

[0349] "Suggesting gas stations" refers to a process of specifying and suggesting gas stations that the user should stop at to refuel based on the current remaining fuel amount and fuel consumption.

[0350] "Providing feedback" means notifying repair shops and dealers of the necessary information depending on the degree of maintenance required, and encouraging them to prepare the appropriate service and parts.

[0351] "Means for recognizing emotional states" refers to technology that recognizes a user's emotional states, such as stress, impatience, and anxiety, by analyzing the user's voice and facial expressions.

[0352] The "means for providing appropriate feedback" refers to a process of providing advice or suggestions to reduce the user's stress or anxiety based on the user's emotional state.

[0353] System Configuration

[0354] This invention is a system including means for collecting driving data, means for acquiring external information, means for predicting part wear based on the driving data and external information, means for suggesting maintenance times to the user based on the results of the part wear prediction, means for suggesting gas stations based on the current remaining fuel level and consumption, means for providing feedback to maintenance companies and dealers according to the degree of need for maintenance, and means for recognizing the emotional state of the user and providing appropriate feedback.

[0355] Data collection

[0356] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[0357] Obtaining external information

[0358] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[0359] Wear prediction

[0360] The server uses an AI model to predict wear and tear on each part based on collected driving data, external information, and the user's emotional state. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when each part (e.g., engine oil, brake pads, tires) should be replaced.

[0361] Maintenance schedule suggestions

[0362] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. The emotion engine makes suggestions that take into account the user's emotional state.

[0363] Refueling point suggestions

[0364] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[0365] Providing Feedback

[0366] The server provides the results of wear predictions to repair shops and dealers, allowing them to prepare necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[0367] Specific examples

[0368] For example, a device might record that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the mileage was 1,500 km. Furthermore, the device might recognize that the user is feeling stressed while driving. The server might also acquire information that the current local weather is rainy and the roads are slippery. Furthermore, the server might predict that frequent engine starts and stops will accelerate engine oil deterioration and notify the user that the oil is due for replacement. It might also determine that driving on slippery roads has accelerated tire wear. Furthermore, if the user's stress level is affecting the vehicle's wear, the device might urge the user to take special precautions. Based on this information, the server might notify the user that "it is recommended to change the engine oil" and, at the same time, that "it is recommended to check the tires after the next 1,000 km of driving." Furthermore, if the user is feeling stressed, the server might add a suggestion that "it is recommended to take a break in a place where you can relax while driving."

[0369] Prompt Sentence Examples

[0370] Describe an assistant application that identifies the stress level a user experiences while driving and, based on that, suggests appropriate relaxation or resting spots.

[0371] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0372] Step 1:

[0373] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[0374] *Input: various sensor data from the car, user's voice and facial expressions

[0375] * Output: Driving data and user's emotional state

[0376] Step 2:

[0377] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[0378] *Input: Data from weather API and traffic information API

[0379] * Output: Weather information, road surface conditions, traffic information

[0380] Step 3:

[0381] The server normalizes the collected driving data and external information and inputs it into an AI model. The AI ​​model uses this data to predict wear and tear on each part. Specifically, driving data (number of engine starts and stops, light on time, etc.) and external information (weather, road conditions, etc.) are input, normalized, and the AI ​​model predicts part deterioration.

[0382] *Input: operation data, external information

[0383] * Output: Part wear prediction results

[0384] Step 4:

[0385] The server then proposes maintenance times to the user based on the wear prediction results. Specifically, it sends a notification message to the user's smartphone or in-car display. The emotion engine makes proposals that take into account the user's emotional state.

[0386] *Input: wear prediction results, user's emotional state

[0387] * Output: Maintenance time suggestion message

[0388] Step 5:

[0389] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[0390] *Input: current remaining gasoline, consumption, driving distance, user's emotional state

[0391] * Output: Gas station suggestion message

[0392] Step 6:

[0393] The server provides the results of wear predictions to repair shops and dealers, allowing them to prepare necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[0394] *Input: wear prediction results, user's emotional state

[0395] * Output: Feedback information for repair shops and dealers

[0396] 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.

[0397] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0398] 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.

[0399] [Second embodiment]

[0400] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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).

[0406] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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."

[0412] This invention is a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that performs wear prediction, and means for suggesting maintenance and gas stations to users. The program processing of this system is explained below in natural language.

[0413] Data collection

[0414] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are in operation, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.

[0415] Example: The device records that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance traveled was 1500 km.

[0416] Obtaining external information

[0417] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[0418] Example: A server receives information that the current local weather is rainy and road conditions are slippery.

[0419] Wear prediction

[0420] The server uses an AI model to predict wear and tear on each part based on collected driving data and external information. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when to replace each part (e.g., engine oil, brake pads, tires).

[0421] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that the oil is due for replacement. It also determines that tires are worn out as a result of driving on slippery roads.

[0422] Maintenance schedule suggestions

[0423] The server then recommends maintenance times to the user based on the wear prediction results, and a notification message is sent to the smartphone app or on the in-car display.

[0424] Example: The server notifies the user that "it is recommended to change the engine oil" and also that "it is recommended to check the tires after the next 1000 km of driving."

[0425] Refueling point suggestions

[0426] The server calculates the distance to the destination based on the current amount of gasoline remaining and consumption, and if refueling is required along the way, it suggests appropriate gas stations.

[0427] Example: The server determines that the user's next destination is 200 km away and suggests suitable refueling points since the current amount of gasoline is insufficient.

[0428] Providing Feedback

[0429] The server provides the results of wear predictions to maintenance companies and dealers, allowing them to prepare the necessary parts and maintenance in advance.

[0430] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides the service.

[0431] summary

[0432] This system collects and analyzes vehicle driving data and external information to predict wear and tear on each part, and by suggesting appropriate maintenance and refueling times to the user and providing feedback to maintenance companies, it supports efficient maintenance and safe driving.

[0433] The processing flow will be explained below.

[0434] Step 1:

[0435] The device collects driving data.

[0436] Specifically, the data collected includes the number of times the engine is started and stopped, the duration of time the lights are on, the duration of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, the route traveled, etc. This data is collected automatically via on-board sensors and GPS.

[0437] Step 2:

[0438] The driving data collected by the terminal is periodically sent to the server.

[0439] The data is uploaded to a server over the internet using a secure communication protocol, with precise timestamps attached to the data and the order in which it was collected maintained.

[0440] Step 3:

[0441] The server obtains external information via the Internet.

[0442] Specifically, weather information is obtained from a weather API, and road surface and traffic conditions are obtained from a traffic information API. The obtained external information is also saved with a timestamp.

[0443] Step 4:

[0444] The server receives and integrates driving data and external information.

[0445] The acquired data is mapped onto the same time axis and preprocessed, for example, by filling in missing data and normalizing the data.

[0446] Step 5:

[0447] The server inputs the preprocessed data into the AI ​​model.

[0448] The AI ​​model predicts the wear and tear of each part based on a machine learning algorithm, which has been trained in advance using a large amount of learning data.

[0449] Step 6:

[0450] The server analyzes the prediction results from the AI ​​model and calculates the wear and tear and replacement time for each part.

[0451] For example, the deterioration level of engine oil and the state of tire wear are output as numerical values, and the next maintenance schedule is determined based on these.

[0452] Step 7:

[0453] The server will suggest maintenance times and necessary part replacements to the user.

[0454] The recommendations are sent to a smartphone app or on the in-car display, and include specific replacement times and the recommended date and time for the next inspection.

[0455] Step 8:

[0456] The user confirms the proposed maintenance.

[0457] The user checks the maintenance schedule and makes a reservation if necessary.

[0458] Step 9:

[0459] The server calculates the distance to the destination based on the current fuel level and consumption.

[0460] This uses historical fuel consumption data and current fuel remaining data.

[0461] Step 10:

[0462] The server suggests gas stations.

[0463] Taking into consideration the route to the destination, if refueling is required along the way, appropriate refueling stations are suggested to the user.

[0464] Step 11:

[0465] The server provides feedback to the repair company or dealer.

[0466] It provides advance notification of predicted maintenance and required parts, allowing maintenance companies to make appropriate preparations.

[0467] Step 12:

[0468] A maintenance company prepares parts based on the notified feedback, and provides the user with prompt maintenance.

[0469] The maintenance company checks the parts inventory and arranges for the necessary parts.

[0470] summary

[0471] The system's processing steps collect and analyze driving data and external information, and use an AI model to predict the wear and tear of each part. Optimal maintenance and refueling times are suggested to users, and necessary information is provided to maintenance companies in advance. This ensures efficient and safe vehicle maintenance.

[0472] Example 1

[0473] 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."

[0474] Conventional technology did not offer a system that efficiently collected vehicle driving data and external information, analyzed them, and then suggested appropriate maintenance and refueling timings. This made it difficult for users to perform maintenance at the appropriate time, resulting in increased wear and tear on the vehicle and increased risk of breakdowns. Furthermore, it was difficult for repair companies and dealers to prepare the necessary parts and services in advance, creating a need for more efficient maintenance.

[0475] 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.

[0476] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for preprocessing data based on the driving data and the external information, means for predicting wear based on the results of the data preprocessing, means for suggesting maintenance times to the user based on the results of the part wear prediction, means for suggesting refueling locations based on the remaining amount of fuel and the amount of fuel consumed, and means for providing feedback to repair companies and dealers according to the degree of maintenance necessity. This allows the user to perform maintenance and refueling at the appropriate time, reducing wear and tear on the vehicle and the risk of breakdown, and also allows repair companies and dealers to prepare necessary parts in advance, thereby improving maintenance efficiency.

[0477] "Driving data" refers to information relating to the vehicle's driving state and operating conditions.

[0478] "External information" refers to information about the external environment of the vehicle, such as weather and traffic conditions.

[0479] "Data preprocessing" refers to the process of analyzing and normalizing collected operational data and external information, and converting them into a format suitable for analysis and predictive models.

[0480] "Wear prediction" is the prediction of the deterioration state and replacement time of each vehicle part based on processed data.

[0481] The "means for proposing the timing of maintenance" is to notify the user of the appropriate timing of maintenance based on the predicted wear data.

[0482] The "means for suggesting a refueling location" is to suggest the most suitable refueling location to the user based on the current remaining amount of fuel and the predicted fuel consumption.

[0483] The "means for providing feedback" refers to providing the results of wear prediction to maintenance companies and dealers, enabling them to prepare the necessary parts and services in advance.

[0484] An "artificial intelligence model" is a computer algorithm that analyzes and learns from multiple data sets to recognize and predict patterns.

[0485] MODE FOR CARRYING OUT THE INVENTION

[0486] This invention is a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables. This system includes a terminal for collecting driving data, a server for acquiring external information, an AI model for predicting wear, a means for making maintenance suggestions to users, and a means for suggesting gas stations.

[0487] Data collection

[0488] The device collects driving data from the vehicle's engine control unit (ECU) and various sensors, including the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. The collected data is then stored on the vehicle's onboard storage media.

[0489] Example: The device connects to the vehicle's ECU and records 50 engine starts and stops, 120 minutes of headlight time, 30 minutes of windshield wiper time, and 1,500 km of driving distance.

[0490] Obtaining external information

[0491] The server obtains the necessary external information from weather information APIs and traffic information APIs via the Internet. This includes weather information, road surface conditions, traffic information, etc. Specifically, data can be obtained using the OpenWeatherMap API and Google Maps Traffic API.

[0492] Example: A server receives information that the current local weather is rainy and road conditions are slippery.

[0493] Data Preprocessing

[0494] The server receives driving data sent from the terminal and external information it acquires, and preprocesses them. Data preprocessing involves analyzing and normalizing the collected data and converting it into a format suitable for analysis and predictive models.

[0495] Example: The server normalizes each item of driving data (e.g., number of engine starts and distance traveled) to a uniform scale, and similarly normalizes weather and traffic data.

[0496] Wear prediction

[0497] The server inputs the preprocessed data into a generative AI model (e.g., a model trained with TensorFlow or PyTorch) to predict wear and tear for each part. The AI ​​model predicts wear and tear based on the collected data and returns the results to the server.

[0498] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that the oil is due for replacement. It also determines that tires are worn out as a result of driving on slippery roads.

[0499] Maintenance schedule suggestions

[0500] The server notifies the user of the need for maintenance based on the wear prediction results received from the AI ​​model, and the notification message is sent to a smartphone app or an in-car display.

[0501] Example: The server notifies the user that "it is recommended to change the engine oil" and also that "it is recommended to check the tires after the next 1000 km of driving."

[0502] Refueling point suggestions

[0503] The server calculates the current amount of gasoline remaining and the predicted consumption, and suggests appropriate refueling points based on the remaining distance to the destination.

[0504] Example: The server determines that the user's next destination is 200 km away and suggests refueling stops along the way, since the current amount of gasoline is insufficient.

[0505] Providing Feedback

[0506] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare for necessary parts and maintenance in advance.

[0507] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides the service.

[0508] Prompt Sentence Examples

[0509] Here are some example prompts to input to a generative AI model:

[0510] Please explain in detail the step-by-step program process for a system that predicts the deterioration status of a vehicle's consumables based on the following information:

[0511] Engine start / stop count: 50 times

[0512] Light duration: 120 minutes

[0513] Wiper operation time: 30 minutes

[0514] Mileage: 1500km

[0515] Weather information: rain

[0516] Road Condition: Slippery

[0517] Based on this information, please explain in detail the process of predicting when to change engine oil or tires and providing maintenance suggestions to the user.

[0518] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0519] Step 1: Collect driving data

[0520] The device collects driving data from the vehicle's engine control unit (ECU) and various sensors. The device is connected to the vehicle's ECU and obtains data such as the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.

[0521] Input: Raw data from various vehicle sensors and ECUs.

[0522] Output: A set of collected driving data (e.g., 50 engine starts, 120 minutes with the lights on, 1500 km driven, etc.).

[0523] Specific operation: The terminal is installed in the vehicle, collects data from the ECU and sensors in real time, and stores it on the vehicle's storage media.

[0524] Step 2: Obtaining external information

[0525] The server obtains external information from weather information APIs and traffic information APIs via the Internet. Specifically, it collects data using the OpenWeatherMap API and Google Maps Traffic API.

[0526] Input: Requests to the Weather and Traffic APIs.

[0527] Output: Captured weather and traffic data.

[0528] Specific operation: The server periodically accesses the API to obtain current weather information (e.g., rain, slippery roads) and traffic information, and stores it as well-formatted data.

[0529] Step 3: Preprocessing the data

[0530] The server receives driving data sent from the device and external information it acquires, normalizes and preprocesses this data, adjusting each item of driving data to a uniform scale and converting it into a format used by the AI ​​model.

[0531] Input: Collected driving and external information data.

[0532] Output: A normalized dataset.

[0533] Specific operation: The server scales the data and performs processes such as "normalizing the number of engine starts to a range of 0 to 1" and "converting weather data into a numerical format."

[0534] Step 4: Wear and tear prediction

[0535] The server inputs the preprocessed data into a generative AI model to predict wear and tear for each part. The AI ​​model analyzes the wear and tear status based on the input data and returns the results to the server.

[0536] Input: The normalized dataset.

[0537] Output: Wear prediction results for each part.

[0538] Specific operation: An AI model trained with TensorFlow predicts the degree of engine oil deterioration, the degree of tire wear, etc., and calculates when to replace them.

[0539] Step 5: Maintenance schedule suggestions

[0540] The server notifies the user of the need for maintenance based on the wear prediction results received from the AI ​​model, and the notification message is sent to a smartphone app or an in-car display.

[0541] Input: Wear prediction results for each part.

[0542] Output: Maintenance suggestion notification to user.

[0543] Specific operation: The server generates a message such as "It is recommended to change the engine oil" and sends a push notification to the user's smartphone. The same information is also displayed on the car's display.

[0544] Step 6: Propose refueling points

[0545] The server calculates the current amount of gasoline remaining and the predicted consumption, and suggests the optimal refueling location to the user. The server also determines the need for refueling based on the distance to the destination.

[0546] Input: Current gasoline level, predicted consumption data.

[0547] Output: Refueling point suggestions to the user.

[0548] Specific operation: Based on the information that "the remaining distance to the next destination is 200 km and the current amount of gasoline is insufficient," the server suggests refueling points along the way.

[0549] Step 7: Provide feedback

[0550] The server provides the results of wear predictions to maintenance companies and dealers, allowing them to prepare the necessary parts and services in advance.

[0551] Input: Wear prediction results for each part.

[0552] Output: Feedback notification to maintenance companies and dealers.

[0553] Specific operation: The server sends a message to the repair shop saying "User XX's vehicle needs an engine oil change," and the repair shop prepares the parts and gets ready to provide service.

[0554] (Application example 1)

[0555] 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."

[0556] Conventional automobile maintenance systems often fail to fully utilize driving data and external information, resulting in inappropriate prediction of part wear and inappropriate suggestions for maintenance timing. Furthermore, the system's ability to suggest appropriate gas stations based on remaining fuel levels is insufficient, resulting in low user convenience. Furthermore, feedback provided to repair companies and dealers is ineffective, resulting in low maintenance efficiency. The present invention aims to solve these problems and support users in driving safely and efficiently.

[0557] 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.

[0558] In this invention, the server includes a means for collecting driving data, a means for acquiring external information, a means for predicting part wear based on the driving data and the external information, a means for suggesting maintenance times to the user based on the part wear prediction results, a means for suggesting gas stations based on the current fuel level and consumption, a means for providing feedback to maintenance companies and dealers based on the degree of maintenance necessity, a data normalization means for predicting wear using a generative AI model, and a means for notifying the user based on a prompt sentence. This makes it possible to appropriately utilize driving data and external information to predict part wear and accurately suggest maintenance times and gas stations to the user. Furthermore, by providing prompt and accurate feedback to maintenance companies and dealers, maintenance efficiency can be improved.

[0559] "Means for collecting driving data" refers to devices and systems for obtaining data related to the driving conditions of a vehicle.

[0560] "Means for acquiring external information" refers to techniques and methods for collecting information about the external environment, such as weather information, road surface conditions, and traffic information.

[0561] "Means for predicting part wear based on driving data and external information" refers to technology that uses driving data and collected external information to predict the deterioration and replacement timing of automobile parts.

[0562] "Means for proposing maintenance timing to users based on the results of part wear prediction" refers to technology that notifies and suggests appropriate maintenance timing to users based on the results of wear prediction.

[0563] "Means for suggesting gas stations based on the current remaining fuel amount and consumption amount" refers to technology that guides the user to the most suitable gas station based on the remaining fuel amount and the rate at which it is consumed.

[0564] "Means for providing feedback to repair companies and dealers based on the degree of maintenance required" refers to technology that provides necessary information to repair companies and dealers when the need for maintenance increases.

[0565] "Data normalization method for wear and tear prediction using generative AI models" refers to a technique that converts input data into a unified format so that the AI ​​model can function efficiently.

[0566] "User notification means based on prompt sentences" refers to a technology that appropriately notifies the user of necessary information based on defined questions or instruction sentences.

[0567] This invention is a system that collects and analyzes operational data and external information to predict the deterioration status of consumables and the timing of maintenance. A detailed description of this system is provided below.

[0568] Data collection

[0569] The device collects driving data from the vehicle's sensors. This data includes the number of times the engine was started and stopped, the duration the lights were on, the duration the wipers were on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. The device transmits this data in real time, for example, via Bluetooth or Wi-Fi. For example, the device can record that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance traveled was 1,500 km.

[0570] Obtaining external information

[0571] The server obtains external information via the Internet. This information includes weather information, road surface conditions, and traffic information. The server uses the OpenWeatherMap API for weather information and the Google Maps API for traffic information. For example, the server can obtain information that the current weather in the area is rainy and the roads are slippery.

[0572] Wear prediction

[0573] The server uses a generative AI model to predict wear and tear on each part based on collected driving data and external information. The data is normalized and input into an AI model using, for example, TensorFlow or PyTorch. This predicts when each part (e.g., engine oil, brake pads, tires) needs to be replaced. For example, the server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that it is soon time to replace the oil. It may also determine that tires are wearing out as a result of driving on slippery roads.

[0574] Maintenance schedule suggestions

[0575] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. For example, a message such as "We recommend changing your engine oil" or "We recommend checking your tires after the next 1000km of driving" is sent.

[0576] Refueling point suggestions

[0577] The server calculates the distance to the destination based on the current fuel remaining and consumption, and if refueling is required along the way, suggests an appropriate gas station. Based on the distance to the destination and the current location information, the server uses the Google Maps API to guide the user to nearby gas stations. As a specific example, if the user confirms that the next destination is 200 km away and the current gas level is insufficient, the server suggests an appropriate refueling point.

[0578] Providing Feedback

[0579] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare the necessary parts and maintenance in advance. For example, the server notifies a repair company that "User XX's vehicle needs an engine oil change," and the repair company prepares the necessary parts based on this information and provides the service.

[0580] Prompt Sentence Examples

[0581] "To predict vehicle maintenance, please predict engine oil deterioration based on the following driving data and external information: Number of engine starts: 50, Lights on for: 120 minutes, Wiper operation time: 30 minutes, Mileage: 1500 km, Weather information: Rain, Road conditions: Slippery. For output, please display the recommended engine oil change interval in Japanese."

[0582] In this way, the present invention provides a system that combines driving data and external information to predict the deterioration status of each part and notify the user of the appropriate maintenance timing. In addition, by providing the wear prediction results to maintenance companies, maintenance efficiency can be improved.

[0583] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0584] Step 1:

[0585] The terminal collects driving data from the vehicle. This driving data includes the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are operated, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Specifically, the terminal obtains this data from the vehicle's sensors using Bluetooth or Wi-Fi and transmits the data to the server in real time. The input data is the readings from the various sensors, and the output is the driving data sent to the server.

[0586] Step 2:

[0587] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. For example, the server obtains current weather information using the OpenWeatherMap API and traffic conditions using the Google Maps API. The input is a data request from the weather API or traffic information API, and the output is the obtained external information.

[0588] Step 3:

[0589] The server uses a generative AI model to predict wear and tear on each part based on the collected driving data and external information. Specifically, the driving data and external information are normalized and input into an AI model using TensorFlow and PyTorch. The AI ​​model uses this data to predict when to replace consumables such as engine oil, brake pads, and tires. The input is the normalized driving data and external information, and the output is the predicted replacement times for consumables.

[0590] Step 4:

[0591] The server will suggest maintenance times to the user based on the results of the wear prediction. Specifically, if it determines that maintenance is necessary based on the results of the wear prediction, it will send a notification message to the user using the smartphone's push notification function. The input is the wear prediction result, and the output is the notification message to the user.

[0592] Step 5:

[0593] The server calculates the distance to the destination based on the current fuel level and consumption, and if refueling is required along the way, suggests suitable gas stations. Specifically, it uses the Google Maps API to guide the driver to nearby gas stations based on the distance to the destination and the current location. The input is the current fuel level, consumption, location, and distance to the destination, and the output is information about suggested gas stations.

[0594] Step 6:

[0595] The server provides the results of wear prediction to maintenance companies and dealers. Specifically, it uses a REST API to send information about users who need to replace consumables to maintenance companies. The input is the wear prediction results and user information, and the output is a notification to the maintenance company. This allows maintenance companies to prepare the necessary parts in advance and provide services efficiently.

[0596] 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.

[0597] This invention combines a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance schedule of consumables with an emotion engine that recognizes user emotions. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that predicts wear and tear, a means for suggesting maintenance and gas stations to the user, and an emotion engine that recognizes user emotions and provides appropriate feedback. The program processing of this system is explained below in natural language.

[0598] Data collection

[0599] The device collects driving data from the vehicle, such as the number of engine starts and stops, the duration of headlights, the duration of wiper operation, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[0600] Example: The device records that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance driven was 1500 km. Furthermore, the device recognizes that the user is stressed while driving.

[0601] Obtaining external information

[0602] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[0603] Example: The server receives information that the current weather in the area is rainy and the roads are slippery. The server collects the user's emotional state as feedback and considers appropriate countermeasures.

[0604] Wear prediction

[0605] The server uses an AI model to predict wear and tear on each part based on collected driving data, external information, and the user's emotional state. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when each part (e.g., engine oil, brake pads, tires) should be replaced.

[0606] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that it is time to change the oil. It also determines that tires are wearing out as a result of driving on slippery roads. Furthermore, if the user's stress level is affecting the vehicle's wear and tear, the server will provide special attention.

[0607] Maintenance schedule suggestions

[0608] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. The emotion engine makes suggestions that take into account the user's emotional state.

[0609] Example: The server notifies the user that "It is recommended to change the engine oil." At the same time, it also notifies that "It is recommended to check the tires after the next 1000 km of driving." Furthermore, if the user is feeling stressed, it adds a suggestion that "It is recommended to take a break in a place where you can drive in a relaxed manner."

[0610] Refueling point suggestions

[0611] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[0612] Example: The server confirms that the user's next destination is 200 km away, and suggests an appropriate refueling point since the current amount of gasoline is insufficient. If the user feels impatient or anxious, the server suggests "We recommend refueling at the next safe location."

[0613] Providing Feedback

[0614] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare for necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[0615] Example: The server notifies the maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides service. If the user is feeling stressed, the server considers providing special service.

[0616] summary

[0617] The system's processing steps collect and analyze driving data and external information, and use an AI model to predict the wear and tear of each part. The system suggests optimal maintenance and refueling times to users, and provides necessary information to maintenance companies in advance. The integration of an emotion engine provides a safe and comfortable driving environment that takes into account the user's emotional state.

[0618] The processing flow will be explained below.

[0619] Step 1:

[0620] The device collects driving data.

[0621] Specifically, it automatically collects data from each sensor, such as the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.In addition, it uses an emotion engine to analyze the user's voice and recognize their face, and recognizes their emotional state (e.g., stress, anxiety, relaxation, etc.) in real time.

[0622] Example: The device records that the engine has been started 50 times, the lights have been on for 120 minutes, the wipers have been on for 30 minutes, and the distance traveled is 1500 km. In addition, the emotion engine recognizes that the user is feeling stressed while driving.

[0623] Step 2:

[0624] The terminal transmits the collected driving data and user emotion data to the server.

[0625] The data is periodically uploaded to a server using a secure communication protocol and is time-stamped to record the exact time of collection.

[0626] Example: The device sends the collected driving data and user emotion data on "stress state" to the server.

[0627] Step 3:

[0628] The server obtains external information via the Internet.

[0629] Specifically, weather information is obtained from a weather API, and road surface conditions and traffic information are obtained from a traffic information API. The obtained external information is also saved with a timestamp.

[0630] Example: The server retrieves the weather information for the current location, indicating that it is raining and the roads are slippery.

[0631] Step 4:

[0632] The server integrates driving data, external information, and user emotion data.

[0633] The acquired data is mapped onto the same time axis and preprocessed, specifically by filling in missing data, normalizing the data, and calculating correlations.

[0634] Example: A server integrates driving data, weather information, road information, and user sentiment data and prepares it for analysis.

[0635] Step 5:

[0636] The server inputs the preprocessed data into an AI model to predict part wear.

[0637] The AI ​​model uses machine learning algorithms to predict the wear and tear of each part. The model is pre-trained with a large amount of learning data. The prediction results include the wear and tear and replacement times for parts such as engine oil, brake pads, and tires.

[0638] Example: The server predicts that the engine oil is deteriorating quickly and needs to be replaced soon, and determines that the brake pads are wearing out due to frequent braking.

[0639] Step 6:

[0640] The server analyzes the prediction results from the AI ​​model and provides detailed feedback while taking into account the user's emotional state.

[0641] Based on the predicted replacement times for parts and user sentiment, an appropriate maintenance schedule is created and notified to the user.

[0642] Example: The server notifies the user that "it is recommended to change the engine oil" and also advises that "it is recommended to check the tires after the next 1000 km of driving." In addition, because the user is in a stressed state, it makes an additional suggestion that "it is recommended to take a break in a relaxing place."

[0643] Step 7:

[0644] The server calculates the distance to the destination based on the current fuel level and consumption.

[0645] It does this by using historical fuel consumption data and current fuel level data, and also takes into account the user's emotional state.

[0646] Example: The server recognizes that the user is heading to a destination 200 km away, and determines that the current fuel level is insufficient and that refueling is necessary along the way. If the user is feeling anxious or anxious, the server suggests safe refueling points.

[0647] Step 8:

[0648] The server suggests gas stations to the user.

[0649] The suggestions are displayed on a smartphone app or on an in-car display, and change depending on the user's emotional state.

[0650] Example: The server suggests "Please fill up at a gas station within the next 100 km" or, if the user is feeling impatient, notifies "Searching for a safe gas station."

[0651] Step 9:

[0652] The server provides feedback on the wear prediction results and user emotion data to maintenance companies and dealers.

[0653] This allows necessary parts and maintenance to be prepared in advance.

[0654] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change and the user is currently feeling stressed." The maintenance company uses this information to provide prompt and appropriate service.

[0655] Step 10:

[0656] The maintenance company prepares parts based on the feedback and provides the user with prompt maintenance.

[0657] The repair company will check the parts inventory and arrange for parts as needed, and will also respond appropriately depending on the user's emotional state.

[0658] Example: A maintenance company prepares engine oil and has all the necessary information ready before the user arrives. When the user arrives, they receive special treatment, such as a relaxing environment.

[0659] summary

[0660] The system's processing steps collect and analyze driving data, external information, and user emotional data, and use an AI model to predict the wear and tear of each part. The system suggests appropriate maintenance and refueling times to users, and provides necessary information to maintenance companies in advance. The integration of an emotional engine takes the user's emotional state into consideration, creating a safe and comfortable driving environment.

[0661] Example 2

[0662] 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."

[0663] Modern cars are equipped with many sensors and can collect a wide variety of data, but systems that effectively utilize this data and appropriately notify users of optimal maintenance and refueling times are not widely available. Furthermore, conventional systems do not take user emotions into account and do not provide appropriate feedback based on changes in stress and emotion. This can compromise user safety and comfort.

[0664] 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.

[0665] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for predicting parts wear based on the driving data, the external information, and the user's emotions, means for suggesting maintenance times to the user based on the parts wear prediction results, means for suggesting gas stations based on the current remaining fuel amount and consumption amount, and means for providing feedback to repair companies and dealers according to the degree of necessity for maintenance and the user's emotions. This makes it possible to propose optimal maintenance and refueling timings that take into account the user's emotions while utilizing the driving data and external information.

[0666] "Driving data" refers to data relating to the vehicle's operating state and driving conditions, and specifically includes the number of times the engine is started and stopped, the length of time the lights are on, the length of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, and the route traveled.

[0667] "External information" refers to information obtained via the Internet or external APIs, and specifically includes weather information, road surface conditions, traffic information, etc.

[0668] An "emotion engine" is a system that analyzes emotions from the user's voice, facial expressions, etc., and recognizes stress levels and changes in emotions.

[0669] "Wear prediction" involves predicting the deterioration status and replacement timing of vehicle parts (e.g., engine oil, brake pads, tires) based on collected driving data, external information, and the user's emotional state.

[0670] "Maintenance timing suggestion" means notifying the user when maintenance such as replacement or inspection of each vehicle part is required based on the wear prediction results.

[0671] "Fuel station suggestion" calculates the distance to the destination based on the current fuel remaining and consumption, and recommends appropriate fuel stations if refueling is required along the way.

[0672] "Providing feedback" means providing information to repair companies and dealers regarding vehicle maintenance and preparation of necessary parts based on wear prediction results and user emotion data.

[0673] An "AI model" refers to an artificial intelligence system that receives collected data as input and uses a learning algorithm to predict wear and tear.

[0674] "Data normalization" refers to converting collected data to a certain scale or format, making it suitable for input into an AI model.

[0675] This invention combines a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables with an emotion engine that recognizes user emotions. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that performs wear prediction, a means for suggesting maintenance and gas stations to the user, and an emotion engine that recognizes user emotions and provides appropriate feedback.

[0676] The device collects driving data from the vehicle in real time. The device is connected to a GPS module, engine control unit (ECU), and sensor array, and acquires data from these. Specifically, the device collects data such as the number of engine starts and stops, the duration of headlight illumination, the duration of wiper operation, the number and duration of accelerator and brake operation, mileage, and driving route. The device is also equipped with a camera and microphone, which are used to analyze the user's voice and facial expressions and activate an emotion engine that recognizes emotions. For example, the device acquires the number of engine starts from the engine control unit (ECU) and measures the mileage using the GPS module. The camera also captures the user's facial expressions in real time, and the emotion engine analyzes the user's stress level.

[0677] The server obtains external information via the Internet. This includes weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data. For example, the server sends a request to the weather forecast API to obtain weather information for the current location and destination. At the same time, it obtains information from the road API that the current road surface conditions have been updated to "slippery."

[0678] The server inputs collected driving data, external information, and the user's emotional state into the AI ​​model. The AI ​​model uses a wear prediction algorithm based on deep learning to predict the deterioration status and replacement timing of each part, such as engine oil, brake pads, and tires. At this time, the data is normalized and input into the AI ​​model. For example, the server supplies data to the AI ​​model, which predicts that "the engine oil needs to be changed in 500 km." It also takes into account road condition data and determines that the remaining mileage of the tires may be shortened.

[0679] The server notifies the user of the optimal maintenance timing based on the wear prediction results. This notification is sent to the smartphone app or in-car display. The emotion engine also makes suggestions that take the user's emotional state into account. For example, the server may notify the user's smartphone app, "It's almost time to change your engine oil. We recommend changing it within the next 500 km." Furthermore, if the server recognizes that the user is feeling stressed, it adds a message saying, "We also recommend taking a break in a relaxing place."

[0680] The server calculates the remaining distance to the destination based on the current amount of gasoline remaining and consumption, and suggests suitable gas stations if refueling is required along the way. This is also done by analyzing GPS data and route information to select the most efficient and safe refueling point. For example, based on the user's current location and remaining gasoline, the server might suggest, "You will run out of gas in the next 150 km. We recommend that the next refueling point be a service area 30 km away." If the user is in a hurry, it adds a comment saying, "We recommend refueling at the shortest distance."

[0681] Based on the wear prediction results and the user's emotional data, the server provides repair companies and dealers with information about vehicle maintenance and the preparation of necessary parts. This allows necessary parts and maintenance to be prepared in advance, allowing the user to receive service smoothly. For example, the server may notify a repair company that "User A's vehicle is nearing the time for an engine oil change. Please prepare the parts." Furthermore, based on the user's emotional data, the server may suggest that "The user is feeling stressed, so please consider providing service in a relaxed environment."

[0682] By utilizing this system, it is possible to effectively analyze driving data and external information, provide users with optimal maintenance and refueling timings, and improve services that reflect the user's emotional state.

[0683] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0684] Step 1: Data collection

[0685] The device collects various driving data from the vehicle in real time. It is connected to a GPS module, engine control unit (ECU), and various sensors, and acquires data from these devices. Specifically, it collects the number of engine starts and stops, the duration of headlight illumination, the duration of wiper operation, the number and duration of accelerator and brake operation, the distance traveled, and the route traveled. It also uses a camera and microphone to analyze the user's voice and facial expressions, and an emotion engine detects the user's stress level.

[0686] Input: In-vehicle devices (GPS module, ECU, various sensors), camera, microphone

[0687] Output: Driving data (mileage, number of engine starts, etc.), emotional data (stress level, etc.)

[0688] Specific operation: The device obtains the number of engine starts from the ECU, measures the mileage using the GPS module, captures the user's facial expressions in real time using the camera, and analyzes the user's stress level using the emotion engine.

[0689] Step 2: Obtaining external information

[0690] The server uses external APIs to obtain weather information, road surface conditions, and traffic information. Data is collected in real time using weather APIs and traffic information APIs.

[0691] Input: Weather API, Road API, Traffic API

[0692] Output: External information (weather information, road surface conditions, traffic conditions)

[0693] Specific operation: The server sends a request to the weather forecast API to obtain weather information for the current location and destination. At the same time, it obtains information from the road API that the current road conditions have been updated to "slippery."

[0694] Step 3: Wear and tear prediction

[0695] The server inputs the driving data collected in step 1, the external information obtained in step 2, and the user's emotional data into the AI ​​model. The AI ​​model uses deep learning to execute a wear prediction algorithm and predict the deterioration status and replacement timing of each part. The data is normalized and input into the AI ​​model.

[0696] Input: driving data, external information, emotion data

[0697] Output: Wear prediction results (engine oil change timing, tire wear status, etc.)

[0698] Specific operation: The server normalizes the collected data and inputs it into the AI ​​model. The AI ​​model analyzes the data and outputs a prediction result: "It's time to change the engine oil in 500 km."

[0699] Step 4: Maintenance schedule suggestions

[0700] The server notifies the user of the optimal maintenance period based on the wear prediction results. Maintenance suggestions are sent to the user's smartphone app or the in-car display. The emotion engine makes suggestions that take the user's emotional state into consideration.

[0701] Input: Wear prediction results, user emotion data

[0702] Output: Maintenance notification (smartphone app, in-car display)

[0703] Specific operation: The server notifies the user's smartphone app that "It's almost time to change the engine oil. We recommend changing it within the next 500 km." If the user is feeling stressed, the server adds a suggestion that "We also recommend taking a break in a relaxing place."

[0704] Step 5: Propose refueling points

[0705] The server calculates the remaining distance to the destination based on the current fuel level and consumption, and suggests suitable gas stations if refueling is required along the way. It analyzes GPS data and route information to select the optimal refueling point.

[0706] Input: Fuel level, consumption, GPS data, route information

[0707] Output: Refueling suggestion (location information of gas stations)

[0708] Specific operation: Based on the current location and remaining gasoline of the user's vehicle, the server suggests, "You will run out of gas in the next 150 km. We recommend that the next refueling point be a service area 30 km away." If the user is in a hurry, it adds a comment saying, "We recommend refueling at the shortest distance."

[0709] Step 6: Provide feedback

[0710] The server provides repair companies and dealers with information on maintenance and the preparation of necessary parts based on the wear prediction results and user emotion data, allowing the necessary parts and maintenance to be prepared in advance, ensuring smooth service for users.

[0711] Input: Wear prediction results, user emotion data

[0712] Output: Feedback information (notification to maintenance companies and dealers)

[0713] Specific operation: The server notifies the maintenance company that "User A's vehicle's engine oil is due for a change soon. Please prepare the parts." It also suggests that "The user is feeling stressed, so please consider providing the service in a relaxed environment."

[0714] (Application example 2)

[0715] 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."

[0716] Conventional car maintenance systems can predict part wear and suggest maintenance times based on driving data and external information, but they have the problem of not being able to provide feedback that takes into account the user's emotional state. This makes it difficult to reduce the user's stress and anxiety, and to provide a safe and comfortable driving environment.

[0717] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0718] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for predicting parts wear based on the driving data and the external information, means for suggesting maintenance times to the user based on the results of the parts wear prediction, means for suggesting gas stations based on the current remaining fuel level and fuel consumption, means for providing feedback to a maintenance company or dealer according to the degree of need for maintenance, and means for recognizing the user's emotional state and providing appropriate feedback. This provides feedback that takes the user's emotional state into consideration, enabling a safe and comfortable driving environment.

[0719] "Driving data" refers to information about the driving conditions of a vehicle, such as the number of times the engine is started and stopped, the length of time the lights are on, the length of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, and the route traveled.

[0720] "External information" refers to information related to the driving environment of the vehicle, specifically weather information, road surface conditions, traffic information, and the like.

[0721] "Parts wear prediction" refers to predicting the deterioration status and replacement timing of each part of a vehicle (e.g., engine oil, brake pads, tires, etc.) based on driving data and external information.

[0722] "Maintenance timing suggestion" refers to the process of notifying the user of the timing for replacement or inspection of each part of the car based on the results of part wear prediction.

[0723] "Suggesting gas stations" refers to a process of specifying and suggesting gas stations that the user should stop at to refuel based on the current remaining fuel amount and fuel consumption.

[0724] "Providing feedback" means notifying repair shops and dealers of the necessary information depending on the degree of maintenance required, and encouraging them to prepare the appropriate service and parts.

[0725] "Means for recognizing emotional states" refers to technology that recognizes a user's emotional states, such as stress, impatience, and anxiety, by analyzing the user's voice and facial expressions.

[0726] The "means for providing appropriate feedback" refers to a process of providing advice or suggestions to reduce the user's stress or anxiety based on the user's emotional state.

[0727] System Configuration

[0728] This invention is a system including means for collecting driving data, means for acquiring external information, means for predicting part wear based on the driving data and external information, means for suggesting maintenance times to the user based on the results of the part wear prediction, means for suggesting gas stations based on the current remaining fuel level and consumption, means for providing feedback to maintenance companies and dealers according to the degree of need for maintenance, and means for recognizing the emotional state of the user and providing appropriate feedback.

[0729] Data collection

[0730] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[0731] Obtaining external information

[0732] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[0733] Wear prediction

[0734] The server uses an AI model to predict wear and tear on each part based on collected driving data, external information, and the user's emotional state. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when each part (e.g., engine oil, brake pads, tires) should be replaced.

[0735] Maintenance schedule suggestions

[0736] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. The emotion engine makes suggestions that take into account the user's emotional state.

[0737] Refueling point suggestions

[0738] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[0739] Providing Feedback

[0740] The server provides the results of wear predictions to repair shops and dealers, allowing them to prepare necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[0741] Specific examples

[0742] For example, a device might record that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the mileage was 1,500 km. Furthermore, the device might recognize that the user is feeling stressed while driving. The server might also acquire information that the current local weather is rainy and the roads are slippery. Furthermore, the server might predict that frequent engine starts and stops will accelerate engine oil deterioration and notify the user that the oil is due for replacement. It might also determine that driving on slippery roads has accelerated tire wear. Furthermore, if the user's stress level is affecting the vehicle's wear, the device might urge the user to take special precautions. Based on this information, the server might notify the user that "it is recommended to change the engine oil" and, at the same time, that "it is recommended to check the tires after the next 1,000 km of driving." Furthermore, if the user is feeling stressed, the server might add a suggestion that "it is recommended to take a break in a place where you can relax while driving."

[0743] Prompt Sentence Examples

[0744] Describe an assistant application that identifies the stress level a user experiences while driving and, based on that, suggests appropriate relaxation or resting spots.

[0745] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0746] Step 1:

[0747] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[0748] *Input: various sensor data from the car, user's voice and facial expressions

[0749] * Output: Driving data and user's emotional state

[0750] Step 2:

[0751] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[0752] *Input: Data from weather API and traffic information API

[0753] * Output: Weather information, road surface conditions, traffic information

[0754] Step 3:

[0755] The server normalizes the collected driving data and external information and inputs it into an AI model. The AI ​​model uses this data to predict wear and tear on each part. Specifically, driving data (number of engine starts and stops, light on time, etc.) and external information (weather, road conditions, etc.) are input, normalized, and the AI ​​model predicts part deterioration.

[0756] *Input: operation data, external information

[0757] * Output: Part wear prediction results

[0758] Step 4:

[0759] The server then proposes maintenance times to the user based on the wear prediction results. Specifically, it sends a notification message to the user's smartphone or in-car display. The emotion engine makes proposals that take into account the user's emotional state.

[0760] *Input: wear prediction results, user's emotional state

[0761] * Output: Maintenance time suggestion message

[0762] Step 5:

[0763] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[0764] *Input: current remaining gasoline, consumption, driving distance, user's emotional state

[0765] * Output: Gas station suggestion message

[0766] Step 6:

[0767] The server provides the results of wear predictions to repair shops and dealers, allowing them to prepare necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[0768] *Input: wear prediction results, user's emotional state

[0769] * Output: Feedback information for repair shops and dealers

[0770] 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.

[0771] 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.

[0772] 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.

[0773] [Third embodiment]

[0774] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0775] 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.

[0776] 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).

[0777] 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.

[0778] 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.

[0779] 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).

[0780] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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."

[0786] This invention is a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that performs wear prediction, and means for suggesting maintenance and gas stations to users. The program processing of this system is explained below in natural language.

[0787] Data collection

[0788] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are in operation, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.

[0789] Example: The device records that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance traveled was 1500 km.

[0790] Obtaining external information

[0791] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[0792] Example: A server receives information that the current local weather is rainy and road conditions are slippery.

[0793] Wear prediction

[0794] The server uses an AI model to predict wear and tear on each part based on collected driving data and external information. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when to replace each part (e.g., engine oil, brake pads, tires).

[0795] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that the oil is due for replacement. It also determines that tires are worn out as a result of driving on slippery roads.

[0796] Maintenance schedule suggestions

[0797] The server then recommends maintenance times to the user based on the wear prediction results, and a notification message is sent to the smartphone app or on the in-car display.

[0798] Example: The server notifies the user that "it is recommended to change the engine oil" and also that "it is recommended to check the tires after the next 1000 km of driving."

[0799] Refueling point suggestions

[0800] The server calculates the distance to the destination based on the current amount of gasoline remaining and consumption, and if refueling is required along the way, it suggests appropriate gas stations.

[0801] Example: The server determines that the user's next destination is 200 km away and suggests suitable refueling points since the current amount of gasoline is insufficient.

[0802] Providing Feedback

[0803] The server provides the results of wear predictions to maintenance companies and dealers, allowing them to prepare the necessary parts and maintenance in advance.

[0804] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides the service.

[0805] summary

[0806] This system collects and analyzes vehicle driving data and external information to predict wear and tear on each part, and by suggesting appropriate maintenance and refueling times to the user and providing feedback to maintenance companies, it supports efficient maintenance and safe driving.

[0807] The processing flow will be explained below.

[0808] Step 1:

[0809] The device collects driving data.

[0810] Specifically, the data collected includes the number of times the engine is started and stopped, the duration of time the lights are on, the duration of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, the route traveled, etc. This data is collected automatically via on-board sensors and GPS.

[0811] Step 2:

[0812] The driving data collected by the terminal is periodically sent to the server.

[0813] The data is uploaded to a server over the internet using a secure communication protocol, with precise timestamps attached to the data and the order in which it was collected maintained.

[0814] Step 3:

[0815] The server obtains external information via the Internet.

[0816] Specifically, weather information is obtained from a weather API, and road surface and traffic conditions are obtained from a traffic information API. The obtained external information is also saved with a timestamp.

[0817] Step 4:

[0818] The server receives and integrates driving data and external information.

[0819] The acquired data is mapped onto the same time axis and preprocessed, for example, by filling in missing data and normalizing the data.

[0820] Step 5:

[0821] The server inputs the preprocessed data into the AI ​​model.

[0822] The AI ​​model predicts the wear and tear of each part based on a machine learning algorithm, which has been trained in advance using a large amount of learning data.

[0823] Step 6:

[0824] The server analyzes the prediction results from the AI ​​model and calculates the wear and tear and replacement time for each part.

[0825] For example, the deterioration level of engine oil and the state of tire wear are output as numerical values, and the next maintenance schedule is determined based on these.

[0826] Step 7:

[0827] The server will suggest maintenance times and necessary part replacements to the user.

[0828] The recommendations are sent to a smartphone app or on the in-car display, and include specific replacement times and the recommended date and time for the next inspection.

[0829] Step 8:

[0830] The user confirms the proposed maintenance.

[0831] The user checks the maintenance schedule and makes a reservation if necessary.

[0832] Step 9:

[0833] The server calculates the distance to the destination based on the current fuel level and consumption.

[0834] This uses historical fuel consumption data and current fuel remaining data.

[0835] Step 10:

[0836] The server suggests gas stations.

[0837] Taking into consideration the route to the destination, if refueling is required along the way, appropriate refueling stations are suggested to the user.

[0838] Step 11:

[0839] The server provides feedback to the repair company or dealer.

[0840] It provides advance notification of predicted maintenance and required parts, allowing maintenance companies to make appropriate preparations.

[0841] Step 12:

[0842] A maintenance company prepares parts based on the notified feedback, and provides the user with prompt maintenance.

[0843] The maintenance company checks the parts inventory and arranges for the necessary parts.

[0844] summary

[0845] The system's processing steps collect and analyze driving data and external information, and use an AI model to predict the wear and tear of each part. Optimal maintenance and refueling times are suggested to users, and necessary information is provided to maintenance companies in advance. This ensures efficient and safe vehicle maintenance.

[0846] Example 1

[0847] 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."

[0848] Conventional technology did not offer a system that efficiently collected vehicle driving data and external information, analyzed them, and then suggested appropriate maintenance and refueling timings. This made it difficult for users to perform maintenance at the appropriate time, resulting in increased wear and tear on the vehicle and increased risk of breakdowns. Furthermore, it was difficult for repair companies and dealers to prepare the necessary parts and services in advance, creating a need for more efficient maintenance.

[0849] 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.

[0850] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for preprocessing data based on the driving data and the external information, means for predicting wear based on the results of the data preprocessing, means for suggesting maintenance times to the user based on the results of the part wear prediction, means for suggesting refueling locations based on the remaining amount of fuel and the amount of fuel consumed, and means for providing feedback to repair companies and dealers according to the degree of maintenance necessity. This allows the user to perform maintenance and refueling at the appropriate time, reducing wear and tear on the vehicle and the risk of breakdown, and also allows repair companies and dealers to prepare necessary parts in advance, thereby improving maintenance efficiency.

[0851] "Driving data" refers to information relating to the vehicle's driving state and operating conditions.

[0852] "External information" refers to information about the external environment of the vehicle, such as weather and traffic conditions.

[0853] "Data preprocessing" refers to the process of analyzing and normalizing collected operational data and external information, and converting them into a format suitable for analysis and predictive models.

[0854] "Wear prediction" is the prediction of the deterioration state and replacement time of each vehicle part based on processed data.

[0855] The "means for proposing the timing of maintenance" is to notify the user of the appropriate timing of maintenance based on the predicted wear data.

[0856] The "means for suggesting a refueling location" is to suggest the most suitable refueling location to the user based on the current remaining amount of fuel and the predicted fuel consumption.

[0857] The "means for providing feedback" refers to providing the results of wear prediction to maintenance companies and dealers, enabling them to prepare the necessary parts and services in advance.

[0858] An "artificial intelligence model" is a computer algorithm that analyzes and learns from multiple data sets to recognize and predict patterns.

[0859] MODE FOR CARRYING OUT THE INVENTION

[0860] This invention is a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables. This system includes a terminal for collecting driving data, a server for acquiring external information, an AI model for predicting wear, a means for making maintenance suggestions to users, and a means for suggesting gas stations.

[0861] Data collection

[0862] The device collects driving data from the vehicle's engine control unit (ECU) and various sensors, including the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. The collected data is then stored on the vehicle's onboard storage media.

[0863] Example: The device connects to the vehicle's ECU and records 50 engine starts and stops, 120 minutes of headlight time, 30 minutes of windshield wiper time, and 1,500 km of driving distance.

[0864] Obtaining external information

[0865] The server obtains the necessary external information from weather information APIs and traffic information APIs via the Internet. This includes weather information, road surface conditions, traffic information, etc. Specifically, data can be obtained using the OpenWeatherMap API and Google Maps Traffic API.

[0866] Example: A server receives information that the current local weather is rainy and road conditions are slippery.

[0867] Data Preprocessing

[0868] The server receives driving data sent from the terminal and external information it acquires, and preprocesses them. Data preprocessing involves analyzing and normalizing the collected data and converting it into a format suitable for analysis and predictive models.

[0869] Example: The server normalizes each item of driving data (e.g., number of engine starts and distance traveled) to a uniform scale, and similarly normalizes weather and traffic data.

[0870] Wear prediction

[0871] The server inputs the preprocessed data into a generative AI model (e.g., a model trained with TensorFlow or PyTorch) to predict wear and tear for each part. The AI ​​model predicts wear and tear based on the collected data and returns the results to the server.

[0872] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that the oil is due for replacement. It also determines that tires are worn out as a result of driving on slippery roads.

[0873] Maintenance schedule suggestions

[0874] The server notifies the user of the need for maintenance based on the wear prediction results received from the AI ​​model, and the notification message is sent to a smartphone app or an in-car display.

[0875] Example: The server notifies the user that "it is recommended to change the engine oil" and also that "it is recommended to check the tires after the next 1000 km of driving."

[0876] Refueling point suggestions

[0877] The server calculates the current amount of gasoline remaining and the predicted consumption, and suggests appropriate refueling points based on the remaining distance to the destination.

[0878] Example: The server determines that the user's next destination is 200 km away and suggests refueling stops along the way, since the current amount of gasoline is insufficient.

[0879] Providing Feedback

[0880] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare for necessary parts and maintenance in advance.

[0881] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides the service.

[0882] Prompt Sentence Examples

[0883] Here are some example prompts to input to a generative AI model:

[0884] Please explain in detail the step-by-step program process for a system that predicts the deterioration status of a vehicle's consumables based on the following information:

[0885] Engine start / stop count: 50 times

[0886] Light duration: 120 minutes

[0887] Wiper operation time: 30 minutes

[0888] Mileage: 1500km

[0889] Weather information: rain

[0890] Road Condition: Slippery

[0891] Based on this information, please explain in detail the process of predicting when to change engine oil or tires and providing maintenance suggestions to the user.

[0892] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0893] Step 1: Collect driving data

[0894] The device collects driving data from the vehicle's engine control unit (ECU) and various sensors. The device is connected to the vehicle's ECU and obtains data such as the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.

[0895] Input: Raw data from various vehicle sensors and ECUs.

[0896] Output: A set of collected driving data (e.g., 50 engine starts, 120 minutes with the lights on, 1500 km driven, etc.).

[0897] Specific operation: The terminal is installed in the vehicle, collects data from the ECU and sensors in real time, and stores it on the vehicle's storage media.

[0898] Step 2: Obtaining external information

[0899] The server obtains external information from weather information APIs and traffic information APIs via the Internet. Specifically, it collects data using the OpenWeatherMap API and Google Maps Traffic API.

[0900] Input: Requests to the Weather and Traffic APIs.

[0901] Output: Captured weather and traffic data.

[0902] Specific operation: The server periodically accesses the API to obtain current weather information (e.g., rain, slippery roads) and traffic information, and stores it as well-formatted data.

[0903] Step 3: Preprocessing the data

[0904] The server receives driving data sent from the device and external information it acquires, normalizes and preprocesses this data, adjusting each item of driving data to a uniform scale and converting it into a format used by the AI ​​model.

[0905] Input: Collected driving and external information data.

[0906] Output: A normalized dataset.

[0907] Specific operation: The server scales the data and performs processes such as "normalizing the number of engine starts to a range of 0 to 1" and "converting weather data into a numerical format."

[0908] Step 4: Wear and tear prediction

[0909] The server inputs the preprocessed data into a generative AI model to predict wear and tear for each part. The AI ​​model analyzes the wear and tear status based on the input data and returns the results to the server.

[0910] Input: The normalized dataset.

[0911] Output: Wear prediction results for each part.

[0912] Specific operation: An AI model trained with TensorFlow predicts the degree of engine oil deterioration, the degree of tire wear, etc., and calculates when to replace them.

[0913] Step 5: Maintenance schedule suggestions

[0914] The server notifies the user of the need for maintenance based on the wear prediction results received from the AI ​​model, and the notification message is sent to a smartphone app or an in-car display.

[0915] Input: Wear prediction results for each part.

[0916] Output: Maintenance suggestion notification to user.

[0917] Specific operation: The server generates a message such as "It is recommended to change the engine oil" and sends a push notification to the user's smartphone. The same information is also displayed on the car's display.

[0918] Step 6: Propose refueling points

[0919] The server calculates the current amount of gasoline remaining and the predicted consumption, and suggests the optimal refueling location to the user. The server also determines the need for refueling based on the distance to the destination.

[0920] Input: Current gasoline level, predicted consumption data.

[0921] Output: Refueling point suggestions to the user.

[0922] Specific operation: Based on the information that "the remaining distance to the next destination is 200 km and the current amount of gasoline is insufficient," the server suggests refueling points along the way.

[0923] Step 7: Provide feedback

[0924] The server provides the results of wear predictions to maintenance companies and dealers, allowing them to prepare the necessary parts and services in advance.

[0925] Input: Wear prediction results for each part.

[0926] Output: Feedback notification to maintenance companies and dealers.

[0927] Specific operation: The server sends a message to the repair shop saying "User XX's vehicle needs an engine oil change," and the repair shop prepares the parts and gets ready to provide service.

[0928] (Application example 1)

[0929] 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."

[0930] Conventional automobile maintenance systems often fail to fully utilize driving data and external information, resulting in inappropriate prediction of part wear and inappropriate suggestions for maintenance timing. Furthermore, the system's ability to suggest appropriate gas stations based on remaining fuel levels is insufficient, resulting in low user convenience. Furthermore, feedback provided to repair companies and dealers is ineffective, resulting in low maintenance efficiency. The present invention aims to solve these problems and support users in driving safely and efficiently.

[0931] 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.

[0932] In this invention, the server includes a means for collecting driving data, a means for acquiring external information, a means for predicting part wear based on the driving data and the external information, a means for suggesting maintenance times to the user based on the part wear prediction results, a means for suggesting gas stations based on the current fuel level and consumption, a means for providing feedback to maintenance companies and dealers based on the degree of maintenance necessity, a data normalization means for predicting wear using a generative AI model, and a means for notifying the user based on a prompt sentence. This makes it possible to appropriately utilize driving data and external information to predict part wear and accurately suggest maintenance times and gas stations to the user. Furthermore, by providing prompt and accurate feedback to maintenance companies and dealers, maintenance efficiency can be improved.

[0933] "Means for collecting driving data" refers to devices and systems for obtaining data related to the driving conditions of a vehicle.

[0934] "Means for acquiring external information" refers to techniques and methods for collecting information about the external environment, such as weather information, road surface conditions, and traffic information.

[0935] "Means for predicting part wear based on driving data and external information" refers to technology that uses driving data and collected external information to predict the deterioration and replacement timing of automobile parts.

[0936] "Means for proposing maintenance timing to users based on the results of part wear prediction" refers to technology that notifies and suggests appropriate maintenance timing to users based on the results of wear prediction.

[0937] "Means for suggesting gas stations based on the current remaining fuel amount and consumption amount" refers to technology that guides the user to the most suitable gas station based on the remaining fuel amount and the rate at which it is consumed.

[0938] "Means for providing feedback to repair companies and dealers based on the degree of maintenance required" refers to technology that provides necessary information to repair companies and dealers when the need for maintenance increases.

[0939] "Data normalization method for wear and tear prediction using generative AI models" refers to a technique that converts input data into a unified format so that the AI ​​model can function efficiently.

[0940] "User notification means based on prompt sentences" refers to a technology that appropriately notifies the user of necessary information based on defined questions or instruction sentences.

[0941] This invention is a system that collects and analyzes operational data and external information to predict the deterioration status of consumables and the timing of maintenance. A detailed description of this system is provided below.

[0942] Data collection

[0943] The device collects driving data from the vehicle's sensors. This data includes the number of times the engine was started and stopped, the duration the lights were on, the duration the wipers were on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. The device transmits this data in real time, for example, via Bluetooth or Wi-Fi. For example, the device can record that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance traveled was 1,500 km.

[0944] Obtaining external information

[0945] The server obtains external information via the Internet. This information includes weather information, road surface conditions, and traffic information. The server uses the OpenWeatherMap API for weather information and the Google Maps API for traffic information. For example, the server can obtain information that the current weather in the area is rainy and the roads are slippery.

[0946] Wear prediction

[0947] The server uses a generative AI model to predict wear and tear on each part based on collected driving data and external information. The data is normalized and input into an AI model using, for example, TensorFlow or PyTorch. This predicts when each part (e.g., engine oil, brake pads, tires) needs to be replaced. For example, the server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that it is soon time to replace the oil. It may also determine that tires are wearing out as a result of driving on slippery roads.

[0948] Maintenance schedule suggestions

[0949] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. For example, a message such as "We recommend changing your engine oil" or "We recommend checking your tires after the next 1000km of driving" is sent.

[0950] Refueling point suggestions

[0951] The server calculates the distance to the destination based on the current fuel remaining and consumption, and if refueling is required along the way, suggests an appropriate gas station. Based on the distance to the destination and the current location information, the server uses the Google Maps API to guide the user to nearby gas stations. As a specific example, if the user confirms that the next destination is 200 km away and the current gas level is insufficient, the server suggests an appropriate refueling point.

[0952] Providing Feedback

[0953] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare the necessary parts and maintenance in advance. For example, the server notifies a repair company that "User XX's vehicle needs an engine oil change," and the repair company prepares the necessary parts based on this information and provides the service.

[0954] Prompt Sentence Examples

[0955] "To predict vehicle maintenance, please predict engine oil deterioration based on the following driving data and external information: Number of engine starts: 50, Lights on for: 120 minutes, Wiper operation time: 30 minutes, Mileage: 1500 km, Weather information: Rain, Road conditions: Slippery. For output, please display the recommended engine oil change interval in Japanese."

[0956] In this way, the present invention provides a system that combines driving data and external information to predict the deterioration status of each part and notify the user of the appropriate maintenance timing. In addition, by providing the wear prediction results to maintenance companies, maintenance efficiency can be improved.

[0957] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0958] Step 1:

[0959] The terminal collects driving data from the vehicle. This driving data includes the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are operated, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Specifically, the terminal obtains this data from the vehicle's sensors using Bluetooth or Wi-Fi and transmits the data to the server in real time. The input data is the readings from the various sensors, and the output is the driving data sent to the server.

[0960] Step 2:

[0961] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. For example, the server obtains current weather information using the OpenWeatherMap API and traffic conditions using the Google Maps API. The input is a data request from the weather API or traffic information API, and the output is the obtained external information.

[0962] Step 3:

[0963] The server uses a generative AI model to predict wear and tear on each part based on the collected driving data and external information. Specifically, the driving data and external information are normalized and input into an AI model using TensorFlow and PyTorch. The AI ​​model uses this data to predict when to replace consumables such as engine oil, brake pads, and tires. The input is the normalized driving data and external information, and the output is the predicted replacement times for consumables.

[0964] Step 4:

[0965] The server will suggest maintenance times to the user based on the results of the wear prediction. Specifically, if it determines that maintenance is necessary based on the results of the wear prediction, it will send a notification message to the user using the smartphone's push notification function. The input is the wear prediction result, and the output is the notification message to the user.

[0966] Step 5:

[0967] The server calculates the distance to the destination based on the current fuel level and consumption, and if refueling is required along the way, suggests suitable gas stations. Specifically, it uses the Google Maps API to guide the driver to nearby gas stations based on the distance to the destination and the current location. The input is the current fuel level, consumption, location, and distance to the destination, and the output is information about suggested gas stations.

[0968] Step 6:

[0969] The server provides the results of wear prediction to maintenance companies and dealers. Specifically, it uses a REST API to send information about users who need to replace consumables to maintenance companies. The input is the wear prediction results and user information, and the output is a notification to the maintenance company. This allows maintenance companies to prepare the necessary parts in advance and provide services efficiently.

[0970] 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.

[0971] This invention combines a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance schedule of consumables with an emotion engine that recognizes user emotions. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that predicts wear and tear, a means for suggesting maintenance and gas stations to the user, and an emotion engine that recognizes user emotions and provides appropriate feedback. The program processing of this system is explained below in natural language.

[0972] Data collection

[0973] The device collects driving data from the vehicle, such as the number of engine starts and stops, the duration of headlights, the duration of wiper operation, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[0974] Example: The device records that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance driven was 1500 km. Furthermore, the device recognizes that the user is stressed while driving.

[0975] Obtaining external information

[0976] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[0977] Example: The server receives information that the current weather in the area is rainy and the roads are slippery. The server collects the user's emotional state as feedback and considers appropriate countermeasures.

[0978] Wear prediction

[0979] The server uses an AI model to predict wear and tear on each part based on collected driving data, external information, and the user's emotional state. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when each part (e.g., engine oil, brake pads, tires) should be replaced.

[0980] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that it is time to change the oil. It also determines that tires are wearing out as a result of driving on slippery roads. Furthermore, if the user's stress level is affecting the vehicle's wear and tear, the server will provide special attention.

[0981] Maintenance schedule suggestions

[0982] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. The emotion engine makes suggestions that take into account the user's emotional state.

[0983] Example: The server notifies the user that "It is recommended to change the engine oil." At the same time, it also notifies that "It is recommended to check the tires after the next 1000 km of driving." Furthermore, if the user is feeling stressed, it adds a suggestion that "It is recommended to take a break in a place where you can drive in a relaxed manner."

[0984] Refueling point suggestions

[0985] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[0986] Example: The server confirms that the user's next destination is 200 km away, and suggests an appropriate refueling point since the current amount of gasoline is insufficient. If the user feels impatient or anxious, the server suggests "We recommend refueling at the next safe location."

[0987] Providing Feedback

[0988] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare for necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[0989] Example: The server notifies the maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides service. If the user is feeling stressed, the server considers providing special service.

[0990] summary

[0991] The system's processing steps collect and analyze driving data and external information, and use an AI model to predict the wear and tear of each part. The system suggests optimal maintenance and refueling times to users, and provides necessary information to maintenance companies in advance. The integration of an emotion engine provides a safe and comfortable driving environment that takes into account the user's emotional state.

[0992] The processing flow will be explained below.

[0993] Step 1:

[0994] The device collects driving data.

[0995] Specifically, it automatically collects data from each sensor, such as the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.In addition, it uses an emotion engine to analyze the user's voice and recognize their face, and recognizes their emotional state (e.g., stress, anxiety, relaxation, etc.) in real time.

[0996] Example: The device records that the engine has been started 50 times, the lights have been on for 120 minutes, the wipers have been on for 30 minutes, and the distance traveled is 1500 km. In addition, the emotion engine recognizes that the user is feeling stressed while driving.

[0997] Step 2:

[0998] The terminal transmits the collected driving data and user emotion data to the server.

[0999] The data is periodically uploaded to a server using a secure communication protocol and is time-stamped to record the exact time of collection.

[1000] Example: The device sends the collected driving data and user emotion data on "stress state" to the server.

[1001] Step 3:

[1002] The server obtains external information via the Internet.

[1003] Specifically, weather information is obtained from a weather API, and road surface conditions and traffic information are obtained from a traffic information API. The obtained external information is also saved with a timestamp.

[1004] Example: The server retrieves the weather information for the current location, indicating that it is raining and the roads are slippery.

[1005] Step 4:

[1006] The server integrates driving data, external information, and user emotion data.

[1007] The acquired data is mapped onto the same time axis and preprocessed, specifically by filling in missing data, normalizing the data, and calculating correlations.

[1008] Example: A server integrates driving data, weather information, road information, and user sentiment data and prepares it for analysis.

[1009] Step 5:

[1010] The server inputs the preprocessed data into an AI model to predict part wear.

[1011] The AI ​​model uses machine learning algorithms to predict the wear and tear of each part. The model is pre-trained with a large amount of learning data. The prediction results include the wear and tear and replacement times for parts such as engine oil, brake pads, and tires.

[1012] Example: The server predicts that the engine oil is deteriorating quickly and needs to be replaced soon, and determines that the brake pads are wearing out due to frequent braking.

[1013] Step 6:

[1014] The server analyzes the prediction results from the AI ​​model and provides detailed feedback while taking into account the user's emotional state.

[1015] Based on the predicted replacement times for parts and user sentiment, an appropriate maintenance schedule is created and notified to the user.

[1016] Example: The server notifies the user that "it is recommended to change the engine oil" and also advises that "it is recommended to check the tires after the next 1000 km of driving." In addition, because the user is in a stressed state, it makes an additional suggestion that "it is recommended to take a break in a relaxing place."

[1017] Step 7:

[1018] The server calculates the distance to the destination based on the current fuel level and consumption.

[1019] It does this by using historical fuel consumption data and current fuel level data, and also takes into account the user's emotional state.

[1020] Example: The server recognizes that the user is heading to a destination 200 km away, and determines that the current fuel level is insufficient and that refueling is necessary along the way. If the user is feeling anxious or anxious, the server suggests safe refueling points.

[1021] Step 8:

[1022] The server suggests gas stations to the user.

[1023] The suggestions are displayed on a smartphone app or on an in-car display, and change depending on the user's emotional state.

[1024] Example: The server suggests "Please fill up at a gas station within the next 100 km" or, if the user is feeling impatient, notifies "Searching for a safe gas station."

[1025] Step 9:

[1026] The server provides feedback on the wear prediction results and user emotion data to maintenance companies and dealers.

[1027] This allows necessary parts and maintenance to be prepared in advance.

[1028] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change and the user is currently feeling stressed." The maintenance company uses this information to provide prompt and appropriate service.

[1029] Step 10:

[1030] The maintenance company prepares parts based on the feedback and provides the user with prompt maintenance.

[1031] The repair company will check the parts inventory and arrange for parts as needed, and will also respond appropriately depending on the user's emotional state.

[1032] Example: A maintenance company prepares engine oil and has all the necessary information ready before the user arrives. When the user arrives, they receive special treatment, such as a relaxing environment.

[1033] summary

[1034] The system's processing steps collect and analyze driving data, external information, and user emotional data, and use an AI model to predict the wear and tear of each part. The system suggests appropriate maintenance and refueling times to users, and provides necessary information to maintenance companies in advance. The integration of an emotional engine takes the user's emotional state into consideration, creating a safe and comfortable driving environment.

[1035] Example 2

[1036] 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."

[1037] Modern cars are equipped with many sensors and can collect a wide variety of data, but systems that effectively utilize this data and appropriately notify users of optimal maintenance and refueling times are not widely available. Furthermore, conventional systems do not take user emotions into account and do not provide appropriate feedback based on changes in stress and emotion. This can compromise user safety and comfort.

[1038] 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.

[1039] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for predicting parts wear based on the driving data, the external information, and the user's emotions, means for suggesting maintenance times to the user based on the parts wear prediction results, means for suggesting gas stations based on the current remaining fuel amount and consumption amount, and means for providing feedback to repair companies and dealers according to the degree of necessity for maintenance and the user's emotions. This makes it possible to propose optimal maintenance and refueling timings that take into account the user's emotions while utilizing the driving data and external information.

[1040] "Driving data" refers to data relating to the vehicle's operating state and driving conditions, and specifically includes the number of times the engine is started and stopped, the length of time the lights are on, the length of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, and the route traveled.

[1041] "External information" refers to information obtained via the Internet or external APIs, and specifically includes weather information, road surface conditions, traffic information, etc.

[1042] An "emotion engine" is a system that analyzes emotions from the user's voice, facial expressions, etc., and recognizes stress levels and changes in emotions.

[1043] "Wear prediction" involves predicting the deterioration status and replacement timing of vehicle parts (e.g., engine oil, brake pads, tires) based on collected driving data, external information, and the user's emotional state.

[1044] "Maintenance timing suggestion" means notifying the user when maintenance such as replacement or inspection of each vehicle part is required based on the wear prediction results.

[1045] "Fuel station suggestion" calculates the distance to the destination based on the current fuel remaining and consumption, and recommends appropriate fuel stations if refueling is required along the way.

[1046] "Providing feedback" means providing information to repair companies and dealers regarding vehicle maintenance and preparation of necessary parts based on wear prediction results and user emotion data.

[1047] An "AI model" refers to an artificial intelligence system that receives collected data as input and uses a learning algorithm to predict wear and tear.

[1048] "Data normalization" refers to converting collected data to a certain scale or format, making it suitable for input into an AI model.

[1049] This invention combines a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables with an emotion engine that recognizes user emotions. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that performs wear prediction, a means for suggesting maintenance and gas stations to the user, and an emotion engine that recognizes user emotions and provides appropriate feedback.

[1050] The device collects driving data from the vehicle in real time. The device is connected to a GPS module, engine control unit (ECU), and sensor array, and acquires data from these. Specifically, the device collects data such as the number of engine starts and stops, the duration of headlight illumination, the duration of wiper operation, the number and duration of accelerator and brake operation, mileage, and driving route. The device is also equipped with a camera and microphone, which are used to analyze the user's voice and facial expressions and activate an emotion engine that recognizes emotions. For example, the device acquires the number of engine starts from the engine control unit (ECU) and measures the mileage using the GPS module. The camera also captures the user's facial expressions in real time, and the emotion engine analyzes the user's stress level.

[1051] The server obtains external information via the Internet. This includes weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data. For example, the server sends a request to the weather forecast API to obtain weather information for the current location and destination. At the same time, it obtains information from the road API that the current road surface conditions have been updated to "slippery."

[1052] The server inputs collected driving data, external information, and the user's emotional state into the AI ​​model. The AI ​​model uses a wear prediction algorithm based on deep learning to predict the deterioration status and replacement timing of each part, such as engine oil, brake pads, and tires. At this time, the data is normalized and input into the AI ​​model. For example, the server supplies data to the AI ​​model, which predicts that "the engine oil needs to be changed in 500 km." It also takes into account road condition data and determines that the remaining mileage of the tires may be shortened.

[1053] The server notifies the user of the optimal maintenance timing based on the wear prediction results. This notification is sent to the smartphone app or in-car display. The emotion engine also makes suggestions that take the user's emotional state into account. For example, the server may notify the user's smartphone app, "It's almost time to change your engine oil. We recommend changing it within the next 500 km." Furthermore, if the server recognizes that the user is feeling stressed, it adds a message saying, "We also recommend taking a break in a relaxing place."

[1054] The server calculates the remaining distance to the destination based on the current amount of gasoline remaining and consumption, and suggests suitable gas stations if refueling is required along the way. This is also done by analyzing GPS data and route information to select the most efficient and safe refueling point. For example, based on the user's current location and remaining gasoline, the server might suggest, "You will run out of gas in the next 150 km. We recommend that the next refueling point be a service area 30 km away." If the user is in a hurry, it adds a comment saying, "We recommend refueling at the shortest distance."

[1055] Based on the wear prediction results and the user's emotional data, the server provides repair companies and dealers with information about vehicle maintenance and the preparation of necessary parts. This allows necessary parts and maintenance to be prepared in advance, allowing the user to receive service smoothly. For example, the server may notify a repair company that "User A's vehicle is nearing the time for an engine oil change. Please prepare the parts." Furthermore, based on the user's emotional data, the server may suggest that "The user is feeling stressed, so please consider providing service in a relaxed environment."

[1056] By utilizing this system, it is possible to effectively analyze driving data and external information, provide users with optimal maintenance and refueling timings, and improve services that reflect the user's emotional state.

[1057] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1058] Step 1: Data collection

[1059] The device collects various driving data from the vehicle in real time. It is connected to a GPS module, engine control unit (ECU), and various sensors, and acquires data from these devices. Specifically, it collects the number of engine starts and stops, the duration of headlight illumination, the duration of wiper operation, the number and duration of accelerator and brake operation, the distance traveled, and the route traveled. It also uses a camera and microphone to analyze the user's voice and facial expressions, and an emotion engine detects the user's stress level.

[1060] Input: In-vehicle devices (GPS module, ECU, various sensors), camera, microphone

[1061] Output: Driving data (mileage, number of engine starts, etc.), emotional data (stress level, etc.)

[1062] Specific operation: The device obtains the number of engine starts from the ECU, measures the mileage using the GPS module, captures the user's facial expressions in real time using the camera, and analyzes the user's stress level using the emotion engine.

[1063] Step 2: Obtaining external information

[1064] The server uses external APIs to obtain weather information, road surface conditions, and traffic information. Data is collected in real time using weather APIs and traffic information APIs.

[1065] Input: Weather API, Road API, Traffic API

[1066] Output: External information (weather information, road surface conditions, traffic conditions)

[1067] Specific operation: The server sends a request to the weather forecast API to obtain weather information for the current location and destination. At the same time, it obtains information from the road API that the current road conditions have been updated to "slippery."

[1068] Step 3: Wear and tear prediction

[1069] The server inputs the driving data collected in step 1, the external information obtained in step 2, and the user's emotional data into the AI ​​model. The AI ​​model uses deep learning to execute a wear prediction algorithm and predict the deterioration status and replacement timing of each part. The data is normalized and input into the AI ​​model.

[1070] Input: driving data, external information, emotion data

[1071] Output: Wear prediction results (engine oil change timing, tire wear status, etc.)

[1072] Specific operation: The server normalizes the collected data and inputs it into the AI ​​model. The AI ​​model analyzes the data and outputs a prediction result: "It's time to change the engine oil in 500 km."

[1073] Step 4: Maintenance schedule suggestions

[1074] The server notifies the user of the optimal maintenance period based on the wear prediction results. Maintenance suggestions are sent to the user's smartphone app or the in-car display. The emotion engine makes suggestions that take the user's emotional state into consideration.

[1075] Input: Wear prediction results, user emotion data

[1076] Output: Maintenance notification (smartphone app, in-car display)

[1077] Specific operation: The server notifies the user's smartphone app that "It's almost time to change the engine oil. We recommend changing it within the next 500 km." If the user is feeling stressed, the server adds a suggestion that "We also recommend taking a break in a relaxing place."

[1078] Step 5: Propose refueling points

[1079] The server calculates the remaining distance to the destination based on the current fuel level and consumption, and suggests suitable gas stations if refueling is required along the way. It analyzes GPS data and route information to select the optimal refueling point.

[1080] Input: Fuel level, consumption, GPS data, route information

[1081] Output: Refueling suggestion (location information of gas stations)

[1082] Specific operation: Based on the current location and remaining gasoline of the user's vehicle, the server suggests, "You will run out of gas in the next 150 km. We recommend that the next refueling point be a service area 30 km away." If the user is in a hurry, it adds a comment saying, "We recommend refueling at the shortest distance."

[1083] Step 6: Provide feedback

[1084] The server provides repair companies and dealers with information on maintenance and the preparation of necessary parts based on the wear prediction results and user emotion data, allowing the necessary parts and maintenance to be prepared in advance, ensuring smooth service for users.

[1085] Input: Wear prediction results, user emotion data

[1086] Output: Feedback information (notification to maintenance companies and dealers)

[1087] Specific operation: The server notifies the maintenance company that "User A's vehicle's engine oil is due for a change soon. Please prepare the parts." It also suggests that "The user is feeling stressed, so please consider providing the service in a relaxed environment."

[1088] (Application example 2)

[1089] 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."

[1090] Conventional car maintenance systems can predict part wear and suggest maintenance times based on driving data and external information, but they have the problem of not being able to provide feedback that takes into account the user's emotional state. This makes it difficult to reduce the user's stress and anxiety, and to provide a safe and comfortable driving environment.

[1091] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1092] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for predicting parts wear based on the driving data and the external information, means for suggesting maintenance times to the user based on the results of the parts wear prediction, means for suggesting gas stations based on the current remaining fuel level and fuel consumption, means for providing feedback to a maintenance company or dealer according to the degree of need for maintenance, and means for recognizing the user's emotional state and providing appropriate feedback. This provides feedback that takes the user's emotional state into consideration, enabling a safe and comfortable driving environment.

[1093] "Driving data" refers to information about the driving conditions of a vehicle, such as the number of times the engine is started and stopped, the length of time the lights are on, the length of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, and the route traveled.

[1094] "External information" refers to information related to the driving environment of the vehicle, specifically weather information, road surface conditions, traffic information, and the like.

[1095] "Parts wear prediction" refers to predicting the deterioration status and replacement timing of each part of a vehicle (e.g., engine oil, brake pads, tires, etc.) based on driving data and external information.

[1096] "Maintenance timing suggestion" refers to the process of notifying the user of the timing for replacement or inspection of each part of the car based on the results of part wear prediction.

[1097] "Suggesting gas stations" refers to a process of specifying and suggesting gas stations that the user should stop at to refuel based on the current remaining fuel amount and fuel consumption.

[1098] "Providing feedback" means notifying repair shops and dealers of the necessary information depending on the degree of maintenance required, and encouraging them to prepare the appropriate service and parts.

[1099] "Means for recognizing emotional states" refers to technology that recognizes a user's emotional states, such as stress, impatience, and anxiety, by analyzing the user's voice and facial expressions.

[1100] The "means for providing appropriate feedback" refers to a process of providing advice or suggestions to reduce the user's stress or anxiety based on the user's emotional state.

[1101] System Configuration

[1102] This invention is a system including means for collecting driving data, means for acquiring external information, means for predicting part wear based on the driving data and external information, means for suggesting maintenance times to the user based on the results of the part wear prediction, means for suggesting gas stations based on the current remaining fuel level and consumption, means for providing feedback to maintenance companies and dealers according to the degree of need for maintenance, and means for recognizing the emotional state of the user and providing appropriate feedback.

[1103] Data collection

[1104] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[1105] Obtaining external information

[1106] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[1107] Wear prediction

[1108] The server uses an AI model to predict wear and tear on each part based on collected driving data, external information, and the user's emotional state. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when each part (e.g., engine oil, brake pads, tires) should be replaced.

[1109] Maintenance schedule suggestions

[1110] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. The emotion engine makes suggestions that take into account the user's emotional state.

[1111] Refueling point suggestions

[1112] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[1113] Providing Feedback

[1114] The server provides the results of wear predictions to repair shops and dealers, allowing them to prepare necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[1115] Specific examples

[1116] For example, a device might record that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the mileage was 1,500 km. Furthermore, the device might recognize that the user is feeling stressed while driving. The server might also acquire information that the current local weather is rainy and the roads are slippery. Furthermore, the server might predict that frequent engine starts and stops will accelerate engine oil deterioration and notify the user that the oil is due for replacement. It might also determine that driving on slippery roads has accelerated tire wear. Furthermore, if the user's stress level is affecting the vehicle's wear, the device might urge the user to take special precautions. Based on this information, the server might notify the user that "it is recommended to change the engine oil" and, at the same time, that "it is recommended to check the tires after the next 1,000 km of driving." Furthermore, if the user is feeling stressed, the server might add a suggestion that "it is recommended to take a break in a place where you can relax while driving."

[1117] Prompt Sentence Examples

[1118] Describe an assistant application that identifies the stress level a user experiences while driving and, based on that, suggests appropriate relaxation or resting spots.

[1119] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1120] Step 1:

[1121] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[1122] *Input: various sensor data from the car, user's voice and facial expressions

[1123] * Output: Driving data and user's emotional state

[1124] Step 2:

[1125] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[1126] *Input: Data from weather API and traffic information API

[1127] * Output: Weather information, road surface conditions, traffic information

[1128] Step 3:

[1129] The server normalizes the collected driving data and external information and inputs it into an AI model. The AI ​​model uses this data to predict wear and tear on each part. Specifically, driving data (number of engine starts and stops, light on time, etc.) and external information (weather, road conditions, etc.) are input, normalized, and the AI ​​model predicts part deterioration.

[1130] *Input: operation data, external information

[1131] * Output: Part wear prediction results

[1132] Step 4:

[1133] The server then proposes maintenance times to the user based on the wear prediction results. Specifically, it sends a notification message to the user's smartphone or in-car display. The emotion engine makes proposals that take into account the user's emotional state.

[1134] *Input: wear prediction results, user's emotional state

[1135] * Output: Maintenance time suggestion message

[1136] Step 5:

[1137] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[1138] *Input: current remaining gasoline, consumption, driving distance, user's emotional state

[1139] * Output: Gas station suggestion message

[1140] Step 6:

[1141] The server provides the results of wear predictions to repair shops and dealers, allowing them to prepare necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[1142] *Input: wear prediction results, user's emotional state

[1143] * Output: Feedback information for repair shops and dealers

[1144] 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.

[1145] 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.

[1146] 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.

[1147] [Fourth embodiment]

[1148] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1149] 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.

[1150] 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).

[1151] 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.

[1152] 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.

[1153] 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).

[1154] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1155] 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.

[1156] 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.

[1157] 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.

[1158] 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.

[1159] 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.

[1160] 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."

[1161] This invention is a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that performs wear prediction, and means for suggesting maintenance and gas stations to users. The program processing of this system is explained below in natural language.

[1162] Data collection

[1163] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are in operation, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.

[1164] Example: The device records that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance traveled was 1500 km.

[1165] Obtaining external information

[1166] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[1167] Example: A server receives information that the current local weather is rainy and road conditions are slippery.

[1168] Wear prediction

[1169] The server uses an AI model to predict wear and tear on each part based on collected driving data and external information. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when to replace each part (e.g., engine oil, brake pads, tires).

[1170] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that the oil is due for replacement. It also determines that tires are worn out as a result of driving on slippery roads.

[1171] Maintenance schedule suggestions

[1172] The server then recommends maintenance times to the user based on the wear prediction results, and a notification message is sent to the smartphone app or on the in-car display.

[1173] Example: The server notifies the user that "it is recommended to change the engine oil" and also that "it is recommended to check the tires after the next 1000 km of driving."

[1174] Refueling point suggestions

[1175] The server calculates the distance to the destination based on the current amount of gasoline remaining and consumption, and if refueling is required along the way, it suggests appropriate gas stations.

[1176] Example: The server determines that the user's next destination is 200 km away and suggests suitable refueling points since the current amount of gasoline is insufficient.

[1177] Providing Feedback

[1178] The server provides the results of wear predictions to maintenance companies and dealers, allowing them to prepare the necessary parts and maintenance in advance.

[1179] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides the service.

[1180] summary

[1181] This system collects and analyzes vehicle driving data and external information to predict wear and tear on each part, and by suggesting appropriate maintenance and refueling times to the user and providing feedback to maintenance companies, it supports efficient maintenance and safe driving.

[1182] The processing flow will be explained below.

[1183] Step 1:

[1184] The device collects driving data.

[1185] Specifically, the data collected includes the number of times the engine is started and stopped, the duration of time the lights are on, the duration of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, the route traveled, etc. This data is collected automatically via on-board sensors and GPS.

[1186] Step 2:

[1187] The driving data collected by the terminal is periodically sent to the server.

[1188] The data is uploaded to a server over the internet using a secure communication protocol, with precise timestamps attached to the data and the order in which it was collected maintained.

[1189] Step 3:

[1190] The server obtains external information via the Internet.

[1191] Specifically, weather information is obtained from a weather API, and road surface and traffic conditions are obtained from a traffic information API. The obtained external information is also saved with a timestamp.

[1192] Step 4:

[1193] The server receives and integrates driving data and external information.

[1194] The acquired data is mapped onto the same time axis and preprocessed, for example, by filling in missing data and normalizing the data.

[1195] Step 5:

[1196] The server inputs the preprocessed data into the AI ​​model.

[1197] The AI ​​model predicts the wear and tear of each part based on a machine learning algorithm, which has been trained in advance using a large amount of learning data.

[1198] Step 6:

[1199] The server analyzes the prediction results from the AI ​​model and calculates the wear and tear and replacement time for each part.

[1200] For example, the deterioration level of engine oil and the state of tire wear are output as numerical values, and the next maintenance schedule is determined based on these.

[1201] Step 7:

[1202] The server will suggest maintenance times and necessary part replacements to the user.

[1203] The recommendations are sent to a smartphone app or on the in-car display, and include specific replacement times and the recommended date and time for the next inspection.

[1204] Step 8:

[1205] The user confirms the proposed maintenance.

[1206] The user checks the maintenance schedule and makes a reservation if necessary.

[1207] Step 9:

[1208] The server calculates the distance to the destination based on the current fuel level and consumption.

[1209] This uses historical fuel consumption data and current fuel remaining data.

[1210] Step 10:

[1211] The server suggests gas stations.

[1212] Taking into consideration the route to the destination, if refueling is required along the way, appropriate refueling stations are suggested to the user.

[1213] Step 11:

[1214] The server provides feedback to the repair company or dealer.

[1215] It provides advance notification of predicted maintenance and required parts, allowing maintenance companies to make appropriate preparations.

[1216] Step 12:

[1217] A maintenance company prepares parts based on the notified feedback, and provides the user with prompt maintenance.

[1218] The maintenance company checks the parts inventory and arranges for the necessary parts.

[1219] summary

[1220] The system's processing steps collect and analyze driving data and external information, and use an AI model to predict the wear and tear of each part. Optimal maintenance and refueling times are suggested to users, and necessary information is provided to maintenance companies in advance. This ensures efficient and safe vehicle maintenance.

[1221] Example 1

[1222] 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."

[1223] Conventional technology did not offer a system that efficiently collected vehicle driving data and external information, analyzed them, and then suggested appropriate maintenance and refueling timings. This made it difficult for users to perform maintenance at the appropriate time, resulting in increased wear and tear on the vehicle and increased risk of breakdowns. Furthermore, it was difficult for repair companies and dealers to prepare the necessary parts and services in advance, creating a need for more efficient maintenance.

[1224] 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.

[1225] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for preprocessing data based on the driving data and the external information, means for predicting wear based on the results of the data preprocessing, means for suggesting maintenance times to the user based on the results of the part wear prediction, means for suggesting refueling locations based on the remaining amount of fuel and the amount of fuel consumed, and means for providing feedback to repair companies and dealers according to the degree of maintenance necessity. This allows the user to perform maintenance and refueling at the appropriate time, reducing wear and tear on the vehicle and the risk of breakdown, and also allows repair companies and dealers to prepare necessary parts in advance, thereby improving maintenance efficiency.

[1226] "Driving data" refers to information relating to the vehicle's driving state and operating conditions.

[1227] "External information" refers to information about the external environment of the vehicle, such as weather and traffic conditions.

[1228] "Data preprocessing" refers to the process of analyzing and normalizing collected operational data and external information, and converting them into a format suitable for analysis and predictive models.

[1229] "Wear prediction" is the prediction of the deterioration state and replacement time of each vehicle part based on processed data.

[1230] The "means for proposing the timing of maintenance" is to notify the user of the appropriate timing of maintenance based on the predicted wear data.

[1231] The "means for suggesting a refueling location" is to suggest the most suitable refueling location to the user based on the current remaining amount of fuel and the predicted fuel consumption.

[1232] The "means for providing feedback" refers to providing the results of wear prediction to maintenance companies and dealers, enabling them to prepare the necessary parts and services in advance.

[1233] An "artificial intelligence model" is a computer algorithm that analyzes and learns from multiple data sets to recognize and predict patterns.

[1234] MODE FOR CARRYING OUT THE INVENTION

[1235] This invention is a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables. This system includes a terminal for collecting driving data, a server for acquiring external information, an AI model for predicting wear, a means for making maintenance suggestions to users, and a means for suggesting gas stations.

[1236] Data collection

[1237] The device collects driving data from the vehicle's engine control unit (ECU) and various sensors, including the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. The collected data is then stored on the vehicle's onboard storage media.

[1238] Example: The device connects to the vehicle's ECU and records 50 engine starts and stops, 120 minutes of headlight time, 30 minutes of windshield wiper time, and 1,500 km of driving distance.

[1239] Obtaining external information

[1240] The server obtains the necessary external information from weather information APIs and traffic information APIs via the Internet. This includes weather information, road surface conditions, traffic information, etc. Specifically, data can be obtained using the OpenWeatherMap API and Google Maps Traffic API.

[1241] Example: A server receives information that the current local weather is rainy and road conditions are slippery.

[1242] Data Preprocessing

[1243] The server receives driving data sent from the terminal and external information it acquires, and preprocesses them. Data preprocessing involves analyzing and normalizing the collected data and converting it into a format suitable for analysis and predictive models.

[1244] Example: The server normalizes each item of driving data (e.g., number of engine starts and distance traveled) to a uniform scale, and similarly normalizes weather and traffic data.

[1245] Wear prediction

[1246] The server inputs the preprocessed data into a generative AI model (e.g., a model trained with TensorFlow or PyTorch) to predict wear and tear for each part. The AI ​​model predicts wear and tear based on the collected data and returns the results to the server.

[1247] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that the oil is due for replacement. It also determines that tires are worn out as a result of driving on slippery roads.

[1248] Maintenance schedule suggestions

[1249] The server notifies the user of the need for maintenance based on the wear prediction results received from the AI ​​model, and the notification message is sent to a smartphone app or an in-car display.

[1250] Example: The server notifies the user that "it is recommended to change the engine oil" and also that "it is recommended to check the tires after the next 1000 km of driving."

[1251] Refueling point suggestions

[1252] The server calculates the current amount of gasoline remaining and the predicted consumption, and suggests appropriate refueling points based on the remaining distance to the destination.

[1253] Example: The server determines that the user's next destination is 200 km away and suggests refueling stops along the way, since the current amount of gasoline is insufficient.

[1254] Providing Feedback

[1255] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare for necessary parts and maintenance in advance.

[1256] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides the service.

[1257] Prompt Sentence Examples

[1258] Here are some example prompts to input to a generative AI model:

[1259] Please explain in detail the step-by-step program process for a system that predicts the deterioration status of a vehicle's consumables based on the following information:

[1260] Engine start / stop count: 50 times

[1261] Light duration: 120 minutes

[1262] Wiper operation time: 30 minutes

[1263] Mileage: 1500km

[1264] Weather information: rain

[1265] Road Condition: Slippery

[1266] Based on this information, please explain in detail the process of predicting when to change engine oil or tires and providing maintenance suggestions to the user.

[1267] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1268] Step 1: Collect driving data

[1269] The device collects driving data from the vehicle's engine control unit (ECU) and various sensors. The device is connected to the vehicle's ECU and obtains data such as the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.

[1270] Input: Raw data from various vehicle sensors and ECUs.

[1271] Output: A set of collected driving data (e.g., 50 engine starts, 120 minutes with the lights on, 1500 km driven, etc.).

[1272] Specific operation: The terminal is installed in the vehicle, collects data from the ECU and sensors in real time, and stores it on the vehicle's storage media.

[1273] Step 2: Obtaining external information

[1274] The server obtains external information from weather information APIs and traffic information APIs via the Internet. Specifically, it collects data using the OpenWeatherMap API and Google Maps Traffic API.

[1275] Input: Requests to the Weather and Traffic APIs.

[1276] Output: Captured weather and traffic data.

[1277] Specific operation: The server periodically accesses the API to obtain current weather information (e.g., rain, slippery roads) and traffic information, and stores it as well-formatted data.

[1278] Step 3: Preprocessing the data

[1279] The server receives driving data sent from the device and external information it acquires, normalizes and preprocesses this data, adjusting each item of driving data to a uniform scale and converting it into a format used by the AI ​​model.

[1280] Input: Collected driving and external information data.

[1281] Output: A normalized dataset.

[1282] Specific operation: The server scales the data and performs processes such as "normalizing the number of engine starts to a range of 0 to 1" and "converting weather data into a numerical format."

[1283] Step 4: Wear and tear prediction

[1284] The server inputs the preprocessed data into a generative AI model to predict wear and tear for each part. The AI ​​model analyzes the wear and tear status based on the input data and returns the results to the server.

[1285] Input: The normalized dataset.

[1286] Output: Wear prediction results for each part.

[1287] Specific operation: An AI model trained with TensorFlow predicts the degree of engine oil deterioration, the degree of tire wear, etc., and calculates when to replace them.

[1288] Step 5: Maintenance schedule suggestions

[1289] The server notifies the user of the need for maintenance based on the wear prediction results received from the AI ​​model, and the notification message is sent to a smartphone app or an in-car display.

[1290] Input: Wear prediction results for each part.

[1291] Output: Maintenance suggestion notification to user.

[1292] Specific operation: The server generates a message such as "It is recommended to change the engine oil" and sends a push notification to the user's smartphone. The same information is also displayed on the car's display.

[1293] Step 6: Propose refueling points

[1294] The server calculates the current amount of gasoline remaining and the predicted consumption, and suggests the optimal refueling location to the user. The server also determines the need for refueling based on the distance to the destination.

[1295] Input: Current gasoline level, predicted consumption data.

[1296] Output: Refueling point suggestions to the user.

[1297] Specific operation: Based on the information that "the remaining distance to the next destination is 200 km and the current amount of gasoline is insufficient," the server suggests refueling points along the way.

[1298] Step 7: Provide feedback

[1299] The server provides the results of wear predictions to maintenance companies and dealers, allowing them to prepare the necessary parts and services in advance.

[1300] Input: Wear prediction results for each part.

[1301] Output: Feedback notification to maintenance companies and dealers.

[1302] Specific operation: The server sends a message to the repair shop saying "User XX's vehicle needs an engine oil change," and the repair shop prepares the parts and gets ready to provide service.

[1303] (Application example 1)

[1304] 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."

[1305] Conventional automobile maintenance systems often fail to fully utilize driving data and external information, resulting in inappropriate prediction of part wear and inappropriate suggestions for maintenance timing. Furthermore, the system's ability to suggest appropriate gas stations based on remaining fuel levels is insufficient, resulting in low user convenience. Furthermore, feedback provided to repair companies and dealers is ineffective, resulting in low maintenance efficiency. The present invention aims to solve these problems and support users in driving safely and efficiently.

[1306] 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.

[1307] In this invention, the server includes a means for collecting driving data, a means for acquiring external information, a means for predicting part wear based on the driving data and the external information, a means for suggesting maintenance times to the user based on the part wear prediction results, a means for suggesting gas stations based on the current fuel level and consumption, a means for providing feedback to maintenance companies and dealers based on the degree of maintenance necessity, a data normalization means for predicting wear using a generative AI model, and a means for notifying the user based on a prompt sentence. This makes it possible to appropriately utilize driving data and external information to predict part wear and accurately suggest maintenance times and gas stations to the user. Furthermore, by providing prompt and accurate feedback to maintenance companies and dealers, maintenance efficiency can be improved.

[1308] "Means for collecting driving data" refers to devices and systems for obtaining data related to the driving conditions of a vehicle.

[1309] "Means for acquiring external information" refers to techniques and methods for collecting information about the external environment, such as weather information, road surface conditions, and traffic information.

[1310] "Means for predicting part wear based on driving data and external information" refers to technology that uses driving data and collected external information to predict the deterioration and replacement timing of automobile parts.

[1311] "Means for proposing maintenance timing to users based on the results of part wear prediction" refers to technology that notifies and suggests appropriate maintenance timing to users based on the results of wear prediction.

[1312] "Means for suggesting gas stations based on the current remaining fuel amount and consumption amount" refers to technology that guides the user to the most suitable gas station based on the remaining fuel amount and the rate at which it is consumed.

[1313] "Means for providing feedback to repair companies and dealers based on the degree of maintenance required" refers to technology that provides necessary information to repair companies and dealers when the need for maintenance increases.

[1314] "Data normalization method for wear and tear prediction using generative AI models" refers to a technique that converts input data into a unified format so that the AI ​​model can function efficiently.

[1315] "User notification means based on prompt sentences" refers to a technology that appropriately notifies the user of necessary information based on defined questions or instruction sentences.

[1316] This invention is a system that collects and analyzes operational data and external information to predict the deterioration status of consumables and the timing of maintenance. A detailed description of this system is provided below.

[1317] Data collection

[1318] The device collects driving data from the vehicle's sensors. This data includes the number of times the engine was started and stopped, the duration the lights were on, the duration the wipers were on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. The device transmits this data in real time, for example, via Bluetooth or Wi-Fi. For example, the device can record that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance traveled was 1,500 km.

[1319] Obtaining external information

[1320] The server obtains external information via the Internet. This information includes weather information, road surface conditions, and traffic information. The server uses the OpenWeatherMap API for weather information and the Google Maps API for traffic information. For example, the server can obtain information that the current weather in the area is rainy and the roads are slippery.

[1321] Wear prediction

[1322] The server uses a generative AI model to predict wear and tear on each part based on collected driving data and external information. The data is normalized and input into an AI model using, for example, TensorFlow or PyTorch. This predicts when each part (e.g., engine oil, brake pads, tires) needs to be replaced. For example, the server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that it is soon time to replace the oil. It may also determine that tires are wearing out as a result of driving on slippery roads.

[1323] Maintenance schedule suggestions

[1324] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. For example, a message such as "We recommend changing your engine oil" or "We recommend checking your tires after the next 1000km of driving" is sent.

[1325] Refueling point suggestions

[1326] The server calculates the distance to the destination based on the current fuel remaining and consumption, and if refueling is required along the way, suggests an appropriate gas station. Based on the distance to the destination and the current location information, the server uses the Google Maps API to guide the user to nearby gas stations. As a specific example, if the user confirms that the next destination is 200 km away and the current gas level is insufficient, the server suggests an appropriate refueling point.

[1327] Providing Feedback

[1328] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare the necessary parts and maintenance in advance. For example, the server notifies a repair company that "User XX's vehicle needs an engine oil change," and the repair company prepares the necessary parts based on this information and provides the service.

[1329] Prompt Sentence Examples

[1330] "To predict vehicle maintenance, please predict engine oil deterioration based on the following driving data and external information: Number of engine starts: 50, Lights on for: 120 minutes, Wiper operation time: 30 minutes, Mileage: 1500 km, Weather information: Rain, Road conditions: Slippery. For output, please display the recommended engine oil change interval in Japanese."

[1331] In this way, the present invention provides a system that combines driving data and external information to predict the deterioration status of each part and notify the user of the appropriate maintenance timing. In addition, by providing the wear prediction results to maintenance companies, maintenance efficiency can be improved.

[1332] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1333] Step 1:

[1334] The terminal collects driving data from the vehicle. This driving data includes the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are operated, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Specifically, the terminal obtains this data from the vehicle's sensors using Bluetooth or Wi-Fi and transmits the data to the server in real time. The input data is the readings from the various sensors, and the output is the driving data sent to the server.

[1335] Step 2:

[1336] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. For example, the server obtains current weather information using the OpenWeatherMap API and traffic conditions using the Google Maps API. The input is a data request from the weather API or traffic information API, and the output is the obtained external information.

[1337] Step 3:

[1338] The server uses a generative AI model to predict wear and tear on each part based on the collected driving data and external information. Specifically, the driving data and external information are normalized and input into an AI model using TensorFlow and PyTorch. The AI ​​model uses this data to predict when to replace consumables such as engine oil, brake pads, and tires. The input is the normalized driving data and external information, and the output is the predicted replacement times for consumables.

[1339] Step 4:

[1340] The server will suggest maintenance times to the user based on the results of the wear prediction. Specifically, if it determines that maintenance is necessary based on the results of the wear prediction, it will send a notification message to the user using the smartphone's push notification function. The input is the wear prediction result, and the output is the notification message to the user.

[1341] Step 5:

[1342] The server calculates the distance to the destination based on the current fuel level and consumption, and if refueling is required along the way, suggests suitable gas stations. Specifically, it uses the Google Maps API to guide the driver to nearby gas stations based on the distance to the destination and the current location. The input is the current fuel level, consumption, location, and distance to the destination, and the output is information about suggested gas stations.

[1343] Step 6:

[1344] The server provides the results of wear prediction to maintenance companies and dealers. Specifically, it uses a REST API to send information about users who need to replace consumables to maintenance companies. The input is the wear prediction results and user information, and the output is a notification to the maintenance company. This allows maintenance companies to prepare the necessary parts in advance and provide services efficiently.

[1345] 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.

[1346] This invention combines a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance schedule of consumables with an emotion engine that recognizes user emotions. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that predicts wear and tear, a means for suggesting maintenance and gas stations to the user, and an emotion engine that recognizes user emotions and provides appropriate feedback. The program processing of this system is explained below in natural language.

[1347] Data collection

[1348] The device collects driving data from the vehicle, such as the number of engine starts and stops, the duration of headlights, the duration of wiper operation, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[1349] Example: The device records that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the distance driven was 1500 km. Furthermore, the device recognizes that the user is stressed while driving.

[1350] Obtaining external information

[1351] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[1352] Example: The server receives information that the current weather in the area is rainy and the roads are slippery. The server collects the user's emotional state as feedback and considers appropriate countermeasures.

[1353] Wear prediction

[1354] The server uses an AI model to predict wear and tear on each part based on collected driving data, external information, and the user's emotional state. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when each part (e.g., engine oil, brake pads, tires) should be replaced.

[1355] Example: The server predicts that frequent engine starts and stops will accelerate engine oil deterioration and notify the driver that it is time to change the oil. It also determines that tires are wearing out as a result of driving on slippery roads. Furthermore, if the user's stress level is affecting the vehicle's wear and tear, the server will provide special attention.

[1356] Maintenance schedule suggestions

[1357] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. The emotion engine makes suggestions that take into account the user's emotional state.

[1358] Example: The server notifies the user that "It is recommended to change the engine oil." At the same time, it also notifies that "It is recommended to check the tires after the next 1000 km of driving." Furthermore, if the user is feeling stressed, it adds a suggestion that "It is recommended to take a break in a place where you can drive in a relaxed manner."

[1359] Refueling point suggestions

[1360] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[1361] Example: The server confirms that the user's next destination is 200 km away, and suggests an appropriate refueling point since the current amount of gasoline is insufficient. If the user feels impatient or anxious, the server suggests "We recommend refueling at the next safe location."

[1362] Providing Feedback

[1363] The server provides the results of wear predictions to repair companies and dealers, allowing them to prepare for necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[1364] Example: The server notifies the maintenance company that "User XX's vehicle needs an engine oil change." Based on this information, the maintenance company prepares the necessary parts and provides service. If the user is feeling stressed, the server considers providing special service.

[1365] summary

[1366] The system's processing steps collect and analyze driving data and external information, and use an AI model to predict the wear and tear of each part. The system suggests optimal maintenance and refueling times to users, and provides necessary information to maintenance companies in advance. The integration of an emotion engine provides a safe and comfortable driving environment that takes into account the user's emotional state.

[1367] The processing flow will be explained below.

[1368] Step 1:

[1369] The device collects driving data.

[1370] Specifically, it automatically collects data from each sensor, such as the number of times the engine is started and stopped, the duration of the lights, the duration of the wipers, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled.In addition, it uses an emotion engine to analyze the user's voice and recognize their face, and recognizes their emotional state (e.g., stress, anxiety, relaxation, etc.) in real time.

[1371] Example: The device records that the engine has been started 50 times, the lights have been on for 120 minutes, the wipers have been on for 30 minutes, and the distance traveled is 1500 km. In addition, the emotion engine recognizes that the user is feeling stressed while driving.

[1372] Step 2:

[1373] The terminal transmits the collected driving data and user emotion data to the server.

[1374] The data is periodically uploaded to a server using a secure communication protocol and is time-stamped to record the exact time of collection.

[1375] Example: The device sends the collected driving data and user emotion data on "stress state" to the server.

[1376] Step 3:

[1377] The server obtains external information via the Internet.

[1378] Specifically, weather information is obtained from a weather API, and road surface conditions and traffic information are obtained from a traffic information API. The obtained external information is also saved with a timestamp.

[1379] Example: The server retrieves the weather information for the current location, indicating that it is raining and the roads are slippery.

[1380] Step 4:

[1381] The server integrates driving data, external information, and user emotion data.

[1382] The acquired data is mapped onto the same time axis and preprocessed, specifically by filling in missing data, normalizing the data, and calculating correlations.

[1383] Example: A server integrates driving data, weather information, road information, and user sentiment data and prepares it for analysis.

[1384] Step 5:

[1385] The server inputs the preprocessed data into an AI model to predict part wear.

[1386] The AI ​​model uses machine learning algorithms to predict the wear and tear of each part. The model is pre-trained with a large amount of learning data. The prediction results include the wear and tear and replacement times for parts such as engine oil, brake pads, and tires.

[1387] Example: The server predicts that the engine oil is deteriorating quickly and needs to be replaced soon, and determines that the brake pads are wearing out due to frequent braking.

[1388] Step 6:

[1389] The server analyzes the prediction results from the AI ​​model and provides detailed feedback while taking into account the user's emotional state.

[1390] Based on the predicted replacement times for parts and user sentiment, an appropriate maintenance schedule is created and notified to the user.

[1391] Example: The server notifies the user that "it is recommended to change the engine oil" and also advises that "it is recommended to check the tires after the next 1000 km of driving." In addition, because the user is in a stressed state, it makes an additional suggestion that "it is recommended to take a break in a relaxing place."

[1392] Step 7:

[1393] The server calculates the distance to the destination based on the current fuel level and consumption.

[1394] It does this by using historical fuel consumption data and current fuel level data, and also takes into account the user's emotional state.

[1395] Example: The server recognizes that the user is heading to a destination 200 km away, and determines that the current fuel level is insufficient and that refueling is necessary along the way. If the user is feeling anxious or anxious, the server suggests safe refueling points.

[1396] Step 8:

[1397] The server suggests gas stations to the user.

[1398] The suggestions are displayed on a smartphone app or on an in-car display, and change depending on the user's emotional state.

[1399] Example: The server suggests "Please fill up at a gas station within the next 100 km" or, if the user is feeling impatient, notifies "Searching for a safe gas station."

[1400] Step 9:

[1401] The server provides feedback on the wear prediction results and user emotion data to maintenance companies and dealers.

[1402] This allows necessary parts and maintenance to be prepared in advance.

[1403] Example: The server notifies a maintenance company that "User XX's vehicle needs an engine oil change and the user is currently feeling stressed." The maintenance company uses this information to provide prompt and appropriate service.

[1404] Step 10:

[1405] The maintenance company prepares parts based on the feedback and provides the user with prompt maintenance.

[1406] The repair company will check the parts inventory and arrange for parts as needed, and will also respond appropriately depending on the user's emotional state.

[1407] Example: A maintenance company prepares engine oil and has all the necessary information ready before the user arrives. When the user arrives, they receive special treatment, such as a relaxing environment.

[1408] summary

[1409] The system's processing steps collect and analyze driving data, external information, and user emotional data, and use an AI model to predict the wear and tear of each part. The system suggests appropriate maintenance and refueling times to users, and provides necessary information to maintenance companies in advance. The integration of an emotional engine takes the user's emotional state into consideration, creating a safe and comfortable driving environment.

[1410] Example 2

[1411] 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."

[1412] Modern cars are equipped with many sensors and can collect a wide variety of data, but systems that effectively utilize this data and appropriately notify users of optimal maintenance and refueling times are not widely available. Furthermore, conventional systems do not take user emotions into account and do not provide appropriate feedback based on changes in stress and emotion. This can compromise user safety and comfort.

[1413] 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.

[1414] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for predicting parts wear based on the driving data, the external information, and the user's emotions, means for suggesting maintenance times to the user based on the parts wear prediction results, means for suggesting gas stations based on the current remaining fuel amount and consumption amount, and means for providing feedback to repair companies and dealers according to the degree of necessity for maintenance and the user's emotions. This makes it possible to propose optimal maintenance and refueling timings that take into account the user's emotions while utilizing the driving data and external information.

[1415] "Driving data" refers to data relating to the vehicle's operating state and driving conditions, and specifically includes the number of times the engine is started and stopped, the length of time the lights are on, the length of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, and the route traveled.

[1416] "External information" refers to information obtained via the Internet or external APIs, and specifically includes weather information, road surface conditions, traffic information, etc.

[1417] An "emotion engine" is a system that analyzes emotions from the user's voice, facial expressions, etc., and recognizes stress levels and changes in emotions.

[1418] "Wear prediction" involves predicting the deterioration status and replacement timing of vehicle parts (e.g., engine oil, brake pads, tires) based on collected driving data, external information, and the user's emotional state.

[1419] "Maintenance timing suggestion" means notifying the user when maintenance such as replacement or inspection of each vehicle part is required based on the wear prediction results.

[1420] "Fuel station suggestion" calculates the distance to the destination based on the current fuel remaining and consumption, and recommends appropriate fuel stations if refueling is required along the way.

[1421] "Providing feedback" means providing information to repair companies and dealers regarding vehicle maintenance and preparation of necessary parts based on wear prediction results and user emotion data.

[1422] An "AI model" refers to an artificial intelligence system that receives collected data as input and uses a learning algorithm to predict wear and tear.

[1423] "Data normalization" refers to converting collected data to a certain scale or format, making it suitable for input into an AI model.

[1424] This invention combines a system that collects and analyzes vehicle driving data and external information to predict the deterioration status and maintenance timing of consumables with an emotion engine that recognizes user emotions. This system includes a terminal that collects driving data, a server that acquires external information, an AI model that performs wear prediction, a means for suggesting maintenance and gas stations to the user, and an emotion engine that recognizes user emotions and provides appropriate feedback.

[1425] The device collects driving data from the vehicle in real time. The device is connected to a GPS module, engine control unit (ECU), and sensor array, and acquires data from these. Specifically, the device collects data such as the number of engine starts and stops, the duration of headlight illumination, the duration of wiper operation, the number and duration of accelerator and brake operation, mileage, and driving route. The device is also equipped with a camera and microphone, which are used to analyze the user's voice and facial expressions and activate an emotion engine that recognizes emotions. For example, the device acquires the number of engine starts from the engine control unit (ECU) and measures the mileage using the GPS module. The camera also captures the user's facial expressions in real time, and the emotion engine analyzes the user's stress level.

[1426] The server obtains external information via the Internet. This includes weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data. For example, the server sends a request to the weather forecast API to obtain weather information for the current location and destination. At the same time, it obtains information from the road API that the current road surface conditions have been updated to "slippery."

[1427] The server inputs collected driving data, external information, and the user's emotional state into the AI ​​model. The AI ​​model uses a wear prediction algorithm based on deep learning to predict the deterioration status and replacement timing of each part, such as engine oil, brake pads, and tires. At this time, the data is normalized and input into the AI ​​model. For example, the server supplies data to the AI ​​model, which predicts that "the engine oil needs to be changed in 500 km." It also takes into account road condition data and determines that the remaining mileage of the tires may be shortened.

[1428] The server notifies the user of the optimal maintenance timing based on the wear prediction results. This notification is sent to the smartphone app or in-car display. The emotion engine also makes suggestions that take the user's emotional state into account. For example, the server may notify the user's smartphone app, "It's almost time to change your engine oil. We recommend changing it within the next 500 km." Furthermore, if the server recognizes that the user is feeling stressed, it adds a message saying, "We also recommend taking a break in a relaxing place."

[1429] The server calculates the remaining distance to the destination based on the current amount of gasoline remaining and consumption, and suggests suitable gas stations if refueling is required along the way. This is also done by analyzing GPS data and route information to select the most efficient and safe refueling point. For example, based on the user's current location and remaining gasoline, the server might suggest, "You will run out of gas in the next 150 km. We recommend that the next refueling point be a service area 30 km away." If the user is in a hurry, it adds a comment saying, "We recommend refueling at the shortest distance."

[1430] Based on the wear prediction results and the user's emotional data, the server provides repair companies and dealers with information about vehicle maintenance and the preparation of necessary parts. This allows necessary parts and maintenance to be prepared in advance, allowing the user to receive service smoothly. For example, the server may notify a repair company that "User A's vehicle is nearing the time for an engine oil change. Please prepare the parts." Furthermore, based on the user's emotional data, the server may suggest that "The user is feeling stressed, so please consider providing service in a relaxed environment."

[1431] By utilizing this system, it is possible to effectively analyze driving data and external information, provide users with optimal maintenance and refueling timings, and improve services that reflect the user's emotional state.

[1432] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1433] Step 1: Data collection

[1434] The device collects various driving data from the vehicle in real time. It is connected to a GPS module, engine control unit (ECU), and various sensors, and acquires data from these devices. Specifically, it collects the number of engine starts and stops, the duration of headlight illumination, the duration of wiper operation, the number and duration of accelerator and brake operation, the distance traveled, and the route traveled. It also uses a camera and microphone to analyze the user's voice and facial expressions, and an emotion engine detects the user's stress level.

[1435] Input: In-vehicle devices (GPS module, ECU, various sensors), camera, microphone

[1436] Output: Driving data (mileage, number of engine starts, etc.), emotional data (stress level, etc.)

[1437] Specific operation: The device obtains the number of engine starts from the ECU, measures the mileage using the GPS module, captures the user's facial expressions in real time using the camera, and analyzes the user's stress level using the emotion engine.

[1438] Step 2: Obtaining external information

[1439] The server uses external APIs to obtain weather information, road surface conditions, and traffic information. Data is collected in real time using weather APIs and traffic information APIs.

[1440] Input: Weather API, Road API, Traffic API

[1441] Output: External information (weather information, road surface conditions, traffic conditions)

[1442] Specific operation: The server sends a request to the weather forecast API to obtain weather information for the current location and destination. At the same time, it obtains information from the road API that the current road conditions have been updated to "slippery."

[1443] Step 3: Wear and tear prediction

[1444] The server inputs the driving data collected in step 1, the external information obtained in step 2, and the user's emotional data into the AI ​​model. The AI ​​model uses deep learning to execute a wear prediction algorithm and predict the deterioration status and replacement timing of each part. The data is normalized and input into the AI ​​model.

[1445] Input: driving data, external information, emotion data

[1446] Output: Wear prediction results (engine oil change timing, tire wear status, etc.)

[1447] Specific operation: The server normalizes the collected data and inputs it into the AI ​​model. The AI ​​model analyzes the data and outputs a prediction result: "It's time to change the engine oil in 500 km."

[1448] Step 4: Maintenance schedule suggestions

[1449] The server notifies the user of the optimal maintenance period based on the wear prediction results. Maintenance suggestions are sent to the user's smartphone app or the in-car display. The emotion engine makes suggestions that take the user's emotional state into consideration.

[1450] Input: Wear prediction results, user emotion data

[1451] Output: Maintenance notification (smartphone app, in-car display)

[1452] Specific operation: The server notifies the user's smartphone app that "It's almost time to change the engine oil. We recommend changing it within the next 500 km." If the user is feeling stressed, the server adds a suggestion that "We also recommend taking a break in a relaxing place."

[1453] Step 5: Propose refueling points

[1454] The server calculates the remaining distance to the destination based on the current fuel level and consumption, and suggests suitable gas stations if refueling is required along the way. It analyzes GPS data and route information to select the optimal refueling point.

[1455] Input: Fuel level, consumption, GPS data, route information

[1456] Output: Refueling suggestion (location information of gas stations)

[1457] Specific operation: Based on the current location and remaining gasoline of the user's vehicle, the server suggests, "You will run out of gas in the next 150 km. We recommend that the next refueling point be a service area 30 km away." If the user is in a hurry, it adds a comment saying, "We recommend refueling at the shortest distance."

[1458] Step 6: Provide feedback

[1459] The server provides repair companies and dealers with information on maintenance and the preparation of necessary parts based on the wear prediction results and user emotion data, allowing the necessary parts and maintenance to be prepared in advance, ensuring smooth service for users.

[1460] Input: Wear prediction results, user emotion data

[1461] Output: Feedback information (notification to maintenance companies and dealers)

[1462] Specific operation: The server notifies the maintenance company that "User A's vehicle's engine oil is due for a change soon. Please prepare the parts." It also suggests that "The user is feeling stressed, so please consider providing the service in a relaxed environment."

[1463] (Application example 2)

[1464] 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."

[1465] Conventional car maintenance systems can predict part wear and suggest maintenance times based on driving data and external information, but they have the problem of not being able to provide feedback that takes into account the user's emotional state. This makes it difficult to reduce the user's stress and anxiety, and to provide a safe and comfortable driving environment.

[1466] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1467] In this invention, the server includes means for collecting driving data, means for acquiring external information, means for predicting parts wear based on the driving data and the external information, means for suggesting maintenance times to the user based on the results of the parts wear prediction, means for suggesting gas stations based on the current remaining fuel level and fuel consumption, means for providing feedback to a maintenance company or dealer according to the degree of need for maintenance, and means for recognizing the user's emotional state and providing appropriate feedback. This provides feedback that takes the user's emotional state into consideration, enabling a safe and comfortable driving environment.

[1468] "Driving data" refers to information about the driving conditions of a vehicle, such as the number of times the engine is started and stopped, the length of time the lights are on, the length of time the wipers are operated, the number of times / time the accelerator and brake are operated, the distance traveled, and the route traveled.

[1469] "External information" refers to information related to the driving environment of the vehicle, specifically weather information, road surface conditions, traffic information, and the like.

[1470] "Parts wear prediction" refers to predicting the deterioration status and replacement timing of each part of a vehicle (e.g., engine oil, brake pads, tires, etc.) based on driving data and external information.

[1471] "Maintenance timing suggestion" refers to the process of notifying the user of the timing for replacement or inspection of each part of the car based on the results of part wear prediction.

[1472] "Suggesting gas stations" refers to a process of specifying and suggesting gas stations that the user should stop at to refuel based on the current remaining fuel amount and fuel consumption.

[1473] "Providing feedback" means notifying repair shops and dealers of the necessary information depending on the degree of maintenance required, and encouraging them to prepare the appropriate service and parts.

[1474] "Means for recognizing emotional states" refers to technology that recognizes a user's emotional states, such as stress, impatience, and anxiety, by analyzing the user's voice and facial expressions.

[1475] The "means for providing appropriate feedback" refers to a process of providing advice or suggestions to reduce the user's stress or anxiety based on the user's emotional state.

[1476] System Configuration

[1477] This invention is a system including means for collecting driving data, means for acquiring external information, means for predicting part wear based on the driving data and external information, means for suggesting maintenance times to the user based on the results of the part wear prediction, means for suggesting gas stations based on the current remaining fuel level and consumption, means for providing feedback to maintenance companies and dealers according to the degree of need for maintenance, and means for recognizing the emotional state of the user and providing appropriate feedback.

[1478] Data collection

[1479] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[1480] Obtaining external information

[1481] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[1482] Wear prediction

[1483] The server uses an AI model to predict wear and tear on each part based on collected driving data, external information, and the user's emotional state. The data is normalized and input into the AI ​​model. Based on the prediction results, it calculates when each part (e.g., engine oil, brake pads, tires) should be replaced.

[1484] Maintenance schedule suggestions

[1485] The server then recommends maintenance times to the user based on the wear prediction results. Notification messages are sent to the smartphone app or the in-car display. The emotion engine makes suggestions that take into account the user's emotional state.

[1486] Refueling point suggestions

[1487] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[1488] Providing Feedback

[1489] The server provides the results of wear predictions to repair shops and dealers, allowing them to prepare necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[1490] Specific examples

[1491] For example, a device might record that the engine was started 50 times, the lights were on for 120 minutes, the wipers were on for 30 minutes, and the mileage was 1,500 km. Furthermore, the device might recognize that the user is feeling stressed while driving. The server might also acquire information that the current local weather is rainy and the roads are slippery. Furthermore, the server might predict that frequent engine starts and stops will accelerate engine oil deterioration and notify the user that the oil is due for replacement. It might also determine that driving on slippery roads has accelerated tire wear. Furthermore, if the user's stress level is affecting the vehicle's wear, the device might urge the user to take special precautions. Based on this information, the server might notify the user that "it is recommended to change the engine oil" and, at the same time, that "it is recommended to check the tires after the next 1,000 km of driving." Furthermore, if the user is feeling stressed, the server might add a suggestion that "it is recommended to take a break in a place where you can relax while driving."

[1492] Prompt Sentence Examples

[1493] Describe an assistant application that identifies the stress level a user experiences while driving and, based on that, suggests appropriate relaxation or resting spots.

[1494] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1495] Step 1:

[1496] The device collects driving data from the vehicle, such as the number of times the engine is started and stopped, the duration the lights are on, the duration the wipers are on, the number and duration of accelerator and brake operations, the distance traveled, and the route traveled. Additionally, the device is equipped with an emotion engine that analyzes the user's voice and facial expressions to recognize their emotions.

[1497] *Input: various sensor data from the car, user's voice and facial expressions

[1498] * Output: Driving data and user's emotional state

[1499] Step 2:

[1500] The server obtains external information via the Internet, including weather information, road surface conditions, and traffic information. It uses weather APIs and traffic information APIs to collect the necessary data.

[1501] *Input: Data from weather API and traffic information API

[1502] * Output: Weather information, road surface conditions, traffic information

[1503] Step 3:

[1504] The server normalizes the collected driving data and external information and inputs it into an AI model. The AI ​​model uses this data to predict wear and tear on each part. Specifically, driving data (number of engine starts and stops, light on time, etc.) and external information (weather, road conditions, etc.) are input, normalized, and the AI ​​model predicts part deterioration.

[1505] *Input: operation data, external information

[1506] * Output: Part wear prediction results

[1507] Step 4:

[1508] The server then proposes maintenance times to the user based on the wear prediction results. Specifically, it sends a notification message to the user's smartphone or in-car display. The emotion engine makes proposals that take into account the user's emotional state.

[1509] *Input: wear prediction results, user's emotional state

[1510] * Output: Maintenance time suggestion message

[1511] Step 5:

[1512] The server calculates the distance to the destination based on the current gasoline level and consumption, and if refueling is required along the way, suggests suitable gas stations. The server also takes into account the user's emotional state.

[1513] *Input: current remaining gasoline, consumption, driving distance, user's emotional state

[1514] * Output: Gas station suggestion message

[1515] Step 6:

[1516] The server provides the results of wear predictions to repair shops and dealers, allowing them to prepare necessary parts and maintenance in advance. Data from the emotion engine is also used as feedback.

[1517] *Input: wear prediction results, user's emotional state

[1518] * Output: Feedback information for repair shops and dealers

[1519] 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.

[1520] 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.

[1521] 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.

[1522] 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.

[1523] 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 emoti...

Claims

1. a means for collecting driving data; A means for obtaining external information; A means for predicting part wear based on operating data and external information; a means for suggesting a maintenance timing to a user based on the result of the part wear prediction; A means to suggest fuel stations based on current fuel remaining and consumption, A means of providing feedback to repair companies and dealers on the extent of maintenance needs; A system including:

2. 2. The system according to claim 1, wherein part wear prediction is performed using artificial intelligence.

3. 2. The system according to claim 1, wherein the external information includes at least weather information and road surface conditions.

Images