System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring driving AI from a sensor mounted in the vehicle; means for analyzing the acquired driving data based on a generative data model; means for generating advice for improving driving based on an analysis result; means for providing the generated advice to a driver in real time; means for storing a history of the driving data and the advice and visualizing driving performance; and means for providing an incentive for fuel-efficient driving.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, rising fuel costs and worsening environmental problems have made it urgent to reduce fuel consumption. However, it is not easy for ordinary drivers to voluntarily improve fuel efficiency, and it is difficult to maintain an effective driving style. In addition, there are currently limited means to learn specific driving methods for improving fuel efficiency in real time. Therefore, there is a need to present efficient driving methods and aim to improve fuel efficiency. [Means for solving the problem]

[0005] We provide a system that acquires driving data from sensors mounted on vehicles and analyzes that data based on a generative AI model. This system generates advice for driving improvement based on the analysis results and provides it to the driver in real time. It also supports drivers in improving their driving style by saving the driving data and advice history and visualizing driving performance. Furthermore, we incorporate a means to provide incentives for fuel-efficient driving, raising drivers' awareness of improving fuel efficiency. This promotes efficient driving, contributing to improved fuel efficiency and solving environmental problems.

[0006] "Vehicle" means a mechanical device for moving on roads, a means of transportation having an engine, wheels, and other devices.

[0007] A "sensor" is a device that measures physical or chemical quantities and converts them into electrical signals, and is used to detect vehicle speed, acceleration, position information, etc.

[0008] "Driving data" is data that includes speed, acceleration, position information, braking, and other driving-related information as the vehicle moves.

[0009] A "generative AI model" is an artificial intelligence system that is trained using algorithms such as machine learning and deep learning to perform a specific task (such as analyzing driving data).

[0010] "Analysis" is the process of examining collected data to find specific patterns and trends.

[0011] "Advice" is specific instructions or suggestions provided to the driver to improve their driving style and fuel economy.

[0012] "Real-time" refers to a situation in which processing or communication occurs with extremely low latency and the results are immediately available.

[0013] "History" is a record of past driving data and advice that allows you to track fluctuations in driving performance.

[0014] "Visualization" is the process of displaying data in a visual format, such as a graph, chart, or table, to make the information easier to understand.

[0015] An "incentive" is a reward or benefit provided to promote a particular behavior, and in this system, it is given for fuel-efficient driving. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. It also has a means for providing incentives for fuel-efficient driving.

[0038] Data collection

[0039] server

[0040] Driving data is acquired from sensors installed in the vehicle (e.g., speed sensor, acceleration sensor, GPS sensor), which allows the vehicle's speed, acceleration, location information, etc. to be recorded in real time.

[0041] Terminal

[0042] The acquired data is compressed and sent to the server periodically, for example every minute.

[0043] User

[0044] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[0045] Analyzing the data

[0046] server

[0047] The acquired driving data is analyzed using a generative AI model, which learns from past driving data and can extract driving patterns that contribute to improved fuel efficiency.

[0048] As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[0049] Providing advice

[0050] server

[0051] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[0052] Terminal

[0053] Advice sent from the server is provided to the user in real time, using audio guidance and on-screen displays.

[0054] User

[0055] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[0056] History storage and visualization

[0057] server

[0058] The driving data and advice history is stored in a database, which is later used to evaluate driving performance.

[0059] The stored data can be analyzed to calculate statistics and trends.

[0060] Terminal

[0061] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[0062] User

[0063] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[0064] Providing incentives

[0065] server

[0066] A points system is applied to incentive users for fuel-efficient driving. The points are calculated based on the evaluation score of driving data.

[0067] Terminal

[0068] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[0069] User

[0070] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[0071] As a concrete example, driving data is collected while a user is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of times there was sudden acceleration or deceleration, and the distance traveled. The server analyzes this data and provides the user with specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The user then follows the advice and continues driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the user to save on fuel costs and contribute to the environment.

[0072] The above is an embodiment of the present invention.

[0073] The processing flow will be explained below.

[0074] Step 1: Acquiring Sensor Data

[0075] The terminal acquires driving data in real time from various sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.).

[0076] Specific operation: Obtain speed data from the speed sensor every second, obtain location information from the GPS sensor every second, and collect acceleration data from the acceleration sensor.

[0077] Step 2: Compress and send the data

[0078] The terminal compresses the collected driving data at regular intervals (for example, every minute) and transmits it to the server.

[0079] Specific operation: Collected data is compressed into CSV format and sent to the server using HTTPS.

[0080] Step 3: Receiving and storing data

[0081] The server receives the data sent from the terminal and stores it in a database.

[0082] Specific operation: The received data is inserted into a database for analysis (e.g. MongoDB) and stored using the session ID as a key.

[0083] Step 4: Analysis by generative AI model

[0084] The server inputs the stored data into a generative AI model to analyze driving style.

[0085] Specific operation: Data is input into a generative AI model to extract features such as patterns of sudden acceleration and deceleration, average speed, and distance traveled.

[0086] Step 5: Evaluate driving and generate advice

[0087] The server evaluates the driving style based on the analysis results and generates specific advice for improving fuel efficiency.

[0088] Specific behavior: The AI ​​model evaluates the driving style on a scale of 70 / 100 and generates advice such as "avoid sudden acceleration" and "maintain a constant speed."

[0089] Step 6: Submitting Advice

[0090] The server transmits the generated advice to the terminal.

[0091] Specific behavior: Advice is encoded in JSON format and sent to the device via an HTTP POST request.

[0092] Step 7: Viewing Advice

[0093] The device displays the received advice to the user in real time, using various display methods including text, graphics, and audio guidance.

[0094] Specific operation: A text message saying "Avoid sudden acceleration" is displayed on the screen, and the same advice is spoken aloud using voice synthesis.

[0095] Step 8: User execution

[0096] The user checks the advice provided and applies it to their actual driving.

[0097] Specific actions: The user follows the advice and presses the accelerator pedal slowly to avoid sudden acceleration.

[0098] Step 9: Save historical data

[0099] The server stores the data and advice history for each driving session in a database.

[0100] Specific operation: Driving data and generated advice are saved together so that the user can check them later.

[0101] Step 10: Visualize the data

[0102] The server calculates statistics and trends based on historical data and provides the data in a format that can be visually confirmed by the user.

[0103] What it does: Create monthly reports of driving data and generate graphs and charts.

[0104] Step 11: Send visualization data

[0105] The server transmits the generated visualization data to the terminal.

[0106] Specific behavior: Convert the report to PDF format and send it to the device.

[0107] Step 12: View the report

[0108] The terminal displays the received report on a user interface.

[0109] What it does: Opens the monthly report on the device and displays past driving data as graphs and charts.

[0110] Step 13: Calculate and award incentives

[0111] The server calculates incentives (points) based on the driving evaluation and assigns them to the user's account.

[0112] Specific operation: Calculate incentive points based on the evaluation score and add 50 points to the user ID.

[0113] Step 14: Points Notification

[0114] The terminal notifies the user that the points have been awarded.

[0115] Specific behavior: Display a pop-up notification such as "50 eco-driving points have been awarded."

[0116] Step 15: Use your points

[0117] Users can check their accumulated points and use them for special offers and discounts at partner stores.

[0118] Specific operation: Check points through the terminal and use them for discounts at online shops.

[0119] Example 1

[0120] 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."

[0121] In order to achieve efficient fuel consumption and reduce environmental impact, a system is needed that enables drivers to accurately understand and practice how to drive. However, conventional systems do not adequately process driving data in real time, which can delay feedback to the driver, making it difficult to improve driving efficiency. In addition, there was a lack of effective visualization of driving data and the provision of incentives, making it difficult to improve driver motivation.

[0122] 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.

[0123] In this invention, the server includes a means for acquiring driving data from multiple sensors installed in the vehicle, a means for analyzing the acquired driving data using a generative AI model, and a means for generating specific advice for improving driving based on the analysis results. This allows for real-time acquisition of driving data and analysis using the generative AI model, enabling immediate and specific feedback to the driver. Furthermore, adding a means for saving the driving data and advice history, visualizing driving performance, and providing incentives for fuel-efficient driving can improve the driver's motivation and achieve efficient driving.

[0124] The "multiple sensors" refer to a number of sensor devices, such as a speed sensor, an acceleration sensor, and a GPS sensor, that are mounted on a vehicle to collect driving data of the vehicle.

[0125] "Driving data" refers to information about vehicle driving, such as speed, acceleration, location information, distance traveled, and driving behavior, and is data acquired from multiple sensors.

[0126] A "generative AI model" is an artificial intelligence model used to learn from past driving data and analyze driving patterns and fuel efficiency.

[0127] "Analysis" refers to the process of using generative AI models to identify driving patterns and styles based on captured driving data.

[0128] "Specific advice" refers to advice that the generative AI model provides to the driver based on the analysis of driving data to improve driving efficiency and reduce fuel consumption.

[0129] "Real-time" refers to the time frame in which data is acquired and processed immediately, with little or no delay, to provide results.

[0130] "History" refers to data that records and saves driving data acquired in the past and advice generated in chronological order.

[0131] "Visualization" refers to the process of displaying collected driving data and advice history in visual formats such as graphs and charts to make the data easier for drivers to understand.

[0132] "Incentives" are benefits or rewards offered to drivers to encourage efficient driving.

[0133] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from multiple sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. It also has a means for providing incentives for fuel-efficient driving.

[0134] The server acquires driving data in real time from multiple sensors, including speed sensors, acceleration sensors, and GPS sensors. This driving data includes speed, acceleration, location information, distance traveled, driving behavior, and more. The terminal also compresses the acquired driving data at regular intervals (for example, every minute) and sends it to the server via the Internet. The driver does not need to perform any special operations; data is collected automatically simply by driving normally.

[0135] Once the data is sent to the server, the server analyzes the collected driving data based on a generative AI model. The generative AI model learns from past driving data and extracts driving patterns that contribute to improving fuel efficiency. This analysis process begins when the server provides a prompt to the generative AI model. For example, the server might pass the prompt to the model: "Please generate optimal fuel efficiency improvement advice from this driving data."

[0136] Based on the analysis results generated by the generative AI model, the server provides specific advice to the driver in real time, such as "avoid sudden acceleration" or "maintain a constant speed," allowing the driver to immediately improve their driving style.

[0137] Furthermore, the server stores driving data and the history of advice provided in a database. The stored history is later used to evaluate driving performance and is visualized through the terminal. The terminal displays past driving data in graphs and charts and provides it to the driver. The driver can review this data to objectively evaluate their own driving style and obtain specific clues for improvement.

[0138] To encourage fuel-efficient driving, the server applies a point system and awards points for fuel-efficient driving. These points are calculated based on the evaluation score of driving data and are offered to drivers as an incentive. The terminal notifies the driver of the awarded points, which the driver can confirm and use for rewards or discounts. This motivates the driver to drive more efficiently.

[0139] As a concrete example, driving data is collected from a vehicle traveling on a highway. The driving data includes the number of times the speed exceeded 100 km / h, the number of times sudden acceleration or deceleration occurred, and the distance traveled. The server analyzes this data and provides the driver with specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the driver to save on fuel costs and contribute to the environment.

[0140] An example prompt is, "Based on your driving data from the past week, please provide some advice on how to maximize fuel economy on your next trip."

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

[0142] Step 1:

[0143] The server acquires driving data from multiple sensors installed in the vehicle. Input data from the sensors includes speed, acceleration, and location information. The server collects this data in real time and stores it in a database. Specifically, it interprets data packets sent from the sensors and stores them in a structured format.

[0144] Step 2:

[0145] The server processes the acquired driving data in batches at regular intervals. Specifically, it compresses the data and prepares it for transfer to the terminal. The input raw data is reduced in size using a compression algorithm to make efficient use of network bandwidth. The compressed data is generated as output.

[0146] Step 3:

[0147] The terminal receives the compressed data sent from the server and performs decompression processing. The input data is compressed driving data, and this decompression processing reconstructs the original driving data. The reconstructed data is sent back to the server or temporarily stored on the terminal.

[0148] Step 4:

[0149] The server analyzes the decompressed driving data based on the generative AI model. The input data is the decompressed driving data, which undergoes a process of being input into the generative AI model. Specifically, a prompt statement is passed to the generative AI model and analysis is performed. The prompt statement used is "Please generate optimal fuel economy improvement advice from this data." The analysis results output insights into driving patterns and fuel economy improvement.

[0150] Step 5:

[0151] The server generates specific driving improvement advice based on the analysis results obtained from the generative AI model. The input data is the analysis results, from which information such as the number of sudden accelerations and decelerations and average speed is extracted. Specific operations involve applying an algorithm that generates advice statements based on conditions. For example, the output might be, "Maintaining a constant speed will improve fuel efficiency."

[0152] Step 6:

[0153] The terminal receives advice sent from the server and provides it to the driver in real time. The input data is advice text, which is processed to be displayed as a voice guide or on a display. Specifically, the advice is played back as a voice using a speech synthesis engine, or displayed as text on a display.

[0154] Step 7:

[0155] The server stores driving data and advice history in a database. The input data is raw driving data and advice history, which is stored in a structured format. The stored data is later analyzed to provide statistics and trends as output.

[0156] Step 8:

[0157] The terminal visualizes the driving data and advice history stored in the database and provides it to the user. The input data is the stored history data, and a visualization algorithm is applied to display it in graph or chart format. Specifically, the terminal uses a visualization library to generate graphs and charts and display them to the user.

[0158] Step 9:

[0159] The server applies a points system to incentive users for fuel-efficient driving. The input data is the evaluation score, and the server applies a points calculation algorithm to calculate points. The calculated points are obtained as output and added to the user profile.

[0160] Step 10:

[0161] The device receives the notification of point award sent from the server and notifies the user. The input data is point information, and processing is performed to notify the user of this. Specifically, the device's notification function is used to display a message indicating that points have been awarded, or the notification is sent via an application.

[0162] Step 11:

[0163] Users can check the points they have earned and use them for special offers or discounts. The input data is point information, which is evaluated and used for specific services or products. Specific operations include using points to receive discounts at online stores or participating in point exchange programs.

[0164] (Application example 1)

[0165] 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."

[0166] The present invention relates to a system for improving vehicle driving efficiency and reducing fuel consumption. However, conventional systems do not provide advice to drivers in real time, and it is difficult for drivers to intuitively understand the advice. Furthermore, there is a problem that the system does not provide sufficient incentives for fuel-efficient driving, which reduces driver motivation.

[0167] 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.

[0168] In this invention, the server includes means for acquiring driving data from sensors mounted on the vehicle, means for analyzing the acquired driving data based on a generative AI model, means for generating advice for improving driving based on the analysis results, means for providing the generated advice to the driver in real time, means for displaying the driving data on smart glasses or a head-mounted display to visualize it for the driver, means for saving the driving data and advice history and visualizing driving performance, and means for providing incentives for fuel-efficient driving. This allows the driver to receive intuitive advice in real time, thereby increasing their motivation to drive fuel-efficiently.

[0169] "Sensors mounted on a vehicle" are devices for acquiring information such as the vehicle's speed, acceleration, and location.

[0170] "Driving data" refers to various information related to driving, such as vehicle speed, acceleration, and location information.

[0171] A "generative AI model" is an artificial intelligence model that analyzes collected driving data and extracts patterns to improve fuel efficiency and driving.

[0172] "Provided in real time" means that advice is provided instantly while driving, without delay.

[0173] "Smart glasses and head-mounted displays" refer to wearable devices that drivers wear to display driving advice in real time as visual information.

[0174] "Storing and visualizing history" means recording past driving data and advice information and displaying it in a format that can be easily referenced later.

[0175] "Providing incentives" means offering rewards such as points or perks for fuel-efficient driving.

[0176] An embodiment of the present invention is described below. It is a system for improving driving efficiency in a vehicle and reducing fuel consumption. This system acquires driving data from sensors installed in the vehicle, analyzes it based on a generative AI model, and provides advice to the driver in real time. It also stores the driving data and advice history, visualizes driving performance, and provides incentives for fuel-efficient driving.

[0177] Data collection

[0178] server

[0179] Driving data is acquired from sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.), which allows speed, acceleration, location information, etc. to be recorded in real time.

[0180] Terminal

[0181] The acquired data is compressed and sent to the server periodically, for example, every minute.

[0182] User

[0183] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[0184] Analyzing the data

[0185] server

[0186] The acquired driving data is analyzed using a generative AI model. By learning from past driving data, this model can extract driving patterns that contribute to improved fuel efficiency. As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[0187] Providing advice

[0188] server

[0189] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[0190] Terminal

[0191] Advice sent from the server is provided to the user in real time using audio guidance and on-screen displays using smart glasses or a head-mounted display.

[0192] User

[0193] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[0194] History storage and visualization

[0195] server

[0196] Driving data and advice history is stored in a database. This data is later used to evaluate driving performance. The stored data can also be analyzed to calculate statistics and trends.

[0197] Terminal

[0198] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[0199] User

[0200] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[0201] Providing incentives

[0202] server

[0203] A points system is applied to incentive users for fuel-efficient driving. The points are calculated based on the evaluation score of driving data.

[0204] Terminal

[0205] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[0206] User

[0207] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[0208] Specific examples

[0209] While a user is driving on a highway, driving data is collected. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data and provides specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The user can then follow the advice and continue driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the user to save on fuel costs and contribute to the environment.

[0210] Example prompt sentence:

[0211] "Generate advice to improve fuel efficiency for the driver based on the number of times the speed reached 110 km / h and the number of times the acceleration exceeded 3 m / s^2."

[0212] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0213] Step 1:

[0214] Input: Driving data obtained from sensors installed in the vehicle (speed, acceleration, position information, etc.)

[0215] Processing: Sensor data collection. This data is recorded in real time from the vehicle's speed sensor, acceleration sensor, and GPS sensor. The collected data is temporarily stored on the device.

[0216] Output: Raw driving data is saved to the device.

[0217] Step 2:

[0218] Input: Driving data stored on the device

[0219] Processing: The terminal periodically compresses the driving data and sends it to the server. This transmission is performed, for example, every minute. The compressed data is sent to the server via a communication line.

[0220] Output: Compressed driving data is sent to the server.

[0221] Step 3:

[0222] Input: Compressed driving data sent to the server

[0223] Processing: The server decompresses the received data and analyzes it based on the generative AI model. For analysis, an AI model (e.g., TensorFlow) that has learned from past driving data is used. Driving patterns such as sudden acceleration, sudden deceleration, average speed, and number of stops are extracted.

[0224] Output: Analysis results are generated.

[0225] Step 4:

[0226] Input: Analysis results

[0227] Processing: Based on the analysis results, the server generates specific advice for improving fuel efficiency. The generated advice might be, for example, "avoid sudden acceleration" or "maintain a constant speed." The analysis results are input into the generative AI model using prompt statements, and appropriate advice is generated.

[0228] Output: Fuel economy improvement advice is generated.

[0229] Step 5:

[0230] Input: Fuel economy improvement advice

[0231] Processing: The server sends the generated advice to the device, which then provides the advice to the driver in real time via smart glasses or a head-mounted display.

[0232] Output: Advice is displayed on the driver's device.

[0233] Step 6:

[0234] Input: Driver behavior data

[0235] Action: The user checks the provided advice and applies it to their driving. For example, they should try to avoid sudden acceleration and accelerate slowly.

[0236] Output: Driver behavior improves and driving data changes.

[0237] Step 7:

[0238] Input: Improved driving data and advice history

[0239] Processing: The server stores the driving data and advice history in a database, which is later used to evaluate driving performance.

[0240] Output: Driving data and advice history are stored in a database.

[0241] Step 8:

[0242] Input: Stored driving data and advice history

[0243] Processing: The server analyzes the stored data, calculates statistics and trends, and presents this data to the user in visualizations (graphs, charts, etc.).

[0244] Output: Visualized driving data and advice history are displayed on the terminal.

[0245] Step 9:

[0246] Input: visualized driving data and advice history

[0247] Processing: The user reviews the provided data and objectively evaluates their driving style. They learn effective driving techniques and apply them to future driving. For example, they understand which driving techniques have a positive impact on fuel economy.

[0248] Output: User's driving style is evaluated and fed back for the next drive.

[0249] Step 10:

[0250] Input: Evaluated driving data and points system

[0251] Processing: The server calculates points for fuel-efficient driving and awards incentives to the user. Points are calculated based on the evaluation score of the driving data. The terminal notifies the user that points have been awarded and applies the points to the connected incentive program.

[0252] Output: The user is given an incentive and notified.

[0253] 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.

[0254] This invention relates to a system for improving driving efficiency and reducing fuel consumption in vehicles. The system acquires driving data from sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. Furthermore, it has a means for providing incentives for fuel-efficient driving and incorporates an emotion engine that recognizes the user's emotions.

[0255] Data collection

[0256] server

[0257] Driving data is acquired from sensors installed in the vehicle (e.g., speed sensor, acceleration sensor, GPS sensor), which allows the vehicle's speed, acceleration, location information, etc. to be recorded in real time.

[0258] Terminal

[0259] The acquired data is compressed and sent to the server periodically, for example every minute.

[0260] User

[0261] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[0262] Analyzing the data

[0263] server

[0264] The acquired driving data is analyzed using a generative AI model, which learns from past driving data and can extract driving patterns that contribute to improved fuel efficiency.

[0265] As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[0266] Providing advice

[0267] server

[0268] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[0269] Terminal

[0270] Advice sent from the server is provided to the user in real time, using audio guidance and on-screen displays.

[0271] User

[0272] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[0273] User Emotion Recognition

[0274] Terminal

[0275] Using sensors such as cameras and microphones installed in the vehicle, the system analyzes the driver's emotions from facial expressions, tone of voice, etc. This determines whether the driver is feeling stressed or relaxed.

[0276] server

[0277] The acquired emotional data is analyzed to understand the user's emotional state, which is then used to adjust the content of advice and the form of incentives.

[0278] History storage and visualization

[0279] server

[0280] The driving data and advice history is stored in a database, which is later used to evaluate driving performance.

[0281] The stored data can be analyzed to calculate statistics and trends.

[0282] Terminal

[0283] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[0284] User

[0285] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[0286] Advice adjustment

[0287] server

[0288] The emotion engine adjusts the content and tone of advice based on the user's emotions. For example, if the user is feeling stressed, the advice will be given in a calmer tone.

[0289] Terminal

[0290] Providing tailored advice to users in real time.

[0291] Providing incentives

[0292] server

[0293] The type of incentive provided is adjusted based on the emotions recognized by the emotion engine. A points system is applied to reward fuel-efficient driving, and the points are calculated based on the evaluation score of the driving data.

[0294] Terminal

[0295] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[0296] User

[0297] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[0298] As a concrete example, driving data is collected while a driver is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data to understand the driver's emotional state. If the driver is feeling stressed, the server provides specific advice in a calm tone, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining an appropriate speed, thereby improving fuel efficiency. Furthermore, if the driver is determined to be relaxed, incentives can be actively provided to further motivate them. This allows users to save on fuel costs and contribute to the environment.

[0299] The above is an embodiment of the present invention.

[0300] The processing flow will be explained below.

[0301] Step 1: Acquiring Sensor Data

[0302] The terminal acquires driving data in real time from various sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.).

[0303] Specific operation: Obtain speed data from the speed sensor every second, obtain location information from the GPS sensor every second, and collect acceleration data from the acceleration sensor.

[0304] Step 2: Compress and send the data

[0305] The terminal compresses the collected driving data at regular intervals (for example, every minute) and transmits it to the server.

[0306] Specific operation: Collected data is compressed into CSV format and sent to the server using HTTPS.

[0307] Step 3: Receiving and storing data

[0308] The server receives the data sent from the terminal and stores it in a database.

[0309] Specific operation: The received data is inserted into a database for analysis (e.g. MongoDB) and stored using the session ID as a key.

[0310] Step 4: Analysis by generative AI model

[0311] The server inputs the stored data into a generative AI model to analyze driving style.

[0312] Specific operation: Data is input into a generative AI model to extract features such as patterns of sudden acceleration and deceleration, average speed, and distance traveled.

[0313] Step 5: Emotion Recognition with the Emotion Engine

[0314] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from facial expressions, tone of voice, etc.

[0315] Specific operation: Using a facial expression recognition algorithm, analyzes the user's facial expression data to determine emotions such as anger, joy, stress, etc. Analyzes audio data from the microphone to complement the emotional state.

[0316] Step 6: Evaluate driving and generate advice

[0317] The server evaluates the driver's driving style based on the analysis results and generates specific advice for improving fuel efficiency, incorporating the results of the emotion engine.

[0318] Specific behavior: If the AI ​​model evaluates the driving style as 70 / 100 and the user feels stressed, it generates advice in a gentle tone such as "avoid sudden acceleration" and "maintain a constant speed."

[0319] Step 7: Submitting Advice

[0320] The server transmits the generated advice to the terminal.

[0321] Specific behavior: Advice is encoded in JSON format and sent to the device via an HTTP POST request.

[0322] Step 8: Viewing Advice

[0323] The device displays the received advice to the user in real time, using various display methods including text, graphics, and audio guidance.

[0324] Specific operation: A text message saying "Avoid sudden acceleration" is displayed on the screen, and the same advice is spoken aloud using voice synthesis.

[0325] Step 9: User execution

[0326] The user checks the advice provided and applies it to their actual driving.

[0327] Specific actions: The user follows the advice and presses the accelerator pedal slowly to avoid sudden acceleration.

[0328] Step 10: Save historical data

[0329] The server stores the data and advice history for each driving session in a database.

[0330] Specific operation: Driving data and generated advice are saved together so that the user can check them later.

[0331] Step 11: Visualize the data

[0332] The server calculates statistics and trends based on historical data and provides the data in a format that can be visually confirmed by the user.

[0333] What it does: Create monthly reports of driving data and generate graphs and charts.

[0334] Step 12: Send visualization data

[0335] The server transmits the generated visualization data to the terminal.

[0336] Specific behavior: Convert the report to PDF format and send it to the device.

[0337] Step 13: View the report

[0338] The terminal displays the received report on a user interface.

[0339] What it does: Opens the monthly report on the device and displays past driving data as graphs and charts.

[0340] Step 14: Calculate and award incentives

[0341] The server calculates incentives (points) based on the driving evaluation and assigns them to the user's account, taking into account the results of the emotion engine.

[0342] Specific operation: Incentive points are calculated based on the evaluation score, and additional points are awarded for less stressful driving.

[0343] Step 15: Points Notification

[0344] The terminal notifies the user that the points have been awarded.

[0345] Specific behavior: Display a pop-up notification such as "50 eco-driving points have been awarded."

[0346] Step 16: Use your points

[0347] Users can check their accumulated points and use them for special offers and discounts at partner stores.

[0348] Specific operation: Check points through the terminal and use them for discounts at online shops.

[0349] Example 2

[0350] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0351] There are limitations to methods for improving driving efficiency and reducing fuel consumption. Existing technologies lack real-time driver advice and incentive systems that take into account the driver's emotional state. Furthermore, drivers lack the opportunity and means to objectively evaluate and improve their own driving style, making it difficult to comprehensively improve their driving performance.

[0352] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0353] In this invention, the server includes: means for acquiring driving data from sensors installed in the vehicle; means for periodically compressing the acquired driving data and transmitting the compressed data to the server; means for analyzing the acquired driving data using a generative AI model; means for generating specific advice for improving driving based on the analysis results; means for providing the generated advice to the driver in real time; means for storing the driving data and advice history in a database and visualizing driving performance; means for adjusting the content and tone of the advice using an emotion engine that recognizes the user's emotions; and means for providing incentives for fuel-efficient driving. This allows the system to analyze driving data in real time and provide specific advice to the driver, thereby improving driving performance and fuel efficiency. Furthermore, the emotion recognition function can be used to reduce driver stress and improve driving efficiency.

[0354] "Driving data" refers to data such as speed, acceleration, and position information obtained from sensors installed in the vehicle.

[0355] "Generative AI model" refers to an artificial intelligence model that learns from past driving data and analyzes driving patterns that contribute to improved fuel efficiency.

[0356] "Advice" refers to instructions or suggestions for improving driving that are generated based on the analysis of driving data and provided to the driver.

[0357] "Real-time" refers to a situation where data is acquired, analyzed, and advice is provided almost simultaneously, with very little delay.

[0358] "Emotion engine" refers to technology that analyzes emotions from the user's facial expressions, tone of voice, and other information obtained from sensors installed in the vehicle.

[0359] "Incentives" refer to points or rewards awarded to encourage improved driving performance and more fuel-efficient driving.

[0360] "Database" refers to an information system for storing and managing driving data and advice history.

[0361] "Sensor" refers to a device installed in a vehicle and used to acquire driving data, including speed sensors, acceleration sensors, and GPS sensors.

[0362] "Compression" refers to the process of reducing the size of collected data so that it can be stored or transmitted efficiently.

[0363] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from sensors mounted on the vehicle and analyzes the data based on a generative AI model to provide real-time advice to the driver. Specifically, hardware such as a speed sensor, an acceleration sensor, and a GPS sensor is used. The software used includes the AI ​​model (e.g., TensorFlow or PyTorch) required to analyze the data.

[0364] Data collection

[0365] The server centrally collects driving data acquired from the vehicle's speed sensor, acceleration sensor, GPS sensor, etc. This allows speed, acceleration, location information, etc. to be recorded in real time.

[0366] The terminal compresses the collected data and periodically (for example, every minute) transmits it to the server. The transmitted data is in a compressed format (for example, ZIP format) and is uploaded to the server using an HTTP POST request.

[0367] The user simply drives as usual and data is collected automatically, with no special operations or confirmations required.

[0368] Analyzing the data

[0369] The server analyzes the acquired driving data based on a generative AI model. The generative AI model learns from past driving data and can extract driving patterns that contribute to improving fuel efficiency. As a result of the analysis, it can identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops. TensorFlow and PyTorch are used as AI libraries for the analysis.

[0370] Providing advice

[0371] Based on the analysis results, the server generates specific advice for improving fuel efficiency, such as "avoid sudden acceleration" and "maintain a constant speed."

[0372] The device provides the user with advice sent from the server in real time, using voice guidance (using a speech synthesis engine) and on-screen displays.

[0373] The user can check the provided advice and apply it to their driving. For example, they can learn to refrain from sudden acceleration and to step on the accelerator slowly.

[0374] User Emotion Recognition

[0375] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from their facial expressions and tone of voice, determining whether they are stressed or relaxed. Facial recognition software and voice analysis software are used.

[0376] The server analyzes the acquired emotional data to understand the user's emotional state, which is then used to adjust the content of advice and the form of incentives.

[0377] History storage and visualization

[0378] The server stores driving data and advice history in a database, which allows for later evaluation of driving performance. SQL is typically used to manage the database.

[0379] The device visualizes the stored driving data and provides it to the user. Graph generation libraries such as Chart.js and D3.js are used to display historical driving data using graphs and charts.

[0380] Users can view the visualized data and objectively evaluate their own driving style, thereby understanding how their driving habits affect fuel economy.

[0381] Advice adjustment

[0382] The server adjusts the content and tone of advice based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, the server will provide advice in a calm tone. Emotion data is used to select templates for advice messages and adjust the tone.

[0383] The device provides tailored advice to the user in real time, and if the user is not stressed, the advice is provided in a normal tone.

[0384] Providing incentives

[0385] The server adjusts the type of incentive to provide based on the emotions recognized by the emotion engine. A points system is applied to fuel-efficient driving to provide incentives to users. These points are calculated based on the evaluation score of the driving data. An evaluation algorithm is used to calculate and apply the points.

[0386] The terminal notifies the user that points have been awarded and applies the points to an incentive program, which is integrated into the incentive program using an API.

[0387] Users can view the points they have earned and use them for rewards and discounts, which motivates them to drive more efficiently.

[0388] Specific examples

[0389] For example, driving data is collected while a driver is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data to understand the driver's emotional state. If the driver appears stressed, the server provides specific advice in a calm tone, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining an appropriate speed, thereby improving fuel efficiency. Furthermore, if the driver is determined to be relaxed, incentives can be actively provided to further motivate them. This allows users to save on fuel costs and contribute to the environment.

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

[0391] Step 1:

[0392] Acquire driving data from sensors installed in the vehicle

[0393] The server acquires driving data in real time from the vehicle's speed sensor, acceleration sensor, and GPS sensor. Specifically, it continuously monitors the data stream from each sensor and converts the collected data into a specified format (for example, JSON format).

[0394] Input: Speed, acceleration, position information

[0395] Output: Format converted operation data

[0396] Step 2:

[0397] Compression and transmission of driving data

[0398] The terminal compresses the collected data and sends it to the server periodically (for example, every minute). Specifically, the terminal compresses the collected data in ZIP format or similar and sends an HTTP POST request to the specified server endpoint.

[0399] Input: Format converted operation data

[0400] Output: Compressed driving data

[0401] Step 3:

[0402] Analysis of driving data

[0403] The server analyzes the received driving data based on the generated AI model. Specifically, the data is input into the AI ​​model to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops in real time.

[0404] Input: Decompressed driving data

[0405] Output: Driving style analysis results

[0406] Step 4:

[0407] Generating Advice

[0408] The server generates specific advice for improving fuel efficiency based on the analysis results. Specifically, it generates advice messages based on templates and stores them in a database.

[0409] Input: Driving style analysis results

[0410] Output: Specific advice message

[0411] Step 5:

[0412] Providing advice

[0413] The device provides the user with advice sent from the server in real time, specifically by generating audio guidance using a speech synthesis engine and displaying the advice visually on a display.

[0414] Input: Specific advice message

[0415] Output: Providing advice to the user (audio and display)

[0416] Step 6:

[0417] Reflecting user driving

[0418] The user confirms the advice provided and applies it to their driving, specifically by operating the accelerator and adjusting speed according to the advice.

[0419] Input: Specific advice

[0420] Output: Driving operation based on advice

[0421] Step 7:

[0422] Emotional Data Analysis

[0423] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from their facial expressions and tone of voice. Specifically, it uses facial recognition software and voice analysis software to analyze the user's emotions in real time.

[0424] Input: User's facial expression data, tone of voice

[0425] Output: Parsed emotion data

[0426] Step 8:

[0427] Tailoring advice based on emotions

[0428] The server adjusts the content and tone of advice based on the analyzed emotional data. Specifically, it references the emotional data to select a template for the advice message and adjust the tone.

[0429] Input: Parsed emotion data

[0430] Output: Adjusted advice message

[0431] Step 9:

[0432] Incentive calculation and awarding

[0433] The server applies a point system to fuel-efficient driving and gives incentives to users. Specifically, it calculates points based on driving data and evaluation scores and stores them in a database.

[0434] Input: Driving data, evaluation score

[0435] Output: Incentive points

[0436] Step 10:

[0437] Incentive notification and use

[0438] The terminal notifies the user that points have been awarded and applies them to incentive programs. The user can then check the points they have earned and use them for rewards and discounts.

[0439] Input: Incentive points

[0440] Output: Incentive notification, point usage

[0441] (Application example 2)

[0442] 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."

[0443] Conventional vehicle driver assistance systems focused on collecting and analyzing driving data, and were unable to recognize and respond to driver emotions in real time. This made it difficult to respond appropriately to the driver's stress state and emotional changes, leading to a demand for further improvements in driving efficiency and ensuring safety. There was also a lack of incentive systems that could simultaneously improve fuel efficiency and increase driver motivation.

[0444] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring driving data from sensors installed in the vehicle, means for analyzing the acquired driving data using a generative AI model, means for generating advice for improving driving based on the analysis results, means for providing the generated advice to the driver in real time, means for saving the driving data and advice history and visualizing driving performance, means for providing incentives for fuel-efficient driving, means for recognizing the driver's emotions using sensors such as an installed camera and microphone, and means for adjusting the content and tone of the advice based on the emotional data. This makes it possible to grasp the driver's emotional state in real time and provide appropriate advice depending on the situation. This reduces driver stress, improves driving efficiency, and further reduces costs and protects the environment by improving fuel efficiency.

[0445] "Vehicle sensors" refer to various sensors installed in a vehicle, such as speed sensors, acceleration sensors, and GPS sensors, and have the function of acquiring driving data.

[0446] A "generative AI model" is an artificial intelligence model that learns from past driving data and analyzes and predicts driving patterns.

[0447] "Analysis means" refers to a device or software that analyzes acquired driving data based on a generative AI model and identifies driving tendencies and patterns.

[0448] The "advice generating means" has a function of automatically generating specific advice for improving driving based on the analysis results obtained by the analysis means.

[0449] The "real-time providing means" refers to a method or system for immediately providing the generated advice to the driver, and includes voice guidance and display.

[0450] The "history storage means" refers to a storage device such as a memory or database that records and stores the driving data and advice history so that it can be referenced at a later date.

[0451] The "driving performance visualization means" has a function to display the saved driving data and advice history in a visual format such as a graph or chart so that the driver can check it.

[0452] An "incentive granting means" is a method or system that provides points or rewards for fuel-efficient driving, and serves to keep drivers motivated.

[0453] The "emotion recognition means" has the function of analyzing the driver's facial expression and tone of voice using sensors such as cameras and microphones mounted on the vehicle, and identifying the driver's emotional state.

[0454] The "tone adjustment means" has a function of appropriately adjusting the content and tone of advice based on the emotion data obtained by the emotion recognition means.

[0455] System Overview

[0456] This system is realized by combining multiple sensors installed in the vehicle, a server, and the driver's device such as a smartphone or tablet. Its main functions include collecting and analyzing driving data, providing real-time advice, recognizing emotions, storing and visualizing history, and providing incentives.

[0457] Data collection

[0458] The server acquires driving data from various sensors installed in the vehicle, such as speed sensors, acceleration sensors, and GPS sensors. This data is sent to the server in real time via the terminal. To collect particularly accurate data, external sensor devices connected via Bluetooth or Wi-Fi can also be used.

[0459] Data analysis

[0460] The server analyzes the acquired driving data based on a generative AI model. The generative AI model learns from past driving data to identify driving trends such as sudden acceleration and deceleration, average speed, and number of stops. This allows it to extract driving patterns that lead to improved fuel efficiency.

[0461] Providing advice

[0462] The server generates appropriate driving advice based on the analysis results. The advice is provided to the driver in real time via the terminal. The terminal communicates the advice to the driver using voice guidance and on-screen displays.

[0463] User Emotion Recognition

[0464] The device uses the smartphone or tablet's camera and microphone to analyze the driver's facial expressions and tone of voice to recognize their emotional state. The server analyzes the acquired emotional data and evaluates the user's emotional state. Machine learning models are used to improve the accuracy of emotion recognition.

[0465] Advice adjustment

[0466] The server adjusts the content and tone of the advice based on the driver's emotional data. For example, if the driver is feeling stressed, the server will provide advice in a calm tone such as, "Drive calmly. Avoid sudden acceleration to improve fuel efficiency."

[0467] History storage and visualization

[0468] The server stores driving data and advice history in a database. The device visualizes the stored data in graphs and charts and provides them to the driver, allowing the driver to review past driving data and objectively evaluate their own driving style.

[0469] Providing incentives

[0470] The server provides a function to award points for fuel-efficient driving. The terminal notifies the driver that points have been awarded and allows the driver to exchange the points for rewards in cooperation with an incentive program. This motivates the driver to drive more fuel-efficiently.

[0471] Specific examples

[0472] While the driver is driving on the highway, the system collects speed and acceleration data in real time and sends it to a server. The server then analyzes the collected data using a generative AI model, taking into account the driver's facial expressions and voice data, and provides specific advice such as "maintaining a constant speed will improve fuel efficiency." Additionally, if the driver is relaxed, points are actively awarded to maintain the driver's motivation.

[0473] Prompt Sentence Examples

[0474] The driver's emotion has been identified as "Angry." Provide driving advice in a calm tone. For example, "Drive calmly. Avoiding sudden acceleration will improve fuel economy."

[0475] This allows for driving assistance that takes the driver's emotional state into appropriate consideration.

[0476] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0477] Step 1:

[0478] Input: Driving data from the vehicle's speed sensor, acceleration sensor, and GPS sensor.

[0479] Example: Obtaining speed, acceleration, position information, etc.

[0480] Processing: The device collects and compresses these driving data in real time.

[0481] Output: Compressed driving data.

[0482] Step 2:

[0483] Input: Compressed driving data.

[0484] Example: Collected data, such as speed, acceleration, and position per second.

[0485] Processing: The device periodically transmits the compressed driving data to the server, for example, every minute.

[0486] Output: Driving data sent to the server.

[0487] Step 3:

[0488] Input: Driving data sent to the server.

[0489] Example: Data received by the server, such as speed, acceleration, and location information from the start to the end of a driving session.

[0490] Processing: The server analyzes the received driving data based on the generative AI model.

[0491] Output: Driving style analysis results (sudden acceleration, sudden deceleration, average speed, number of stops, etc.).

[0492] Step 4:

[0493] Input: Analysis results.

[0494] Examples include: number of sudden accelerations, average speed, number of stops, etc.

[0495] Processing: The server generates appropriate driving advice based on the analysis results, such as "avoid sudden acceleration" or "maintain a constant speed."

[0496] Output: The generated driving advice.

[0497] Step 5:

[0498] Input: Generated driving advice.

[0499] Examples: Specific advice such as "avoid sudden acceleration" or "maintain a steady speed."

[0500] Processing: The device provides real-time advice to the driver, conveying the advice through voice prompts and on-screen displays.

[0501] Output: Advice provided in a form that the user can understand.

[0502] Step 6:

[0503] Input: Driver facial expressions and tone of voice captured from cameras and microphones.

[0504] Example: Facial images and audio data of a driver while driving.

[0505] Processing: The device performs emotion recognition based on data acquired through the camera and microphone.

[0506] Output: Perceived driver emotional state (anger, joy, stress, etc.).

[0507] Step 7:

[0508] Input: Perceived driver emotional state.

[0509] Example: A driver is identified as "Angry."

[0510] Processing: The server adjusts the content and tone of the advice based on the emotional data. For example, if the user is feeling stressed, the server will provide advice in a calmer tone.

[0511] Output: Tailored advice.

[0512] Step 8:

[0513] Input: Driving data, advice history.

[0514] Example: Data from past driving sessions and advice provided.

[0515] Processing: The server stores the driving data and advice history in a database.

[0516] Output: Driving history and advice history stored in a database.

[0517] Step 9:

[0518] Input: Driving history and advice history stored in a database.

[0519] Example: Visual data formats such as graphs and charts.

[0520] Processing: The device visualizes the stored data and provides it to the driver, for example by providing trend analysis and graphical representations of historical data.

[0521] Output: Visualized driving data and advice history.

[0522] Step 10:

[0523] Input: Driving data rating score.

[0524] Example: Points calculation based on fuel-efficient driving.

[0525] Processing: The server awards points for fuel-efficient driving and links to incentive programs.

[0526] Output: Points awarded and notification to the user.

[0527] 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.

[0528] 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.

[0529] 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.

[0530] [Second embodiment]

[0531] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0532] 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.

[0533] 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).

[0534] 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.

[0535] 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.

[0536] 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).

[0537] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0538] 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.

[0539] 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.

[0540] 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.

[0541] 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.

[0542] 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."

[0543] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. It also has a means for providing incentives for fuel-efficient driving.

[0544] Data collection

[0545] server

[0546] Driving data is acquired from sensors installed in the vehicle (e.g., speed sensor, acceleration sensor, GPS sensor), which allows the vehicle's speed, acceleration, location information, etc. to be recorded in real time.

[0547] Terminal

[0548] The acquired data is compressed and sent to the server periodically, for example every minute.

[0549] User

[0550] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[0551] Analyzing the data

[0552] server

[0553] The acquired driving data is analyzed using a generative AI model, which learns from past driving data and can extract driving patterns that contribute to improved fuel efficiency.

[0554] As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[0555] Providing advice

[0556] server

[0557] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[0558] Terminal

[0559] Advice sent from the server is provided to the user in real time, using audio guidance and on-screen displays.

[0560] User

[0561] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[0562] History storage and visualization

[0563] server

[0564] The driving data and advice history is stored in a database, which is later used to evaluate driving performance.

[0565] The stored data can be analyzed to calculate statistics and trends.

[0566] Terminal

[0567] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[0568] User

[0569] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[0570] Providing incentives

[0571] server

[0572] A points system is applied to incentive users for fuel-efficient driving. The points are calculated based on the evaluation score of driving data.

[0573] Terminal

[0574] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[0575] User

[0576] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[0577] As a concrete example, driving data is collected while a user is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of times there was sudden acceleration or deceleration, and the distance traveled. The server analyzes this data and provides the user with specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The user then follows the advice and continues driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the user to save on fuel costs and contribute to the environment.

[0578] The above is an embodiment of the present invention.

[0579] The processing flow will be explained below.

[0580] Step 1: Acquiring Sensor Data

[0581] The terminal acquires driving data in real time from various sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.).

[0582] Specific operation: Obtain speed data from the speed sensor every second, obtain location information from the GPS sensor every second, and collect acceleration data from the acceleration sensor.

[0583] Step 2: Compress and send the data

[0584] The terminal compresses the collected driving data at regular intervals (for example, every minute) and transmits it to the server.

[0585] Specific operation: Collected data is compressed into CSV format and sent to the server using HTTPS.

[0586] Step 3: Receiving and storing data

[0587] The server receives the data sent from the terminal and stores it in a database.

[0588] Specific operation: The received data is inserted into a database for analysis (e.g. MongoDB) and stored using the session ID as a key.

[0589] Step 4: Analysis by generative AI model

[0590] The server inputs the stored data into a generative AI model to analyze driving style.

[0591] Specific operation: Data is input into a generative AI model to extract features such as patterns of sudden acceleration and deceleration, average speed, and distance traveled.

[0592] Step 5: Evaluate driving and generate advice

[0593] The server evaluates the driving style based on the analysis results and generates specific advice for improving fuel efficiency.

[0594] Specific behavior: The AI ​​model evaluates the driving style on a scale of 70 / 100 and generates advice such as "avoid sudden acceleration" and "maintain a constant speed."

[0595] Step 6: Submitting Advice

[0596] The server transmits the generated advice to the terminal.

[0597] Specific behavior: Advice is encoded in JSON format and sent to the device via an HTTP POST request.

[0598] Step 7: Viewing Advice

[0599] The device displays the received advice to the user in real time, using various display methods including text, graphics, and audio guidance.

[0600] Specific operation: A text message saying "Avoid sudden acceleration" is displayed on the screen, and the same advice is spoken aloud using voice synthesis.

[0601] Step 8: User execution

[0602] The user checks the advice provided and applies it to their actual driving.

[0603] Specific actions: The user follows the advice and presses the accelerator pedal slowly to avoid sudden acceleration.

[0604] Step 9: Save historical data

[0605] The server stores the data and advice history for each driving session in a database.

[0606] Specific operation: Driving data and generated advice are saved together so that the user can check them later.

[0607] Step 10: Visualize the data

[0608] The server calculates statistics and trends based on historical data and provides the data in a format that can be visually confirmed by the user.

[0609] What it does: Create monthly reports of driving data and generate graphs and charts.

[0610] Step 11: Send visualization data

[0611] The server transmits the generated visualization data to the terminal.

[0612] Specific behavior: Convert the report to PDF format and send it to the device.

[0613] Step 12: View the report

[0614] The terminal displays the received report on a user interface.

[0615] What it does: Opens the monthly report on the device and displays past driving data as graphs and charts.

[0616] Step 13: Calculate and award incentives

[0617] The server calculates incentives (points) based on the driving evaluation and assigns them to the user's account.

[0618] Specific operation: Calculate incentive points based on the evaluation score and add 50 points to the user ID.

[0619] Step 14: Points Notification

[0620] The terminal notifies the user that the points have been awarded.

[0621] Specific behavior: Display a pop-up notification such as "50 eco-driving points have been awarded."

[0622] Step 15: Use your points

[0623] Users can check their accumulated points and use them for special offers and discounts at partner stores.

[0624] Specific operation: Check points through the terminal and use them for discounts at online shops.

[0625] Example 1

[0626] 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."

[0627] In order to achieve efficient fuel consumption and reduce environmental impact, a system is needed that enables drivers to accurately understand and practice how to drive. However, conventional systems do not adequately process driving data in real time, which can delay feedback to the driver, making it difficult to improve driving efficiency. In addition, there was a lack of effective visualization of driving data and the provision of incentives, making it difficult to improve driver motivation.

[0628] 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.

[0629] In this invention, the server includes a means for acquiring driving data from multiple sensors installed in the vehicle, a means for analyzing the acquired driving data using a generative AI model, and a means for generating specific advice for improving driving based on the analysis results. This allows for real-time acquisition of driving data and analysis using the generative AI model, enabling immediate and specific feedback to the driver. Furthermore, adding a means for saving the driving data and advice history, visualizing driving performance, and providing incentives for fuel-efficient driving can improve the driver's motivation and achieve efficient driving.

[0630] The "multiple sensors" refer to a number of sensor devices, such as a speed sensor, an acceleration sensor, and a GPS sensor, that are mounted on a vehicle to collect driving data of the vehicle.

[0631] "Driving data" refers to information about vehicle driving, such as speed, acceleration, location information, distance traveled, and driving behavior, and is data acquired from multiple sensors.

[0632] A "generative AI model" is an artificial intelligence model used to learn from past driving data and analyze driving patterns and fuel efficiency.

[0633] "Analysis" refers to the process of using generative AI models to identify driving patterns and styles based on captured driving data.

[0634] "Specific advice" refers to advice that the generative AI model provides to the driver based on the analysis of driving data to improve driving efficiency and reduce fuel consumption.

[0635] "Real-time" refers to the time frame in which data is acquired and processed immediately, with little or no delay, to provide results.

[0636] "History" refers to data that records and saves driving data acquired in the past and advice generated in chronological order.

[0637] "Visualization" refers to the process of displaying collected driving data and advice history in visual formats such as graphs and charts to make the data easier for drivers to understand.

[0638] "Incentives" are benefits or rewards offered to drivers to encourage efficient driving.

[0639] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from multiple sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. It also has a means for providing incentives for fuel-efficient driving.

[0640] The server acquires driving data in real time from multiple sensors, including speed sensors, acceleration sensors, and GPS sensors. This driving data includes speed, acceleration, location information, distance traveled, driving behavior, and more. The terminal also compresses the acquired driving data at regular intervals (for example, every minute) and sends it to the server via the Internet. The driver does not need to perform any special operations; data is collected automatically simply by driving normally.

[0641] Once the data is sent to the server, the server analyzes the collected driving data based on a generative AI model. The generative AI model learns from past driving data and extracts driving patterns that contribute to improving fuel efficiency. This analysis process begins when the server provides a prompt to the generative AI model. For example, the server might pass the prompt to the model: "Please generate optimal fuel efficiency improvement advice from this driving data."

[0642] Based on the analysis results generated by the generative AI model, the server provides specific advice to the driver in real time, such as "avoid sudden acceleration" or "maintain a constant speed," allowing the driver to immediately improve their driving style.

[0643] Furthermore, the server stores driving data and the history of advice provided in a database. The stored history is later used to evaluate driving performance and is visualized through the terminal. The terminal displays past driving data in graphs and charts and provides it to the driver. The driver can review this data to objectively evaluate their own driving style and obtain specific clues for improvement.

[0644] To encourage fuel-efficient driving, the server applies a point system and awards points for fuel-efficient driving. These points are calculated based on the evaluation score of driving data and are offered to drivers as an incentive. The terminal notifies the driver of the awarded points, which the driver can confirm and use for rewards or discounts. This motivates the driver to drive more efficiently.

[0645] As a concrete example, driving data is collected from a vehicle traveling on a highway. The driving data includes the number of times the speed exceeded 100 km / h, the number of times sudden acceleration or deceleration occurred, and the distance traveled. The server analyzes this data and provides the driver with specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the driver to save on fuel costs and contribute to the environment.

[0646] An example prompt is, "Based on your driving data from the past week, please provide some advice on how to maximize fuel economy on your next trip."

[0647] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0648] Step 1:

[0649] The server acquires driving data from multiple sensors installed in the vehicle. Input data from the sensors includes speed, acceleration, and location information. The server collects this data in real time and stores it in a database. Specifically, it interprets data packets sent from the sensors and stores them in a structured format.

[0650] Step 2:

[0651] The server processes the acquired driving data in batches at regular intervals. Specifically, it compresses the data and prepares it for transfer to the terminal. The input raw data is reduced in size using a compression algorithm to make efficient use of network bandwidth. The compressed data is generated as output.

[0652] Step 3:

[0653] The terminal receives the compressed data sent from the server and performs decompression processing. The input data is compressed driving data, and this decompression processing reconstructs the original driving data. The reconstructed data is sent back to the server or temporarily stored on the terminal.

[0654] Step 4:

[0655] The server analyzes the decompressed driving data based on the generative AI model. The input data is the decompressed driving data, which undergoes a process of being input into the generative AI model. Specifically, a prompt statement is passed to the generative AI model and analysis is performed. The prompt statement used is "Please generate optimal fuel economy improvement advice from this data." The analysis results output insights into driving patterns and fuel economy improvement.

[0656] Step 5:

[0657] The server generates specific driving improvement advice based on the analysis results obtained from the generative AI model. The input data is the analysis results, from which information such as the number of sudden accelerations and decelerations and average speed is extracted. Specific operations involve applying an algorithm that generates advice statements based on conditions. For example, the output might be, "Maintaining a constant speed will improve fuel efficiency."

[0658] Step 6:

[0659] The terminal receives advice sent from the server and provides it to the driver in real time. The input data is advice text, which is processed to be displayed as a voice guide or on a display. Specifically, the advice is played back as a voice using a speech synthesis engine, or displayed as text on a display.

[0660] Step 7:

[0661] The server stores driving data and advice history in a database. The input data is raw driving data and advice history, which is stored in a structured format. The stored data is later analyzed to provide statistics and trends as output.

[0662] Step 8:

[0663] The terminal visualizes the driving data and advice history stored in the database and provides it to the user. The input data is the stored history data, and a visualization algorithm is applied to display it in graph or chart format. Specifically, the terminal uses a visualization library to generate graphs and charts and display them to the user.

[0664] Step 9:

[0665] The server applies a points system to incentive users for fuel-efficient driving. The input data is the evaluation score, and the server applies a points calculation algorithm to calculate points. The calculated points are obtained as output and added to the user profile.

[0666] Step 10:

[0667] The device receives the notification of point award sent from the server and notifies the user. The input data is point information, and processing is performed to notify the user of this. Specifically, the device's notification function is used to display a message indicating that points have been awarded, or the notification is sent via an application.

[0668] Step 11:

[0669] Users can check the points they have earned and use them for special offers or discounts. The input data is point information, which is evaluated and used for specific services or products. Specific operations include using points to receive discounts at online stores or participating in point exchange programs.

[0670] (Application example 1)

[0671] 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."

[0672] The present invention relates to a system for improving vehicle driving efficiency and reducing fuel consumption. However, conventional systems do not provide advice to drivers in real time, and it is difficult for drivers to intuitively understand the advice. Furthermore, there is a problem that the system does not provide sufficient incentives for fuel-efficient driving, which reduces driver motivation.

[0673] 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.

[0674] In this invention, the server includes means for acquiring driving data from sensors mounted on the vehicle, means for analyzing the acquired driving data based on a generative AI model, means for generating advice for improving driving based on the analysis results, means for providing the generated advice to the driver in real time, means for displaying the driving data on smart glasses or a head-mounted display to visualize it for the driver, means for saving the driving data and advice history and visualizing driving performance, and means for providing incentives for fuel-efficient driving. This allows the driver to receive intuitive advice in real time, thereby increasing their motivation to drive fuel-efficiently.

[0675] "Sensors mounted on a vehicle" are devices for acquiring information such as the vehicle's speed, acceleration, and location.

[0676] "Driving data" refers to various information related to driving, such as vehicle speed, acceleration, and location information.

[0677] A "generative AI model" is an artificial intelligence model that analyzes collected driving data and extracts patterns to improve fuel efficiency and driving.

[0678] "Provided in real time" means that advice is provided instantly while driving, without delay.

[0679] "Smart glasses and head-mounted displays" refer to wearable devices that drivers wear to display driving advice in real time as visual information.

[0680] "Storing and visualizing history" means recording past driving data and advice information and displaying it in a format that can be easily referenced later.

[0681] "Providing incentives" means offering rewards such as points or perks for fuel-efficient driving.

[0682] An embodiment of the present invention is described below. It is a system for improving driving efficiency in a vehicle and reducing fuel consumption. This system acquires driving data from sensors installed in the vehicle, analyzes it based on a generative AI model, and provides advice to the driver in real time. It also stores the driving data and advice history, visualizes driving performance, and provides incentives for fuel-efficient driving.

[0683] Data collection

[0684] server

[0685] Driving data is acquired from sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.), which allows speed, acceleration, location information, etc. to be recorded in real time.

[0686] Terminal

[0687] The acquired data is compressed and sent to the server periodically, for example, every minute.

[0688] User

[0689] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[0690] Analyzing the data

[0691] server

[0692] The acquired driving data is analyzed using a generative AI model. By learning from past driving data, this model can extract driving patterns that contribute to improved fuel efficiency. As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[0693] Providing advice

[0694] server

[0695] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[0696] Terminal

[0697] Advice sent from the server is provided to the user in real time using audio guidance and on-screen displays using smart glasses or a head-mounted display.

[0698] User

[0699] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[0700] History storage and visualization

[0701] server

[0702] Driving data and advice history is stored in a database. This data is later used to evaluate driving performance. The stored data can also be analyzed to calculate statistics and trends.

[0703] Terminal

[0704] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[0705] User

[0706] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[0707] Providing incentives

[0708] server

[0709] A points system is applied to incentive users for fuel-efficient driving. The points are calculated based on the evaluation score of driving data.

[0710] Terminal

[0711] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[0712] User

[0713] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[0714] Specific examples

[0715] While a user is driving on a highway, driving data is collected. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data and provides specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The user can then follow the advice and continue driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the user to save on fuel costs and contribute to the environment.

[0716] Example prompt sentence:

[0717] "Generate advice to improve fuel efficiency for the driver based on the number of times the speed reached 110 km / h and the number of times the acceleration exceeded 3 m / s^2."

[0718] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0719] Step 1:

[0720] Input: Driving data obtained from sensors installed in the vehicle (speed, acceleration, position information, etc.)

[0721] Processing: Sensor data collection. This data is recorded in real time from the vehicle's speed sensor, acceleration sensor, and GPS sensor. The collected data is temporarily stored on the device.

[0722] Output: Raw driving data is saved to the device.

[0723] Step 2:

[0724] Input: Driving data stored on the device

[0725] Processing: The terminal periodically compresses the driving data and sends it to the server. This transmission is performed, for example, every minute. The compressed data is sent to the server via a communication line.

[0726] Output: Compressed driving data is sent to the server.

[0727] Step 3:

[0728] Input: Compressed driving data sent to the server

[0729] Processing: The server decompresses the received data and analyzes it based on the generative AI model. For analysis, an AI model (e.g., TensorFlow) that has learned from past driving data is used. Driving patterns such as sudden acceleration, sudden deceleration, average speed, and number of stops are extracted.

[0730] Output: Analysis results are generated.

[0731] Step 4:

[0732] Input: Analysis results

[0733] Processing: Based on the analysis results, the server generates specific advice for improving fuel efficiency. The generated advice might be, for example, "avoid sudden acceleration" or "maintain a constant speed." The analysis results are input into the generative AI model using prompt statements, and appropriate advice is generated.

[0734] Output: Fuel economy improvement advice is generated.

[0735] Step 5:

[0736] Input: Fuel economy improvement advice

[0737] Processing: The server sends the generated advice to the device, which then provides the advice to the driver in real time via smart glasses or a head-mounted display.

[0738] Output: Advice is displayed on the driver's device.

[0739] Step 6:

[0740] Input: Driver behavior data

[0741] Action: The user checks the provided advice and applies it to their driving. For example, they should try to avoid sudden acceleration and accelerate slowly.

[0742] Output: Driver behavior improves and driving data changes.

[0743] Step 7:

[0744] Input: Improved driving data and advice history

[0745] Processing: The server stores the driving data and advice history in a database, which is later used to evaluate driving performance.

[0746] Output: Driving data and advice history are stored in a database.

[0747] Step 8:

[0748] Input: Stored driving data and advice history

[0749] Processing: The server analyzes the stored data, calculates statistics and trends, and presents this data to the user in visualizations (graphs, charts, etc.).

[0750] Output: Visualized driving data and advice history are displayed on the terminal.

[0751] Step 9:

[0752] Input: visualized driving data and advice history

[0753] Processing: The user reviews the provided data and objectively evaluates their driving style. They learn effective driving techniques and apply them to future driving. For example, they understand which driving techniques have a positive impact on fuel economy.

[0754] Output: User's driving style is evaluated and fed back for the next drive.

[0755] Step 10:

[0756] Input: Evaluated driving data and points system

[0757] Processing: The server calculates points for fuel-efficient driving and awards incentives to the user. Points are calculated based on the evaluation score of the driving data. The terminal notifies the user that points have been awarded and applies the points to the connected incentive program.

[0758] Output: The user is given an incentive and notified.

[0759] 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.

[0760] This invention relates to a system for improving driving efficiency and reducing fuel consumption in vehicles. The system acquires driving data from sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. Furthermore, it has a means for providing incentives for fuel-efficient driving and incorporates an emotion engine that recognizes the user's emotions.

[0761] Data collection

[0762] server

[0763] Driving data is acquired from sensors installed in the vehicle (e.g., speed sensor, acceleration sensor, GPS sensor), which allows the vehicle's speed, acceleration, location information, etc. to be recorded in real time.

[0764] Terminal

[0765] The acquired data is compressed and sent to the server periodically, for example every minute.

[0766] User

[0767] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[0768] Analyzing the data

[0769] server

[0770] The acquired driving data is analyzed using a generative AI model, which learns from past driving data and can extract driving patterns that contribute to improved fuel efficiency.

[0771] As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[0772] Providing advice

[0773] server

[0774] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[0775] Terminal

[0776] Advice sent from the server is provided to the user in real time, using audio guidance and on-screen displays.

[0777] User

[0778] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[0779] User Emotion Recognition

[0780] Terminal

[0781] Using sensors such as cameras and microphones installed in the vehicle, the system analyzes the driver's emotions from facial expressions, tone of voice, etc. This determines whether the driver is feeling stressed or relaxed.

[0782] server

[0783] The acquired emotional data is analyzed to understand the user's emotional state, which is then used to adjust the content of advice and the form of incentives.

[0784] History storage and visualization

[0785] server

[0786] The driving data and advice history is stored in a database, which is later used to evaluate driving performance.

[0787] The stored data can be analyzed to calculate statistics and trends.

[0788] Terminal

[0789] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[0790] User

[0791] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[0792] Advice adjustment

[0793] server

[0794] The emotion engine adjusts the content and tone of advice based on the user's emotions. For example, if the user is feeling stressed, the advice will be given in a calmer tone.

[0795] Terminal

[0796] Providing tailored advice to users in real time.

[0797] Providing incentives

[0798] server

[0799] The type of incentive provided is adjusted based on the emotions recognized by the emotion engine. A points system is applied to reward fuel-efficient driving, and the points are calculated based on the evaluation score of the driving data.

[0800] Terminal

[0801] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[0802] User

[0803] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[0804] As a concrete example, driving data is collected while a driver is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data to understand the driver's emotional state. If the driver is feeling stressed, the server provides specific advice in a calm tone, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining an appropriate speed, thereby improving fuel efficiency. Furthermore, if the driver is determined to be relaxed, incentives can be actively provided to further motivate them. This allows users to save on fuel costs and contribute to the environment.

[0805] The above is an embodiment of the present invention.

[0806] The processing flow will be explained below.

[0807] Step 1: Acquiring Sensor Data

[0808] The terminal acquires driving data in real time from various sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.).

[0809] Specific operation: Obtain speed data from the speed sensor every second, obtain location information from the GPS sensor every second, and collect acceleration data from the acceleration sensor.

[0810] Step 2: Compress and send the data

[0811] The terminal compresses the collected driving data at regular intervals (for example, every minute) and transmits it to the server.

[0812] Specific operation: Collected data is compressed into CSV format and sent to the server using HTTPS.

[0813] Step 3: Receiving and storing data

[0814] The server receives the data sent from the terminal and stores it in a database.

[0815] Specific operation: The received data is inserted into a database for analysis (e.g. MongoDB) and stored using the session ID as a key.

[0816] Step 4: Analysis by generative AI model

[0817] The server inputs the stored data into a generative AI model to analyze driving style.

[0818] Specific operation: Data is input into a generative AI model to extract features such as patterns of sudden acceleration and deceleration, average speed, and distance traveled.

[0819] Step 5: Emotion Recognition with the Emotion Engine

[0820] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from facial expressions, tone of voice, etc.

[0821] Specific operation: Using a facial expression recognition algorithm, analyzes the user's facial expression data to determine emotions such as anger, joy, stress, etc. Analyzes audio data from the microphone to complement the emotional state.

[0822] Step 6: Evaluate driving and generate advice

[0823] The server evaluates the driver's driving style based on the analysis results and generates specific advice for improving fuel efficiency, incorporating the results of the emotion engine.

[0824] Specific behavior: If the AI ​​model evaluates the driving style as 70 / 100 and the user feels stressed, it generates advice in a gentle tone such as "avoid sudden acceleration" and "maintain a constant speed."

[0825] Step 7: Submitting Advice

[0826] The server transmits the generated advice to the terminal.

[0827] Specific behavior: Advice is encoded in JSON format and sent to the device via an HTTP POST request.

[0828] Step 8: Viewing Advice

[0829] The device displays the received advice to the user in real time, using various display methods including text, graphics, and audio guidance.

[0830] Specific operation: A text message saying "Avoid sudden acceleration" is displayed on the screen, and the same advice is spoken aloud using voice synthesis.

[0831] Step 9: User execution

[0832] The user checks the advice provided and applies it to their actual driving.

[0833] Specific actions: The user follows the advice and presses the accelerator pedal slowly to avoid sudden acceleration.

[0834] Step 10: Save historical data

[0835] The server stores the data and advice history for each driving session in a database.

[0836] Specific operation: Driving data and generated advice are saved together so that the user can check them later.

[0837] Step 11: Visualize the data

[0838] The server calculates statistics and trends based on historical data and provides the data in a format that can be visually confirmed by the user.

[0839] What it does: Create monthly reports of driving data and generate graphs and charts.

[0840] Step 12: Send visualization data

[0841] The server transmits the generated visualization data to the terminal.

[0842] Specific behavior: Convert the report to PDF format and send it to the device.

[0843] Step 13: View the report

[0844] The terminal displays the received report on a user interface.

[0845] What it does: Opens the monthly report on the device and displays past driving data as graphs and charts.

[0846] Step 14: Calculate and award incentives

[0847] The server calculates incentives (points) based on the driving evaluation and assigns them to the user's account, taking into account the results of the emotion engine.

[0848] Specific operation: Incentive points are calculated based on the evaluation score, and additional points are awarded for less stressful driving.

[0849] Step 15: Points Notification

[0850] The terminal notifies the user that the points have been awarded.

[0851] Specific behavior: Display a pop-up notification such as "50 eco-driving points have been awarded."

[0852] Step 16: Use your points

[0853] Users can check their accumulated points and use them for special offers and discounts at partner stores.

[0854] Specific operation: Check points through the terminal and use them for discounts at online shops.

[0855] Example 2

[0856] 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."

[0857] There are limitations to methods for improving driving efficiency and reducing fuel consumption. Existing technologies lack real-time driver advice and incentive systems that take into account the driver's emotional state. Furthermore, drivers lack the opportunity and means to objectively evaluate and improve their own driving style, making it difficult to comprehensively improve their driving performance.

[0858] 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.

[0859] In this invention, the server includes: means for acquiring driving data from sensors installed in the vehicle; means for periodically compressing the acquired driving data and transmitting the compressed data to the server; means for analyzing the acquired driving data using a generative AI model; means for generating specific advice for improving driving based on the analysis results; means for providing the generated advice to the driver in real time; means for storing the driving data and advice history in a database and visualizing driving performance; means for adjusting the content and tone of the advice using an emotion engine that recognizes the user's emotions; and means for providing incentives for fuel-efficient driving. This allows the system to analyze driving data in real time and provide specific advice to the driver, thereby improving driving performance and fuel efficiency. Furthermore, the emotion recognition function can be used to reduce driver stress and improve driving efficiency.

[0860] "Driving data" refers to data such as speed, acceleration, and position information obtained from sensors installed in the vehicle.

[0861] "Generative AI model" refers to an artificial intelligence model that learns from past driving data and analyzes driving patterns that contribute to improved fuel efficiency.

[0862] "Advice" refers to instructions or suggestions for improving driving that are generated based on the analysis of driving data and provided to the driver.

[0863] "Real-time" refers to a situation where data is acquired, analyzed, and advice is provided almost simultaneously, with very little delay.

[0864] "Emotion engine" refers to technology that analyzes emotions from the user's facial expressions, tone of voice, and other information obtained from sensors installed in the vehicle.

[0865] "Incentives" refer to points or rewards awarded to encourage improved driving performance and more fuel-efficient driving.

[0866] "Database" refers to an information system for storing and managing driving data and advice history.

[0867] "Sensor" refers to a device installed in a vehicle and used to acquire driving data, including speed sensors, acceleration sensors, and GPS sensors.

[0868] "Compression" refers to the process of reducing the size of collected data so that it can be stored or transmitted efficiently.

[0869] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from sensors mounted on the vehicle and analyzes the data based on a generative AI model to provide real-time advice to the driver. Specifically, hardware such as a speed sensor, an acceleration sensor, and a GPS sensor is used. The software used includes the AI ​​model (e.g., TensorFlow or PyTorch) required to analyze the data.

[0870] Data collection

[0871] The server centrally collects driving data acquired from the vehicle's speed sensor, acceleration sensor, GPS sensor, etc. This allows speed, acceleration, location information, etc. to be recorded in real time.

[0872] The terminal compresses the collected data and periodically (for example, every minute) transmits it to the server. The transmitted data is in a compressed format (for example, ZIP format) and is uploaded to the server using an HTTP POST request.

[0873] The user simply drives as usual and data is collected automatically, with no special operations or confirmations required.

[0874] Analyzing the data

[0875] The server analyzes the acquired driving data based on a generative AI model. The generative AI model learns from past driving data and can extract driving patterns that contribute to improving fuel efficiency. As a result of the analysis, it can identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops. TensorFlow and PyTorch are used as AI libraries for the analysis.

[0876] Providing advice

[0877] Based on the analysis results, the server generates specific advice for improving fuel efficiency, such as "avoid sudden acceleration" and "maintain a constant speed."

[0878] The device provides the user with advice sent from the server in real time, using voice guidance (using a speech synthesis engine) and on-screen displays.

[0879] The user can check the provided advice and apply it to their driving. For example, they can learn to refrain from sudden acceleration and to step on the accelerator slowly.

[0880] User Emotion Recognition

[0881] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from their facial expressions and tone of voice, determining whether they are stressed or relaxed. Facial recognition software and voice analysis software are used.

[0882] The server analyzes the acquired emotional data to understand the user's emotional state, which is then used to adjust the content of advice and the form of incentives.

[0883] History storage and visualization

[0884] The server stores driving data and advice history in a database, which allows for later evaluation of driving performance. SQL is typically used to manage the database.

[0885] The device visualizes the stored driving data and provides it to the user. Graph generation libraries such as Chart.js and D3.js are used to display historical driving data using graphs and charts.

[0886] Users can view the visualized data and objectively evaluate their own driving style, thereby understanding how their driving habits affect fuel economy.

[0887] Advice adjustment

[0888] The server adjusts the content and tone of advice based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, the server will provide advice in a calm tone. Emotion data is used to select templates for advice messages and adjust the tone.

[0889] The device provides tailored advice to the user in real time, and if the user is not stressed, the advice is provided in a normal tone.

[0890] Providing incentives

[0891] The server adjusts the type of incentive to provide based on the emotions recognized by the emotion engine. A points system is applied to fuel-efficient driving to provide incentives to users. These points are calculated based on the evaluation score of the driving data. An evaluation algorithm is used to calculate and apply the points.

[0892] The terminal notifies the user that points have been awarded and applies the points to an incentive program, which is integrated into the incentive program using an API.

[0893] Users can view the points they have earned and use them for rewards and discounts, which motivates them to drive more efficiently.

[0894] Specific examples

[0895] For example, driving data is collected while a driver is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data to understand the driver's emotional state. If the driver appears stressed, the server provides specific advice in a calm tone, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining an appropriate speed, thereby improving fuel efficiency. Furthermore, if the driver is determined to be relaxed, incentives can be actively provided to further motivate them. This allows users to save on fuel costs and contribute to the environment.

[0896] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0897] Step 1:

[0898] Acquire driving data from sensors installed in the vehicle

[0899] The server acquires driving data in real time from the vehicle's speed sensor, acceleration sensor, and GPS sensor. Specifically, it continuously monitors the data stream from each sensor and converts the collected data into a specified format (for example, JSON format).

[0900] Input: Speed, acceleration, position information

[0901] Output: Format converted operation data

[0902] Step 2:

[0903] Compression and transmission of driving data

[0904] The terminal compresses the collected data and sends it to the server periodically (for example, every minute). Specifically, the terminal compresses the collected data in ZIP format or similar and sends an HTTP POST request to the specified server endpoint.

[0905] Input: Format converted operation data

[0906] Output: Compressed driving data

[0907] Step 3:

[0908] Analysis of driving data

[0909] The server analyzes the received driving data based on the generated AI model. Specifically, the data is input into the AI ​​model to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops in real time.

[0910] Input: Decompressed driving data

[0911] Output: Driving style analysis results

[0912] Step 4:

[0913] Generating Advice

[0914] The server generates specific advice for improving fuel efficiency based on the analysis results. Specifically, it generates advice messages based on templates and stores them in a database.

[0915] Input: Driving style analysis results

[0916] Output: Specific advice message

[0917] Step 5:

[0918] Providing advice

[0919] The device provides the user with advice sent from the server in real time, specifically by generating audio guidance using a speech synthesis engine and displaying the advice visually on a display.

[0920] Input: Specific advice message

[0921] Output: Providing advice to the user (audio and display)

[0922] Step 6:

[0923] Reflecting user driving

[0924] The user confirms the advice provided and applies it to their driving, specifically by operating the accelerator and adjusting speed according to the advice.

[0925] Input: Specific advice

[0926] Output: Driving operation based on advice

[0927] Step 7:

[0928] Emotional Data Analysis

[0929] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from their facial expressions and tone of voice. Specifically, it uses facial recognition software and voice analysis software to analyze the user's emotions in real time.

[0930] Input: User's facial expression data, tone of voice

[0931] Output: Parsed emotion data

[0932] Step 8:

[0933] Tailoring advice based on emotions

[0934] The server adjusts the content and tone of advice based on the analyzed emotional data. Specifically, it references the emotional data to select a template for the advice message and adjust the tone.

[0935] Input: Parsed emotion data

[0936] Output: Adjusted advice message

[0937] Step 9:

[0938] Incentive calculation and awarding

[0939] The server applies a point system to fuel-efficient driving and gives incentives to users. Specifically, it calculates points based on driving data and evaluation scores and stores them in a database.

[0940] Input: Driving data, evaluation score

[0941] Output: Incentive points

[0942] Step 10:

[0943] Incentive notification and use

[0944] The terminal notifies the user that points have been awarded and applies them to incentive programs. The user can then check the points they have earned and use them for rewards and discounts.

[0945] Input: Incentive points

[0946] Output: Incentive notification, point usage

[0947] (Application example 2)

[0948] 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."

[0949] Conventional vehicle driver assistance systems focused on collecting and analyzing driving data, and were unable to recognize and respond to driver emotions in real time. This made it difficult to respond appropriately to the driver's stress state and emotional changes, leading to a demand for further improvements in driving efficiency and ensuring safety. There was also a lack of incentive systems that could simultaneously improve fuel efficiency and increase driver motivation.

[0950] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring driving data from sensors installed in the vehicle, means for analyzing the acquired driving data using a generative AI model, means for generating advice for improving driving based on the analysis results, means for providing the generated advice to the driver in real time, means for saving the driving data and advice history and visualizing driving performance, means for providing incentives for fuel-efficient driving, means for recognizing the driver's emotions using sensors such as an installed camera and microphone, and means for adjusting the content and tone of the advice based on the emotional data. This makes it possible to grasp the driver's emotional state in real time and provide appropriate advice depending on the situation. This reduces driver stress, improves driving efficiency, and further reduces costs and protects the environment by improving fuel efficiency.

[0951] "Vehicle sensors" refer to various sensors installed in a vehicle, such as speed sensors, acceleration sensors, and GPS sensors, and have the function of acquiring driving data.

[0952] A "generative AI model" is an artificial intelligence model that learns from past driving data and analyzes and predicts driving patterns.

[0953] "Analysis means" refers to a device or software that analyzes acquired driving data based on a generative AI model and identifies driving tendencies and patterns.

[0954] The "advice generating means" has a function of automatically generating specific advice for improving driving based on the analysis results obtained by the analysis means.

[0955] The "real-time providing means" refers to a method or system for immediately providing the generated advice to the driver, and includes voice guidance and display.

[0956] The "history storage means" refers to a storage device such as a memory or database that records and stores the driving data and advice history so that it can be referenced at a later date.

[0957] The "driving performance visualization means" has a function to display the saved driving data and advice history in a visual format such as a graph or chart so that the driver can check it.

[0958] An "incentive granting means" is a method or system that provides points or rewards for fuel-efficient driving, and serves to keep drivers motivated.

[0959] The "emotion recognition means" has the function of analyzing the driver's facial expression and tone of voice using sensors such as cameras and microphones mounted on the vehicle, and identifying the driver's emotional state.

[0960] The "tone adjustment means" has a function of appropriately adjusting the content and tone of advice based on the emotion data obtained by the emotion recognition means.

[0961] System Overview

[0962] This system is realized by combining multiple sensors installed in the vehicle, a server, and the driver's device such as a smartphone or tablet. Its main functions include collecting and analyzing driving data, providing real-time advice, recognizing emotions, storing and visualizing history, and providing incentives.

[0963] Data collection

[0964] The server acquires driving data from various sensors installed in the vehicle, such as speed sensors, acceleration sensors, and GPS sensors. This data is sent to the server in real time via the terminal. To collect particularly accurate data, external sensor devices connected via Bluetooth or Wi-Fi can also be used.

[0965] Data analysis

[0966] The server analyzes the acquired driving data based on a generative AI model. The generative AI model learns from past driving data to identify driving trends such as sudden acceleration and deceleration, average speed, and number of stops. This allows it to extract driving patterns that lead to improved fuel efficiency.

[0967] Providing advice

[0968] The server generates appropriate driving advice based on the analysis results. The advice is provided to the driver in real time via the terminal. The terminal communicates the advice to the driver using voice guidance and on-screen displays.

[0969] User Emotion Recognition

[0970] The device uses the smartphone or tablet's camera and microphone to analyze the driver's facial expressions and tone of voice to recognize their emotional state. The server analyzes the acquired emotional data and evaluates the user's emotional state. Machine learning models are used to improve the accuracy of emotion recognition.

[0971] Advice adjustment

[0972] The server adjusts the content and tone of the advice based on the driver's emotional data. For example, if the driver is feeling stressed, the server will provide advice in a calm tone such as, "Drive calmly. Avoid sudden acceleration to improve fuel efficiency."

[0973] History storage and visualization

[0974] The server stores driving data and advice history in a database. The device visualizes the stored data in graphs and charts and provides them to the driver, allowing the driver to review past driving data and objectively evaluate their own driving style.

[0975] Providing incentives

[0976] The server provides a function to award points for fuel-efficient driving. The terminal notifies the driver that points have been awarded and allows the driver to exchange the points for rewards in cooperation with an incentive program. This motivates the driver to drive more fuel-efficiently.

[0977] Specific examples

[0978] While the driver is driving on the highway, the system collects speed and acceleration data in real time and sends it to a server. The server then analyzes the collected data using a generative AI model, taking into account the driver's facial expressions and voice data, and provides specific advice such as "maintaining a constant speed will improve fuel efficiency." Additionally, if the driver is relaxed, points are actively awarded to maintain the driver's motivation.

[0979] Prompt Sentence Examples

[0980] The driver's emotion has been identified as "Angry." Provide driving advice in a calm tone. For example, "Drive calmly. Avoiding sudden acceleration will improve fuel economy."

[0981] This allows for driving assistance that takes the driver's emotional state into appropriate consideration.

[0982] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0983] Step 1:

[0984] Input: Driving data from the vehicle's speed sensor, acceleration sensor, and GPS sensor.

[0985] Example: Obtaining speed, acceleration, position information, etc.

[0986] Processing: The device collects and compresses these driving data in real time.

[0987] Output: Compressed driving data.

[0988] Step 2:

[0989] Input: Compressed driving data.

[0990] Example: Collected data, such as speed, acceleration, and position per second.

[0991] Processing: The device periodically transmits the compressed driving data to the server, for example, every minute.

[0992] Output: Driving data sent to the server.

[0993] Step 3:

[0994] Input: Driving data sent to the server.

[0995] Example: Data received by the server, such as speed, acceleration, and location information from the start to the end of a driving session.

[0996] Processing: The server analyzes the received driving data based on the generative AI model.

[0997] Output: Driving style analysis results (sudden acceleration, sudden deceleration, average speed, number of stops, etc.).

[0998] Step 4:

[0999] Input: Analysis results.

[1000] Examples include: number of sudden accelerations, average speed, number of stops, etc.

[1001] Processing: The server generates appropriate driving advice based on the analysis results, such as "avoid sudden acceleration" or "maintain a constant speed."

[1002] Output: The generated driving advice.

[1003] Step 5:

[1004] Input: Generated driving advice.

[1005] Examples: Specific advice such as "avoid sudden acceleration" or "maintain a steady speed."

[1006] Processing: The device provides real-time advice to the driver, conveying the advice through voice prompts and on-screen displays.

[1007] Output: Advice provided in a form that the user can understand.

[1008] Step 6:

[1009] Input: Driver facial expressions and tone of voice captured from cameras and microphones.

[1010] Example: Facial images and audio data of a driver while driving.

[1011] Processing: The device performs emotion recognition based on data acquired through the camera and microphone.

[1012] Output: Perceived driver emotional state (anger, joy, stress, etc.).

[1013] Step 7:

[1014] Input: Perceived driver emotional state.

[1015] Example: A driver is identified as "Angry."

[1016] Processing: The server adjusts the content and tone of the advice based on the emotional data. For example, if the user is feeling stressed, the server will provide advice in a calmer tone.

[1017] Output: Tailored advice.

[1018] Step 8:

[1019] Input: Driving data, advice history.

[1020] Example: Data from past driving sessions and advice provided.

[1021] Processing: The server stores the driving data and advice history in a database.

[1022] Output: Driving history and advice history stored in a database.

[1023] Step 9:

[1024] Input: Driving history and advice history stored in a database.

[1025] Example: Visual data formats such as graphs and charts.

[1026] Processing: The device visualizes the stored data and provides it to the driver, for example by providing trend analysis and graphical representations of historical data.

[1027] Output: Visualized driving data and advice history.

[1028] Step 10:

[1029] Input: Driving data rating score.

[1030] Example: Points calculation based on fuel-efficient driving.

[1031] Processing: The server awards points for fuel-efficient driving and links to incentive programs.

[1032] Output: Points awarded and notification to the user.

[1033] 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.

[1034] 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.

[1035] 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.

[1036] [Third embodiment]

[1037] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1038] 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.

[1039] 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).

[1040] 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.

[1041] 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.

[1042] 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).

[1043] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1044] 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.

[1045] 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.

[1046] 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.

[1047] 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.

[1048] 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."

[1049] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. It also has a means for providing incentives for fuel-efficient driving.

[1050] Data collection

[1051] server

[1052] Driving data is acquired from sensors installed in the vehicle (e.g., speed sensor, acceleration sensor, GPS sensor), which allows the vehicle's speed, acceleration, location information, etc. to be recorded in real time.

[1053] Terminal

[1054] The acquired data is compressed and sent to the server periodically, for example every minute.

[1055] User

[1056] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[1057] Analyzing the data

[1058] server

[1059] The acquired driving data is analyzed using a generative AI model, which learns from past driving data and can extract driving patterns that contribute to improved fuel efficiency.

[1060] As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[1061] Providing advice

[1062] server

[1063] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[1064] Terminal

[1065] Advice sent from the server is provided to the user in real time, using audio guidance and on-screen displays.

[1066] User

[1067] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[1068] History storage and visualization

[1069] server

[1070] The driving data and advice history is stored in a database, which is later used to evaluate driving performance.

[1071] The stored data can be analyzed to calculate statistics and trends.

[1072] Terminal

[1073] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[1074] User

[1075] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[1076] Providing incentives

[1077] server

[1078] A points system is applied to incentive users for fuel-efficient driving. The points are calculated based on the evaluation score of driving data.

[1079] Terminal

[1080] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[1081] User

[1082] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[1083] As a concrete example, driving data is collected while a user is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of times there was sudden acceleration or deceleration, and the distance traveled. The server analyzes this data and provides the user with specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The user then follows the advice and continues driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the user to save on fuel costs and contribute to the environment.

[1084] The above is an embodiment of the present invention.

[1085] The processing flow will be explained below.

[1086] Step 1: Acquiring Sensor Data

[1087] The terminal acquires driving data in real time from various sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.).

[1088] Specific operation: Obtain speed data from the speed sensor every second, obtain location information from the GPS sensor every second, and collect acceleration data from the acceleration sensor.

[1089] Step 2: Compress and send the data

[1090] The terminal compresses the collected driving data at regular intervals (for example, every minute) and transmits it to the server.

[1091] Specific operation: Collected data is compressed into CSV format and sent to the server using HTTPS.

[1092] Step 3: Receiving and storing data

[1093] The server receives the data sent from the terminal and stores it in a database.

[1094] Specific operation: The received data is inserted into a database for analysis (e.g. MongoDB) and stored using the session ID as a key.

[1095] Step 4: Analysis by generative AI model

[1096] The server inputs the stored data into a generative AI model to analyze driving style.

[1097] Specific operation: Data is input into a generative AI model to extract features such as patterns of sudden acceleration and deceleration, average speed, and distance traveled.

[1098] Step 5: Evaluate driving and generate advice

[1099] The server evaluates the driving style based on the analysis results and generates specific advice for improving fuel efficiency.

[1100] Specific behavior: The AI ​​model evaluates the driving style on a scale of 70 / 100 and generates advice such as "avoid sudden acceleration" and "maintain a constant speed."

[1101] Step 6: Submitting Advice

[1102] The server transmits the generated advice to the terminal.

[1103] Specific behavior: Advice is encoded in JSON format and sent to the device via an HTTP POST request.

[1104] Step 7: Viewing Advice

[1105] The device displays the received advice to the user in real time, using various display methods including text, graphics, and audio guidance.

[1106] Specific operation: A text message saying "Avoid sudden acceleration" is displayed on the screen, and the same advice is spoken aloud using voice synthesis.

[1107] Step 8: User execution

[1108] The user checks the advice provided and applies it to their actual driving.

[1109] Specific actions: The user follows the advice and presses the accelerator pedal slowly to avoid sudden acceleration.

[1110] Step 9: Save historical data

[1111] The server stores the data and advice history for each driving session in a database.

[1112] Specific operation: Driving data and generated advice are saved together so that the user can check them later.

[1113] Step 10: Visualize the data

[1114] The server calculates statistics and trends based on historical data and provides the data in a format that can be visually confirmed by the user.

[1115] What it does: Create monthly reports of driving data and generate graphs and charts.

[1116] Step 11: Send visualization data

[1117] The server transmits the generated visualization data to the terminal.

[1118] Specific behavior: Convert the report to PDF format and send it to the device.

[1119] Step 12: View the report

[1120] The terminal displays the received report on a user interface.

[1121] What it does: Opens the monthly report on the device and displays past driving data as graphs and charts.

[1122] Step 13: Calculate and award incentives

[1123] The server calculates incentives (points) based on the driving evaluation and assigns them to the user's account.

[1124] Specific operation: Calculate incentive points based on the evaluation score and add 50 points to the user ID.

[1125] Step 14: Points Notification

[1126] The terminal notifies the user that the points have been awarded.

[1127] Specific behavior: Display a pop-up notification such as "50 eco-driving points have been awarded."

[1128] Step 15: Use your points

[1129] Users can check their accumulated points and use them for special offers and discounts at partner stores.

[1130] Specific operation: Check points through the terminal and use them for discounts at online shops.

[1131] Example 1

[1132] 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."

[1133] In order to achieve efficient fuel consumption and reduce environmental impact, a system is needed that enables drivers to accurately understand and practice how to drive. However, conventional systems do not adequately process driving data in real time, which can delay feedback to the driver, making it difficult to improve driving efficiency. In addition, there was a lack of effective visualization of driving data and the provision of incentives, making it difficult to improve driver motivation.

[1134] 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.

[1135] In this invention, the server includes a means for acquiring driving data from multiple sensors installed in the vehicle, a means for analyzing the acquired driving data using a generative AI model, and a means for generating specific advice for improving driving based on the analysis results. This allows for real-time acquisition of driving data and analysis using the generative AI model, enabling immediate and specific feedback to the driver. Furthermore, adding a means for saving the driving data and advice history, visualizing driving performance, and providing incentives for fuel-efficient driving can improve the driver's motivation and achieve efficient driving.

[1136] The "multiple sensors" refer to a number of sensor devices, such as a speed sensor, an acceleration sensor, and a GPS sensor, that are mounted on a vehicle to collect driving data of the vehicle.

[1137] "Driving data" refers to information about vehicle driving, such as speed, acceleration, location information, distance traveled, and driving behavior, and is data acquired from multiple sensors.

[1138] A "generative AI model" is an artificial intelligence model used to learn from past driving data and analyze driving patterns and fuel efficiency.

[1139] "Analysis" refers to the process of using generative AI models to identify driving patterns and styles based on captured driving data.

[1140] "Specific advice" refers to advice that the generative AI model provides to the driver based on the analysis of driving data to improve driving efficiency and reduce fuel consumption.

[1141] "Real-time" refers to the time frame in which data is acquired and processed immediately, with little or no delay, to provide results.

[1142] "History" refers to data that records and saves driving data acquired in the past and advice generated in chronological order.

[1143] "Visualization" refers to the process of displaying collected driving data and advice history in visual formats such as graphs and charts to make the data easier for drivers to understand.

[1144] "Incentives" are benefits or rewards offered to drivers to encourage efficient driving.

[1145] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from multiple sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. It also has a means for providing incentives for fuel-efficient driving.

[1146] The server acquires driving data in real time from multiple sensors, including speed sensors, acceleration sensors, and GPS sensors. This driving data includes speed, acceleration, location information, distance traveled, driving behavior, and more. The terminal also compresses the acquired driving data at regular intervals (for example, every minute) and sends it to the server via the Internet. The driver does not need to perform any special operations; data is collected automatically simply by driving normally.

[1147] Once the data is sent to the server, the server analyzes the collected driving data based on a generative AI model. The generative AI model learns from past driving data and extracts driving patterns that contribute to improving fuel efficiency. This analysis process begins when the server provides a prompt to the generative AI model. For example, the server might pass the prompt to the model: "Please generate optimal fuel efficiency improvement advice from this driving data."

[1148] Based on the analysis results generated by the generative AI model, the server provides specific advice to the driver in real time, such as "avoid sudden acceleration" or "maintain a constant speed," allowing the driver to immediately improve their driving style.

[1149] Furthermore, the server stores driving data and the history of advice provided in a database. The stored history is later used to evaluate driving performance and is visualized through the terminal. The terminal displays past driving data in graphs and charts and provides it to the driver. The driver can review this data to objectively evaluate their own driving style and obtain specific clues for improvement.

[1150] To encourage fuel-efficient driving, the server applies a point system and awards points for fuel-efficient driving. These points are calculated based on the evaluation score of driving data and are offered to drivers as an incentive. The terminal notifies the driver of the awarded points, which the driver can confirm and use for rewards or discounts. This motivates the driver to drive more efficiently.

[1151] As a concrete example, driving data is collected from a vehicle traveling on a highway. The driving data includes the number of times the speed exceeded 100 km / h, the number of times sudden acceleration or deceleration occurred, and the distance traveled. The server analyzes this data and provides the driver with specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the driver to save on fuel costs and contribute to the environment.

[1152] An example prompt is, "Based on your driving data from the past week, please provide some advice on how to maximize fuel economy on your next trip."

[1153] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1154] Step 1:

[1155] The server acquires driving data from multiple sensors installed in the vehicle. Input data from the sensors includes speed, acceleration, and location information. The server collects this data in real time and stores it in a database. Specifically, it interprets data packets sent from the sensors and stores them in a structured format.

[1156] Step 2:

[1157] The server processes the acquired driving data in batches at regular intervals. Specifically, it compresses the data and prepares it for transfer to the terminal. The input raw data is reduced in size using a compression algorithm to make efficient use of network bandwidth. The compressed data is generated as output.

[1158] Step 3:

[1159] The terminal receives the compressed data sent from the server and performs decompression processing. The input data is compressed driving data, and this decompression processing reconstructs the original driving data. The reconstructed data is sent back to the server or temporarily stored on the terminal.

[1160] Step 4:

[1161] The server analyzes the decompressed driving data based on the generative AI model. The input data is the decompressed driving data, which undergoes a process of being input into the generative AI model. Specifically, a prompt statement is passed to the generative AI model and analysis is performed. The prompt statement used is "Please generate optimal fuel economy improvement advice from this data." The analysis results output insights into driving patterns and fuel economy improvement.

[1162] Step 5:

[1163] The server generates specific driving improvement advice based on the analysis results obtained from the generative AI model. The input data is the analysis results, from which information such as the number of sudden accelerations and decelerations and average speed is extracted. Specific operations involve applying an algorithm that generates advice statements based on conditions. For example, the output might be, "Maintaining a constant speed will improve fuel efficiency."

[1164] Step 6:

[1165] The terminal receives advice sent from the server and provides it to the driver in real time. The input data is advice text, which is processed to be displayed as a voice guide or on a display. Specifically, the advice is played back as a voice using a speech synthesis engine, or displayed as text on a display.

[1166] Step 7:

[1167] The server stores driving data and advice history in a database. The input data is raw driving data and advice history, which is stored in a structured format. The stored data is later analyzed to provide statistics and trends as output.

[1168] Step 8:

[1169] The terminal visualizes the driving data and advice history stored in the database and provides it to the user. The input data is the stored history data, and a visualization algorithm is applied to display it in graph or chart format. Specifically, the terminal uses a visualization library to generate graphs and charts and display them to the user.

[1170] Step 9:

[1171] The server applies a points system to incentive users for fuel-efficient driving. The input data is the evaluation score, and the server applies a points calculation algorithm to calculate points. The calculated points are obtained as output and added to the user profile.

[1172] Step 10:

[1173] The device receives the notification of point award sent from the server and notifies the user. The input data is point information, and processing is performed to notify the user of this. Specifically, the device's notification function is used to display a message indicating that points have been awarded, or the notification is sent via an application.

[1174] Step 11:

[1175] Users can check the points they have earned and use them for special offers or discounts. The input data is point information, which is evaluated and used for specific services or products. Specific operations include using points to receive discounts at online stores or participating in point exchange programs.

[1176] (Application example 1)

[1177] 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."

[1178] The present invention relates to a system for improving vehicle driving efficiency and reducing fuel consumption. However, conventional systems do not provide advice to drivers in real time, and it is difficult for drivers to intuitively understand the advice. Furthermore, there is a problem that the system does not provide sufficient incentives for fuel-efficient driving, which reduces driver motivation.

[1179] 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.

[1180] In this invention, the server includes means for acquiring driving data from sensors mounted on the vehicle, means for analyzing the acquired driving data based on a generative AI model, means for generating advice for improving driving based on the analysis results, means for providing the generated advice to the driver in real time, means for displaying the driving data on smart glasses or a head-mounted display to visualize it for the driver, means for saving the driving data and advice history and visualizing driving performance, and means for providing incentives for fuel-efficient driving. This allows the driver to receive intuitive advice in real time, thereby increasing their motivation to drive fuel-efficiently.

[1181] "Sensors mounted on a vehicle" are devices for acquiring information such as the vehicle's speed, acceleration, and location.

[1182] "Driving data" refers to various information related to driving, such as vehicle speed, acceleration, and location information.

[1183] A "generative AI model" is an artificial intelligence model that analyzes collected driving data and extracts patterns to improve fuel efficiency and driving.

[1184] "Provided in real time" means that advice is provided instantly while driving, without delay.

[1185] "Smart glasses and head-mounted displays" refer to wearable devices that drivers wear to display driving advice in real time as visual information.

[1186] "Storing and visualizing history" means recording past driving data and advice information and displaying it in a format that can be easily referenced later.

[1187] "Providing incentives" means offering rewards such as points or perks for fuel-efficient driving.

[1188] An embodiment of the present invention is described below. It is a system for improving driving efficiency in a vehicle and reducing fuel consumption. This system acquires driving data from sensors installed in the vehicle, analyzes it based on a generative AI model, and provides advice to the driver in real time. It also stores the driving data and advice history, visualizes driving performance, and provides incentives for fuel-efficient driving.

[1189] Data collection

[1190] server

[1191] Driving data is acquired from sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.), which allows speed, acceleration, location information, etc. to be recorded in real time.

[1192] Terminal

[1193] The acquired data is compressed and sent to the server periodically, for example, every minute.

[1194] User

[1195] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[1196] Analyzing the data

[1197] server

[1198] The acquired driving data is analyzed using a generative AI model. By learning from past driving data, this model can extract driving patterns that contribute to improved fuel efficiency. As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[1199] Providing advice

[1200] server

[1201] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[1202] Terminal

[1203] Advice sent from the server is provided to the user in real time using audio guidance and on-screen displays using smart glasses or a head-mounted display.

[1204] User

[1205] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[1206] History storage and visualization

[1207] server

[1208] Driving data and advice history is stored in a database. This data is later used to evaluate driving performance. The stored data can also be analyzed to calculate statistics and trends.

[1209] Terminal

[1210] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[1211] User

[1212] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[1213] Providing incentives

[1214] server

[1215] A points system is applied to incentive users for fuel-efficient driving. The points are calculated based on the evaluation score of driving data.

[1216] Terminal

[1217] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[1218] User

[1219] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[1220] Specific examples

[1221] While a user is driving on a highway, driving data is collected. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data and provides specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The user can then follow the advice and continue driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the user to save on fuel costs and contribute to the environment.

[1222] Example prompt sentence:

[1223] "Generate advice to improve fuel efficiency for the driver based on the number of times the speed reached 110 km / h and the number of times the acceleration exceeded 3 m / s^2."

[1224] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1225] Step 1:

[1226] Input: Driving data obtained from sensors installed in the vehicle (speed, acceleration, position information, etc.)

[1227] Processing: Sensor data collection. This data is recorded in real time from the vehicle's speed sensor, acceleration sensor, and GPS sensor. The collected data is temporarily stored on the device.

[1228] Output: Raw driving data is saved to the device.

[1229] Step 2:

[1230] Input: Driving data stored on the device

[1231] Processing: The terminal periodically compresses the driving data and sends it to the server. This transmission is performed, for example, every minute. The compressed data is sent to the server via a communication line.

[1232] Output: Compressed driving data is sent to the server.

[1233] Step 3:

[1234] Input: Compressed driving data sent to the server

[1235] Processing: The server decompresses the received data and analyzes it based on the generative AI model. For analysis, an AI model (e.g., TensorFlow) that has learned from past driving data is used. Driving patterns such as sudden acceleration, sudden deceleration, average speed, and number of stops are extracted.

[1236] Output: Analysis results are generated.

[1237] Step 4:

[1238] Input: Analysis results

[1239] Processing: Based on the analysis results, the server generates specific advice for improving fuel efficiency. The generated advice might be, for example, "avoid sudden acceleration" or "maintain a constant speed." The analysis results are input into the generative AI model using prompt statements, and appropriate advice is generated.

[1240] Output: Fuel economy improvement advice is generated.

[1241] Step 5:

[1242] Input: Fuel economy improvement advice

[1243] Processing: The server sends the generated advice to the device, which then provides the advice to the driver in real time via smart glasses or a head-mounted display.

[1244] Output: Advice is displayed on the driver's device.

[1245] Step 6:

[1246] Input: Driver behavior data

[1247] Action: The user checks the provided advice and applies it to their driving. For example, they should try to avoid sudden acceleration and accelerate slowly.

[1248] Output: Driver behavior improves and driving data changes.

[1249] Step 7:

[1250] Input: Improved driving data and advice history

[1251] Processing: The server stores the driving data and advice history in a database, which is later used to evaluate driving performance.

[1252] Output: Driving data and advice history are stored in a database.

[1253] Step 8:

[1254] Input: Stored driving data and advice history

[1255] Processing: The server analyzes the stored data, calculates statistics and trends, and presents this data to the user in visualizations (graphs, charts, etc.).

[1256] Output: Visualized driving data and advice history are displayed on the terminal.

[1257] Step 9:

[1258] Input: visualized driving data and advice history

[1259] Processing: The user reviews the provided data and objectively evaluates their driving style. They learn effective driving techniques and apply them to future driving. For example, they understand which driving techniques have a positive impact on fuel economy.

[1260] Output: User's driving style is evaluated and fed back for the next drive.

[1261] Step 10:

[1262] Input: Evaluated driving data and points system

[1263] Processing: The server calculates points for fuel-efficient driving and awards incentives to the user. Points are calculated based on the evaluation score of the driving data. The terminal notifies the user that points have been awarded and applies the points to the connected incentive program.

[1264] Output: The user is given an incentive and notified.

[1265] 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.

[1266] This invention relates to a system for improving driving efficiency and reducing fuel consumption in vehicles. The system acquires driving data from sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. Furthermore, it has a means for providing incentives for fuel-efficient driving and incorporates an emotion engine that recognizes the user's emotions.

[1267] Data collection

[1268] server

[1269] Driving data is acquired from sensors installed in the vehicle (e.g., speed sensor, acceleration sensor, GPS sensor), which allows the vehicle's speed, acceleration, location information, etc. to be recorded in real time.

[1270] Terminal

[1271] The acquired data is compressed and sent to the server periodically, for example every minute.

[1272] User

[1273] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[1274] Analyzing the data

[1275] server

[1276] The acquired driving data is analyzed using a generative AI model, which learns from past driving data and can extract driving patterns that contribute to improved fuel efficiency.

[1277] As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[1278] Providing advice

[1279] server

[1280] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[1281] Terminal

[1282] Advice sent from the server is provided to the user in real time, using audio guidance and on-screen displays.

[1283] User

[1284] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[1285] User Emotion Recognition

[1286] Terminal

[1287] Using sensors such as cameras and microphones installed in the vehicle, the system analyzes the driver's emotions from facial expressions, tone of voice, etc. This determines whether the driver is feeling stressed or relaxed.

[1288] server

[1289] The acquired emotional data is analyzed to understand the user's emotional state, which is then used to adjust the content of advice and the form of incentives.

[1290] History storage and visualization

[1291] server

[1292] The driving data and advice history is stored in a database, which is later used to evaluate driving performance.

[1293] The stored data can be analyzed to calculate statistics and trends.

[1294] Terminal

[1295] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[1296] User

[1297] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[1298] Advice adjustment

[1299] server

[1300] The emotion engine adjusts the content and tone of advice based on the user's emotions. For example, if the user is feeling stressed, the advice will be given in a calmer tone.

[1301] Terminal

[1302] Providing tailored advice to users in real time.

[1303] Providing incentives

[1304] server

[1305] The type of incentive provided is adjusted based on the emotions recognized by the emotion engine. A points system is applied to reward fuel-efficient driving, and the points are calculated based on the evaluation score of the driving data.

[1306] Terminal

[1307] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[1308] User

[1309] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[1310] As a concrete example, driving data is collected while a driver is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data to understand the driver's emotional state. If the driver is feeling stressed, the server provides specific advice in a calm tone, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining an appropriate speed, thereby improving fuel efficiency. Furthermore, if the driver is determined to be relaxed, incentives can be actively provided to further motivate them. This allows users to save on fuel costs and contribute to the environment.

[1311] The above is an embodiment of the present invention.

[1312] The processing flow will be explained below.

[1313] Step 1: Acquiring Sensor Data

[1314] The terminal acquires driving data in real time from various sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.).

[1315] Specific operation: Obtain speed data from the speed sensor every second, obtain location information from the GPS sensor every second, and collect acceleration data from the acceleration sensor.

[1316] Step 2: Compress and send the data

[1317] The terminal compresses the collected driving data at regular intervals (for example, every minute) and transmits it to the server.

[1318] Specific operation: Collected data is compressed into CSV format and sent to the server using HTTPS.

[1319] Step 3: Receiving and storing data

[1320] The server receives the data sent from the terminal and stores it in a database.

[1321] Specific operation: The received data is inserted into a database for analysis (e.g. MongoDB) and stored using the session ID as a key.

[1322] Step 4: Analysis by generative AI model

[1323] The server inputs the stored data into a generative AI model to analyze driving style.

[1324] Specific operation: Data is input into a generative AI model to extract features such as patterns of sudden acceleration and deceleration, average speed, and distance traveled.

[1325] Step 5: Emotion Recognition with the Emotion Engine

[1326] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from facial expressions, tone of voice, etc.

[1327] Specific operation: Using a facial expression recognition algorithm, analyzes the user's facial expression data to determine emotions such as anger, joy, stress, etc. Analyzes audio data from the microphone to complement the emotional state.

[1328] Step 6: Evaluate driving and generate advice

[1329] The server evaluates the driver's driving style based on the analysis results and generates specific advice for improving fuel efficiency, incorporating the results of the emotion engine.

[1330] Specific behavior: If the AI ​​model evaluates the driving style as 70 / 100 and the user feels stressed, it generates advice in a gentle tone such as "avoid sudden acceleration" and "maintain a constant speed."

[1331] Step 7: Submitting Advice

[1332] The server transmits the generated advice to the terminal.

[1333] Specific behavior: Advice is encoded in JSON format and sent to the device via an HTTP POST request.

[1334] Step 8: Viewing Advice

[1335] The device displays the received advice to the user in real time, using various display methods including text, graphics, and audio guidance.

[1336] Specific operation: A text message saying "Avoid sudden acceleration" is displayed on the screen, and the same advice is spoken aloud using voice synthesis.

[1337] Step 9: User execution

[1338] The user checks the advice provided and applies it to their actual driving.

[1339] Specific actions: The user follows the advice and presses the accelerator pedal slowly to avoid sudden acceleration.

[1340] Step 10: Save historical data

[1341] The server stores the data and advice history for each driving session in a database.

[1342] Specific operation: Driving data and generated advice are saved together so that the user can check them later.

[1343] Step 11: Visualize the data

[1344] The server calculates statistics and trends based on historical data and provides the data in a format that can be visually confirmed by the user.

[1345] What it does: Create monthly reports of driving data and generate graphs and charts.

[1346] Step 12: Send visualization data

[1347] The server transmits the generated visualization data to the terminal.

[1348] Specific behavior: Convert the report to PDF format and send it to the device.

[1349] Step 13: View the report

[1350] The terminal displays the received report on a user interface.

[1351] What it does: Opens the monthly report on the device and displays past driving data as graphs and charts.

[1352] Step 14: Calculate and award incentives

[1353] The server calculates incentives (points) based on the driving evaluation and assigns them to the user's account, taking into account the results of the emotion engine.

[1354] Specific operation: Incentive points are calculated based on the evaluation score, and additional points are awarded for less stressful driving.

[1355] Step 15: Points Notification

[1356] The terminal notifies the user that the points have been awarded.

[1357] Specific behavior: Display a pop-up notification such as "50 eco-driving points have been awarded."

[1358] Step 16: Use your points

[1359] Users can check their accumulated points and use them for special offers and discounts at partner stores.

[1360] Specific operation: Check points through the terminal and use them for discounts at online shops.

[1361] Example 2

[1362] 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."

[1363] There are limitations to methods for improving driving efficiency and reducing fuel consumption. Existing technologies lack real-time driver advice and incentive systems that take into account the driver's emotional state. Furthermore, drivers lack the opportunity and means to objectively evaluate and improve their own driving style, making it difficult to comprehensively improve their driving performance.

[1364] 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.

[1365] In this invention, the server includes: means for acquiring driving data from sensors installed in the vehicle; means for periodically compressing the acquired driving data and transmitting the compressed data to the server; means for analyzing the acquired driving data using a generative AI model; means for generating specific advice for improving driving based on the analysis results; means for providing the generated advice to the driver in real time; means for storing the driving data and advice history in a database and visualizing driving performance; means for adjusting the content and tone of the advice using an emotion engine that recognizes the user's emotions; and means for providing incentives for fuel-efficient driving. This allows the system to analyze driving data in real time and provide specific advice to the driver, thereby improving driving performance and fuel efficiency. Furthermore, the emotion recognition function can be used to reduce driver stress and improve driving efficiency.

[1366] "Driving data" refers to data such as speed, acceleration, and position information obtained from sensors installed in the vehicle.

[1367] "Generative AI model" refers to an artificial intelligence model that learns from past driving data and analyzes driving patterns that contribute to improved fuel efficiency.

[1368] "Advice" refers to instructions or suggestions for improving driving that are generated based on the analysis of driving data and provided to the driver.

[1369] "Real-time" refers to a situation where data is acquired, analyzed, and advice is provided almost simultaneously, with very little delay.

[1370] "Emotion engine" refers to technology that analyzes emotions from the user's facial expressions, tone of voice, and other information obtained from sensors installed in the vehicle.

[1371] "Incentives" refer to points or rewards awarded to encourage improved driving performance and more fuel-efficient driving.

[1372] "Database" refers to an information system for storing and managing driving data and advice history.

[1373] "Sensor" refers to a device installed in a vehicle and used to acquire driving data, including speed sensors, acceleration sensors, and GPS sensors.

[1374] "Compression" refers to the process of reducing the size of collected data so that it can be stored or transmitted efficiently.

[1375] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from sensors mounted on the vehicle and analyzes the data based on a generative AI model to provide real-time advice to the driver. Specifically, hardware such as a speed sensor, an acceleration sensor, and a GPS sensor is used. The software used includes the AI ​​model (e.g., TensorFlow or PyTorch) required to analyze the data.

[1376] Data collection

[1377] The server centrally collects driving data acquired from the vehicle's speed sensor, acceleration sensor, GPS sensor, etc. This allows speed, acceleration, location information, etc. to be recorded in real time.

[1378] The terminal compresses the collected data and periodically (for example, every minute) transmits it to the server. The transmitted data is in a compressed format (for example, ZIP format) and is uploaded to the server using an HTTP POST request.

[1379] The user simply drives as usual and data is collected automatically, with no special operations or confirmations required.

[1380] Analyzing the data

[1381] The server analyzes the acquired driving data based on a generative AI model. The generative AI model learns from past driving data and can extract driving patterns that contribute to improving fuel efficiency. As a result of the analysis, it can identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops. TensorFlow and PyTorch are used as AI libraries for the analysis.

[1382] Providing advice

[1383] Based on the analysis results, the server generates specific advice for improving fuel efficiency, such as "avoid sudden acceleration" and "maintain a constant speed."

[1384] The device provides the user with advice sent from the server in real time, using voice guidance (using a speech synthesis engine) and on-screen displays.

[1385] The user can check the provided advice and apply it to their driving. For example, they can learn to refrain from sudden acceleration and to step on the accelerator slowly.

[1386] User Emotion Recognition

[1387] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from their facial expressions and tone of voice, determining whether they are stressed or relaxed. Facial recognition software and voice analysis software are used.

[1388] The server analyzes the acquired emotional data to understand the user's emotional state, which is then used to adjust the content of advice and the form of incentives.

[1389] History storage and visualization

[1390] The server stores driving data and advice history in a database, which allows for later evaluation of driving performance. SQL is typically used to manage the database.

[1391] The device visualizes the stored driving data and provides it to the user. Graph generation libraries such as Chart.js and D3.js are used to display historical driving data using graphs and charts.

[1392] Users can view the visualized data and objectively evaluate their own driving style, thereby understanding how their driving habits affect fuel economy.

[1393] Advice adjustment

[1394] The server adjusts the content and tone of advice based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, the server will provide advice in a calm tone. Emotion data is used to select templates for advice messages and adjust the tone.

[1395] The device provides tailored advice to the user in real time, and if the user is not stressed, the advice is provided in a normal tone.

[1396] Providing incentives

[1397] The server adjusts the type of incentive to provide based on the emotions recognized by the emotion engine. A points system is applied to fuel-efficient driving to provide incentives to users. These points are calculated based on the evaluation score of the driving data. An evaluation algorithm is used to calculate and apply the points.

[1398] The terminal notifies the user that points have been awarded and applies the points to an incentive program, which is integrated into the incentive program using an API.

[1399] Users can view the points they have earned and use them for rewards and discounts, which motivates them to drive more efficiently.

[1400] Specific examples

[1401] For example, driving data is collected while a driver is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data to understand the driver's emotional state. If the driver appears stressed, the server provides specific advice in a calm tone, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining an appropriate speed, thereby improving fuel efficiency. Furthermore, if the driver is determined to be relaxed, incentives can be actively provided to further motivate them. This allows users to save on fuel costs and contribute to the environment.

[1402] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1403] Step 1:

[1404] Acquire driving data from sensors installed in the vehicle

[1405] The server acquires driving data in real time from the vehicle's speed sensor, acceleration sensor, and GPS sensor. Specifically, it continuously monitors the data stream from each sensor and converts the collected data into a specified format (for example, JSON format).

[1406] Input: Speed, acceleration, position information

[1407] Output: Format converted operation data

[1408] Step 2:

[1409] Compression and transmission of driving data

[1410] The terminal compresses the collected data and sends it to the server periodically (for example, every minute). Specifically, the terminal compresses the collected data in ZIP format or similar and sends an HTTP POST request to the specified server endpoint.

[1411] Input: Format converted operation data

[1412] Output: Compressed driving data

[1413] Step 3:

[1414] Analysis of driving data

[1415] The server analyzes the received driving data based on the generated AI model. Specifically, the data is input into the AI ​​model to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops in real time.

[1416] Input: Decompressed driving data

[1417] Output: Driving style analysis results

[1418] Step 4:

[1419] Generating Advice

[1420] The server generates specific advice for improving fuel efficiency based on the analysis results. Specifically, it generates advice messages based on templates and stores them in a database.

[1421] Input: Driving style analysis results

[1422] Output: Specific advice message

[1423] Step 5:

[1424] Providing advice

[1425] The device provides the user with advice sent from the server in real time, specifically by generating audio guidance using a speech synthesis engine and displaying the advice visually on a display.

[1426] Input: Specific advice message

[1427] Output: Providing advice to the user (audio and display)

[1428] Step 6:

[1429] Reflecting user driving

[1430] The user confirms the advice provided and applies it to their driving, specifically by operating the accelerator and adjusting speed according to the advice.

[1431] Input: Specific advice

[1432] Output: Driving operation based on advice

[1433] Step 7:

[1434] Emotional Data Analysis

[1435] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from their facial expressions and tone of voice. Specifically, it uses facial recognition software and voice analysis software to analyze the user's emotions in real time.

[1436] Input: User's facial expression data, tone of voice

[1437] Output: Parsed emotion data

[1438] Step 8:

[1439] Tailoring advice based on emotions

[1440] The server adjusts the content and tone of advice based on the analyzed emotional data. Specifically, it references the emotional data to select a template for the advice message and adjust the tone.

[1441] Input: Parsed emotion data

[1442] Output: Adjusted advice message

[1443] Step 9:

[1444] Incentive calculation and awarding

[1445] The server applies a point system to fuel-efficient driving and gives incentives to users. Specifically, it calculates points based on driving data and evaluation scores and stores them in a database.

[1446] Input: Driving data, evaluation score

[1447] Output: Incentive points

[1448] Step 10:

[1449] Incentive notification and use

[1450] The terminal notifies the user that points have been awarded and applies them to incentive programs. The user can then check the points they have earned and use them for rewards and discounts.

[1451] Input: Incentive points

[1452] Output: Incentive notification, point usage

[1453] (Application example 2)

[1454] 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."

[1455] Conventional vehicle driver assistance systems focused on collecting and analyzing driving data, and were unable to recognize and respond to driver emotions in real time. This made it difficult to respond appropriately to the driver's stress state and emotional changes, leading to a demand for further improvements in driving efficiency and ensuring safety. There was also a lack of incentive systems that could simultaneously improve fuel efficiency and increase driver motivation.

[1456] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring driving data from sensors installed in the vehicle, means for analyzing the acquired driving data using a generative AI model, means for generating advice for improving driving based on the analysis results, means for providing the generated advice to the driver in real time, means for saving the driving data and advice history and visualizing driving performance, means for providing incentives for fuel-efficient driving, means for recognizing the driver's emotions using sensors such as an installed camera and microphone, and means for adjusting the content and tone of the advice based on the emotional data. This makes it possible to grasp the driver's emotional state in real time and provide appropriate advice depending on the situation. This reduces driver stress, improves driving efficiency, and further reduces costs and protects the environment by improving fuel efficiency.

[1457] "Vehicle sensors" refer to various sensors installed in a vehicle, such as speed sensors, acceleration sensors, and GPS sensors, and have the function of acquiring driving data.

[1458] A "generative AI model" is an artificial intelligence model that learns from past driving data and analyzes and predicts driving patterns.

[1459] "Analysis means" refers to a device or software that analyzes acquired driving data based on a generative AI model and identifies driving tendencies and patterns.

[1460] The "advice generating means" has a function of automatically generating specific advice for improving driving based on the analysis results obtained by the analysis means.

[1461] The "real-time providing means" refers to a method or system for immediately providing the generated advice to the driver, and includes voice guidance and display.

[1462] The "history storage means" refers to a storage device such as a memory or database that records and stores the driving data and advice history so that it can be referenced at a later date.

[1463] The "driving performance visualization means" has a function to display the saved driving data and advice history in a visual format such as a graph or chart so that the driver can check it.

[1464] An "incentive granting means" is a method or system that provides points or rewards for fuel-efficient driving, and serves to keep drivers motivated.

[1465] The "emotion recognition means" has the function of analyzing the driver's facial expression and tone of voice using sensors such as cameras and microphones mounted on the vehicle, and identifying the driver's emotional state.

[1466] The "tone adjustment means" has a function of appropriately adjusting the content and tone of advice based on the emotion data obtained by the emotion recognition means.

[1467] System Overview

[1468] This system is realized by combining multiple sensors installed in the vehicle, a server, and the driver's device such as a smartphone or tablet. Its main functions include collecting and analyzing driving data, providing real-time advice, recognizing emotions, storing and visualizing history, and providing incentives.

[1469] Data collection

[1470] The server acquires driving data from various sensors installed in the vehicle, such as speed sensors, acceleration sensors, and GPS sensors. This data is sent to the server in real time via the terminal. To collect particularly accurate data, external sensor devices connected via Bluetooth or Wi-Fi can also be used.

[1471] Data analysis

[1472] The server analyzes the acquired driving data based on a generative AI model. The generative AI model learns from past driving data to identify driving trends such as sudden acceleration and deceleration, average speed, and number of stops. This allows it to extract driving patterns that lead to improved fuel efficiency.

[1473] Providing advice

[1474] The server generates appropriate driving advice based on the analysis results. The advice is provided to the driver in real time via the terminal. The terminal communicates the advice to the driver using voice guidance and on-screen displays.

[1475] User Emotion Recognition

[1476] The device uses the smartphone or tablet's camera and microphone to analyze the driver's facial expressions and tone of voice to recognize their emotional state. The server analyzes the acquired emotional data and evaluates the user's emotional state. Machine learning models are used to improve the accuracy of emotion recognition.

[1477] Advice adjustment

[1478] The server adjusts the content and tone of the advice based on the driver's emotional data. For example, if the driver is feeling stressed, the server will provide advice in a calm tone such as, "Drive calmly. Avoid sudden acceleration to improve fuel efficiency."

[1479] History storage and visualization

[1480] The server stores driving data and advice history in a database. The device visualizes the stored data in graphs and charts and provides them to the driver, allowing the driver to review past driving data and objectively evaluate their own driving style.

[1481] Providing incentives

[1482] The server provides a function to award points for fuel-efficient driving. The terminal notifies the driver that points have been awarded and allows the driver to exchange the points for rewards in cooperation with an incentive program. This motivates the driver to drive more fuel-efficiently.

[1483] Specific examples

[1484] While the driver is driving on the highway, the system collects speed and acceleration data in real time and sends it to a server. The server then analyzes the collected data using a generative AI model, taking into account the driver's facial expressions and voice data, and provides specific advice such as "maintaining a constant speed will improve fuel efficiency." Additionally, if the driver is relaxed, points are actively awarded to maintain the driver's motivation.

[1485] Prompt Sentence Examples

[1486] The driver's emotion has been identified as "Angry." Provide driving advice in a calm tone. For example, "Drive calmly. Avoiding sudden acceleration will improve fuel economy."

[1487] This allows for driving assistance that takes the driver's emotional state into appropriate consideration.

[1488] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1489] Step 1:

[1490] Input: Driving data from the vehicle's speed sensor, acceleration sensor, and GPS sensor.

[1491] Example: Obtaining speed, acceleration, position information, etc.

[1492] Processing: The device collects and compresses these driving data in real time.

[1493] Output: Compressed driving data.

[1494] Step 2:

[1495] Input: Compressed driving data.

[1496] Example: Collected data, such as speed, acceleration, and position per second.

[1497] Processing: The device periodically transmits the compressed driving data to the server, for example, every minute.

[1498] Output: Driving data sent to the server.

[1499] Step 3:

[1500] Input: Driving data sent to the server.

[1501] Example: Data received by the server, such as speed, acceleration, and location information from the start to the end of a driving session.

[1502] Processing: The server analyzes the received driving data based on the generative AI model.

[1503] Output: Driving style analysis results (sudden acceleration, sudden deceleration, average speed, number of stops, etc.).

[1504] Step 4:

[1505] Input: Analysis results.

[1506] Examples include: number of sudden accelerations, average speed, number of stops, etc.

[1507] Processing: The server generates appropriate driving advice based on the analysis results, such as "avoid sudden acceleration" or "maintain a constant speed."

[1508] Output: The generated driving advice.

[1509] Step 5:

[1510] Input: Generated driving advice.

[1511] Examples: Specific advice such as "avoid sudden acceleration" or "maintain a steady speed."

[1512] Processing: The device provides real-time advice to the driver, conveying the advice through voice prompts and on-screen displays.

[1513] Output: Advice provided in a form that the user can understand.

[1514] Step 6:

[1515] Input: Driver facial expressions and tone of voice captured from cameras and microphones.

[1516] Example: Facial images and audio data of a driver while driving.

[1517] Processing: The device performs emotion recognition based on data acquired through the camera and microphone.

[1518] Output: Perceived driver emotional state (anger, joy, stress, etc.).

[1519] Step 7:

[1520] Input: Perceived driver emotional state.

[1521] Example: A driver is identified as "Angry."

[1522] Processing: The server adjusts the content and tone of the advice based on the emotional data. For example, if the user is feeling stressed, the server will provide advice in a calmer tone.

[1523] Output: Tailored advice.

[1524] Step 8:

[1525] Input: Driving data, advice history.

[1526] Example: Data from past driving sessions and advice provided.

[1527] Processing: The server stores the driving data and advice history in a database.

[1528] Output: Driving history and advice history stored in a database.

[1529] Step 9:

[1530] Input: Driving history and advice history stored in a database.

[1531] Example: Visual data formats such as graphs and charts.

[1532] Processing: The device visualizes the stored data and provides it to the driver, for example by providing trend analysis and graphical representations of historical data.

[1533] Output: Visualized driving data and advice history.

[1534] Step 10:

[1535] Input: Driving data rating score.

[1536] Example: Points calculation based on fuel-efficient driving.

[1537] Processing: The server awards points for fuel-efficient driving and links to incentive programs.

[1538] Output: Points awarded and notification to the user.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] [Fourth embodiment]

[1543] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1544] 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.

[1545] 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).

[1546] 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.

[1547] 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.

[1548] 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).

[1549] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1550] 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.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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."

[1556] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. It also has a means for providing incentives for fuel-efficient driving.

[1557] Data collection

[1558] server

[1559] Driving data is acquired from sensors installed in the vehicle (e.g., speed sensor, acceleration sensor, GPS sensor), which allows the vehicle's speed, acceleration, location information, etc. to be recorded in real time.

[1560] Terminal

[1561] The acquired data is compressed and sent to the server periodically, for example every minute.

[1562] User

[1563] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[1564] Analyzing the data

[1565] server

[1566] The acquired driving data is analyzed using a generative AI model, which learns from past driving data and can extract driving patterns that contribute to improved fuel efficiency.

[1567] As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[1568] Providing advice

[1569] server

[1570] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[1571] Terminal

[1572] Advice sent from the server is provided to the user in real time, using audio guidance and on-screen displays.

[1573] User

[1574] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[1575] History storage and visualization

[1576] server

[1577] The driving data and advice history is stored in a database, which is later used to evaluate driving performance.

[1578] The stored data can be analyzed to calculate statistics and trends.

[1579] Terminal

[1580] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[1581] User

[1582] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[1583] Providing incentives

[1584] server

[1585] A points system is applied to incentive users for fuel-efficient driving. The points are calculated based on the evaluation score of driving data.

[1586] Terminal

[1587] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[1588] User

[1589] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[1590] As a concrete example, driving data is collected while a user is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of times there was sudden acceleration or deceleration, and the distance traveled. The server analyzes this data and provides the user with specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The user then follows the advice and continues driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the user to save on fuel costs and contribute to the environment.

[1591] The above is an embodiment of the present invention.

[1592] The processing flow will be explained below.

[1593] Step 1: Acquiring Sensor Data

[1594] The terminal acquires driving data in real time from various sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.).

[1595] Specific operation: Obtain speed data from the speed sensor every second, obtain location information from the GPS sensor every second, and collect acceleration data from the acceleration sensor.

[1596] Step 2: Compress and send the data

[1597] The terminal compresses the collected driving data at regular intervals (for example, every minute) and transmits it to the server.

[1598] Specific operation: Collected data is compressed into CSV format and sent to the server using HTTPS.

[1599] Step 3: Receiving and storing data

[1600] The server receives the data sent from the terminal and stores it in a database.

[1601] Specific operation: The received data is inserted into a database for analysis (e.g. MongoDB) and stored using the session ID as a key.

[1602] Step 4: Analysis by generative AI model

[1603] The server inputs the stored data into a generative AI model to analyze driving style.

[1604] Specific operation: Data is input into a generative AI model to extract features such as patterns of sudden acceleration and deceleration, average speed, and distance traveled.

[1605] Step 5: Evaluate driving and generate advice

[1606] The server evaluates the driving style based on the analysis results and generates specific advice for improving fuel efficiency.

[1607] Specific behavior: The AI ​​model evaluates the driving style on a scale of 70 / 100 and generates advice such as "avoid sudden acceleration" and "maintain a constant speed."

[1608] Step 6: Submitting Advice

[1609] The server transmits the generated advice to the terminal.

[1610] Specific behavior: Advice is encoded in JSON format and sent to the device via an HTTP POST request.

[1611] Step 7: Viewing Advice

[1612] The device displays the received advice to the user in real time, using various display methods including text, graphics, and audio guidance.

[1613] Specific operation: A text message saying "Avoid sudden acceleration" is displayed on the screen, and the same advice is spoken aloud using voice synthesis.

[1614] Step 8: User execution

[1615] The user checks the advice provided and applies it to their actual driving.

[1616] Specific actions: The user follows the advice and presses the accelerator pedal slowly to avoid sudden acceleration.

[1617] Step 9: Save historical data

[1618] The server stores the data and advice history for each driving session in a database.

[1619] Specific operation: Driving data and generated advice are saved together so that the user can check them later.

[1620] Step 10: Visualize the data

[1621] The server calculates statistics and trends based on historical data and provides the data in a format that can be visually confirmed by the user.

[1622] What it does: Create monthly reports of driving data and generate graphs and charts.

[1623] Step 11: Send visualization data

[1624] The server transmits the generated visualization data to the terminal.

[1625] Specific behavior: Convert the report to PDF format and send it to the device.

[1626] Step 12: View the report

[1627] The terminal displays the received report on a user interface.

[1628] What it does: Opens the monthly report on the device and displays past driving data as graphs and charts.

[1629] Step 13: Calculate and award incentives

[1630] The server calculates incentives (points) based on the driving evaluation and assigns them to the user's account.

[1631] Specific operation: Calculate incentive points based on the evaluation score and add 50 points to the user ID.

[1632] Step 14: Points Notification

[1633] The terminal notifies the user that the points have been awarded.

[1634] Specific behavior: Display a pop-up notification such as "50 eco-driving points have been awarded."

[1635] Step 15: Use your points

[1636] Users can check their accumulated points and use them for special offers and discounts at partner stores.

[1637] Specific operation: Check points through the terminal and use them for discounts at online shops.

[1638] Example 1

[1639] 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."

[1640] In order to achieve efficient fuel consumption and reduce environmental impact, a system is needed that enables drivers to accurately understand and practice how to drive. However, conventional systems do not adequately process driving data in real time, which can delay feedback to the driver, making it difficult to improve driving efficiency. In addition, there was a lack of effective visualization of driving data and the provision of incentives, making it difficult to improve driver motivation.

[1641] 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.

[1642] In this invention, the server includes a means for acquiring driving data from multiple sensors installed in the vehicle, a means for analyzing the acquired driving data using a generative AI model, and a means for generating specific advice for improving driving based on the analysis results. This allows for real-time acquisition of driving data and analysis using the generative AI model, enabling immediate and specific feedback to the driver. Furthermore, adding a means for saving the driving data and advice history, visualizing driving performance, and providing incentives for fuel-efficient driving can improve the driver's motivation and achieve efficient driving.

[1643] The "multiple sensors" refer to a number of sensor devices, such as a speed sensor, an acceleration sensor, and a GPS sensor, that are mounted on a vehicle to collect driving data of the vehicle.

[1644] "Driving data" refers to information about vehicle driving, such as speed, acceleration, location information, distance traveled, and driving behavior, and is data acquired from multiple sensors.

[1645] A "generative AI model" is an artificial intelligence model used to learn from past driving data and analyze driving patterns and fuel efficiency.

[1646] "Analysis" refers to the process of using generative AI models to identify driving patterns and styles based on captured driving data.

[1647] "Specific advice" refers to advice that the generative AI model provides to the driver based on the analysis of driving data to improve driving efficiency and reduce fuel consumption.

[1648] "Real-time" refers to the time frame in which data is acquired and processed immediately, with little or no delay, to provide results.

[1649] "History" refers to data that records and saves driving data acquired in the past and advice generated in chronological order.

[1650] "Visualization" refers to the process of displaying collected driving data and advice history in visual formats such as graphs and charts to make the data easier for drivers to understand.

[1651] "Incentives" are benefits or rewards offered to drivers to encourage efficient driving.

[1652] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from multiple sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. It also has a means for providing incentives for fuel-efficient driving.

[1653] The server acquires driving data in real time from multiple sensors, including speed sensors, acceleration sensors, and GPS sensors. This driving data includes speed, acceleration, location information, distance traveled, driving behavior, and more. The terminal also compresses the acquired driving data at regular intervals (for example, every minute) and sends it to the server via the Internet. The driver does not need to perform any special operations; data is collected automatically simply by driving normally.

[1654] Once the data is sent to the server, the server analyzes the collected driving data based on a generative AI model. The generative AI model learns from past driving data and extracts driving patterns that contribute to improving fuel efficiency. This analysis process begins when the server provides a prompt to the generative AI model. For example, the server might pass the prompt to the model: "Please generate optimal fuel efficiency improvement advice from this driving data."

[1655] Based on the analysis results generated by the generative AI model, the server provides specific advice to the driver in real time, such as "avoid sudden acceleration" or "maintain a constant speed," allowing the driver to immediately improve their driving style.

[1656] Furthermore, the server stores driving data and the history of advice provided in a database. The stored history is later used to evaluate driving performance and is visualized through the terminal. The terminal displays past driving data in graphs and charts and provides it to the driver. The driver can review this data to objectively evaluate their own driving style and obtain specific clues for improvement.

[1657] To encourage fuel-efficient driving, the server applies a point system and awards points for fuel-efficient driving. These points are calculated based on the evaluation score of driving data and are offered to drivers as an incentive. The terminal notifies the driver of the awarded points, which the driver can confirm and use for rewards or discounts. This motivates the driver to drive more efficiently.

[1658] As a concrete example, driving data is collected from a vehicle traveling on a highway. The driving data includes the number of times the speed exceeded 100 km / h, the number of times sudden acceleration or deceleration occurred, and the distance traveled. The server analyzes this data and provides the driver with specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the driver to save on fuel costs and contribute to the environment.

[1659] An example prompt is, "Based on your driving data from the past week, please provide some advice on how to maximize fuel economy on your next trip."

[1660] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1661] Step 1:

[1662] The server acquires driving data from multiple sensors installed in the vehicle. Input data from the sensors includes speed, acceleration, and location information. The server collects this data in real time and stores it in a database. Specifically, it interprets data packets sent from the sensors and stores them in a structured format.

[1663] Step 2:

[1664] The server processes the acquired driving data in batches at regular intervals. Specifically, it compresses the data and prepares it for transfer to the terminal. The input raw data is reduced in size using a compression algorithm to make efficient use of network bandwidth. The compressed data is generated as output.

[1665] Step 3:

[1666] The terminal receives the compressed data sent from the server and performs decompression processing. The input data is compressed driving data, and this decompression processing reconstructs the original driving data. The reconstructed data is sent back to the server or temporarily stored on the terminal.

[1667] Step 4:

[1668] The server analyzes the decompressed driving data based on the generative AI model. The input data is the decompressed driving data, which undergoes a process of being input into the generative AI model. Specifically, a prompt statement is passed to the generative AI model and analysis is performed. The prompt statement used is "Please generate optimal fuel economy improvement advice from this data." The analysis results output insights into driving patterns and fuel economy improvement.

[1669] Step 5:

[1670] The server generates specific driving improvement advice based on the analysis results obtained from the generative AI model. The input data is the analysis results, from which information such as the number of sudden accelerations and decelerations and average speed is extracted. Specific operations involve applying an algorithm that generates advice statements based on conditions. For example, the output might be, "Maintaining a constant speed will improve fuel efficiency."

[1671] Step 6:

[1672] The terminal receives advice sent from the server and provides it to the driver in real time. The input data is advice text, which is processed to be displayed as a voice guide or on a display. Specifically, the advice is played back as a voice using a speech synthesis engine, or displayed as text on a display.

[1673] Step 7:

[1674] The server stores driving data and advice history in a database. The input data is raw driving data and advice history, which is stored in a structured format. The stored data is later analyzed to provide statistics and trends as output.

[1675] Step 8:

[1676] The terminal visualizes the driving data and advice history stored in the database and provides it to the user. The input data is the stored history data, and a visualization algorithm is applied to display it in graph or chart format. Specifically, the terminal uses a visualization library to generate graphs and charts and display them to the user.

[1677] Step 9:

[1678] The server applies a points system to incentive users for fuel-efficient driving. The input data is the evaluation score, and the server applies a points calculation algorithm to calculate points. The calculated points are obtained as output and added to the user profile.

[1679] Step 10:

[1680] The device receives the notification of point award sent from the server and notifies the user. The input data is point information, and processing is performed to notify the user of this. Specifically, the device's notification function is used to display a message indicating that points have been awarded, or the notification is sent via an application.

[1681] Step 11:

[1682] Users can check the points they have earned and use them for special offers or discounts. The input data is point information, which is evaluated and used for specific services or products. Specific operations include using points to receive discounts at online stores or participating in point exchange programs.

[1683] (Application example 1)

[1684] 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."

[1685] The present invention relates to a system for improving vehicle driving efficiency and reducing fuel consumption. However, conventional systems do not provide advice to drivers in real time, and it is difficult for drivers to intuitively understand the advice. Furthermore, there is a problem that the system does not provide sufficient incentives for fuel-efficient driving, which reduces driver motivation.

[1686] 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.

[1687] In this invention, the server includes means for acquiring driving data from sensors mounted on the vehicle, means for analyzing the acquired driving data based on a generative AI model, means for generating advice for improving driving based on the analysis results, means for providing the generated advice to the driver in real time, means for displaying the driving data on smart glasses or a head-mounted display to visualize it for the driver, means for saving the driving data and advice history and visualizing driving performance, and means for providing incentives for fuel-efficient driving. This allows the driver to receive intuitive advice in real time, thereby increasing their motivation to drive fuel-efficiently.

[1688] "Sensors mounted on a vehicle" are devices for acquiring information such as the vehicle's speed, acceleration, and location.

[1689] "Driving data" refers to various information related to driving, such as vehicle speed, acceleration, and location information.

[1690] A "generative AI model" is an artificial intelligence model that analyzes collected driving data and extracts patterns to improve fuel efficiency and driving.

[1691] "Provided in real time" means that advice is provided instantly while driving, without delay.

[1692] "Smart glasses and head-mounted displays" refer to wearable devices that drivers wear to display driving advice in real time as visual information.

[1693] "Storing and visualizing history" means recording past driving data and advice information and displaying it in a format that can be easily referenced later.

[1694] "Providing incentives" means offering rewards such as points or perks for fuel-efficient driving.

[1695] An embodiment of the present invention is described below. It is a system for improving driving efficiency in a vehicle and reducing fuel consumption. This system acquires driving data from sensors installed in the vehicle, analyzes it based on a generative AI model, and provides advice to the driver in real time. It also stores the driving data and advice history, visualizes driving performance, and provides incentives for fuel-efficient driving.

[1696] Data collection

[1697] server

[1698] Driving data is acquired from sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.), which allows speed, acceleration, location information, etc. to be recorded in real time.

[1699] Terminal

[1700] The acquired data is compressed and sent to the server periodically, for example, every minute.

[1701] User

[1702] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[1703] Analyzing the data

[1704] server

[1705] The acquired driving data is analyzed using a generative AI model. By learning from past driving data, this model can extract driving patterns that contribute to improved fuel efficiency. As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[1706] Providing advice

[1707] server

[1708] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[1709] Terminal

[1710] Advice sent from the server is provided to the user in real time using audio guidance and on-screen displays using smart glasses or a head-mounted display.

[1711] User

[1712] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[1713] History storage and visualization

[1714] server

[1715] Driving data and advice history is stored in a database. This data is later used to evaluate driving performance. The stored data can also be analyzed to calculate statistics and trends.

[1716] Terminal

[1717] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[1718] User

[1719] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[1720] Providing incentives

[1721] server

[1722] A points system is applied to incentive users for fuel-efficient driving. The points are calculated based on the evaluation score of driving data.

[1723] Terminal

[1724] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[1725] User

[1726] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[1727] Specific examples

[1728] While a user is driving on a highway, driving data is collected. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data and provides specific advice, such as "Maintaining a constant speed will improve fuel efficiency." The user can then follow the advice and continue driving while maintaining a speed below 100 km / h, thereby improving fuel efficiency. This allows the user to save on fuel costs and contribute to the environment.

[1729] Example prompt sentence:

[1730] "Generate advice to improve fuel efficiency for the driver based on the number of times the speed reached 110 km / h and the number of times the acceleration exceeded 3 m / s^2."

[1731] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1732] Step 1:

[1733] Input: Driving data obtained from sensors installed in the vehicle (speed, acceleration, position information, etc.)

[1734] Processing: Sensor data collection. This data is recorded in real time from the vehicle's speed sensor, acceleration sensor, and GPS sensor. The collected data is temporarily stored on the device.

[1735] Output: Raw driving data is saved to the device.

[1736] Step 2:

[1737] Input: Driving data stored on the device

[1738] Processing: The terminal periodically compresses the driving data and sends it to the server. This transmission is performed, for example, every minute. The compressed data is sent to the server via a communication line.

[1739] Output: Compressed driving data is sent to the server.

[1740] Step 3:

[1741] Input: Compressed driving data sent to the server

[1742] Processing: The server decompresses the received data and analyzes it based on the generative AI model. For analysis, an AI model (e.g., TensorFlow) that has learned from past driving data is used. Driving patterns such as sudden acceleration, sudden deceleration, average speed, and number of stops are extracted.

[1743] Output: Analysis results are generated.

[1744] Step 4:

[1745] Input: Analysis results

[1746] Processing: Based on the analysis results, the server generates specific advice for improving fuel efficiency. The generated advice might be, for example, "avoid sudden acceleration" or "maintain a constant speed." The analysis results are input into the generative AI model using prompt statements, and appropriate advice is generated.

[1747] Output: Fuel economy improvement advice is generated.

[1748] Step 5:

[1749] Input: Fuel economy improvement advice

[1750] Processing: The server sends the generated advice to the device, which then provides the advice to the driver in real time via smart glasses or a head-mounted display.

[1751] Output: Advice is displayed on the driver's device.

[1752] Step 6:

[1753] Input: Driver behavior data

[1754] Action: The user checks the provided advice and applies it to their driving. For example, they should try to avoid sudden acceleration and accelerate slowly.

[1755] Output: Driver behavior improves and driving data changes.

[1756] Step 7:

[1757] Input: Improved driving data and advice history

[1758] Processing: The server stores the driving data and advice history in a database, which is later used to evaluate driving performance.

[1759] Output: Driving data and advice history are stored in a database.

[1760] Step 8:

[1761] Input: Stored driving data and advice history

[1762] Processing: The server analyzes the stored data, calculates statistics and trends, and presents this data to the user in visualizations (graphs, charts, etc.).

[1763] Output: Visualized driving data and advice history are displayed on the terminal.

[1764] Step 9:

[1765] Input: visualized driving data and advice history

[1766] Processing: The user reviews the provided data and objectively evaluates their driving style. They learn effective driving techniques and apply them to future driving. For example, they understand which driving techniques have a positive impact on fuel economy.

[1767] Output: User's driving style is evaluated and fed back for the next drive.

[1768] Step 10:

[1769] Input: Evaluated driving data and points system

[1770] Processing: The server calculates points for fuel-efficient driving and awards incentives to the user. Points are calculated based on the evaluation score of the driving data. The terminal notifies the user that points have been awarded and applies the points to the connected incentive program.

[1771] Output: The user is given an incentive and notified.

[1772] 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.

[1773] This invention relates to a system for improving driving efficiency and reducing fuel consumption in vehicles. The system acquires driving data from sensors mounted on the vehicle and analyzes the data using a generative AI model to provide real-time advice to the driver. It also stores the driving data and advice history and visualizes driving performance. Furthermore, it has a means for providing incentives for fuel-efficient driving and incorporates an emotion engine that recognizes the user's emotions.

[1774] Data collection

[1775] server

[1776] Driving data is acquired from sensors installed in the vehicle (e.g., speed sensor, acceleration sensor, GPS sensor), which allows the vehicle's speed, acceleration, location information, etc. to be recorded in real time.

[1777] Terminal

[1778] The acquired data is compressed and sent to the server periodically, for example every minute.

[1779] User

[1780] The vehicle driver simply drives as normal without any special operations, and data is automatically collected and sent to the system.

[1781] Analyzing the data

[1782] server

[1783] The acquired driving data is analyzed using a generative AI model, which learns from past driving data and can extract driving patterns that contribute to improved fuel efficiency.

[1784] As a result of the analysis, it is possible to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops.

[1785] Providing advice

[1786] server

[1787] Based on the analysis results, specific advice for improving fuel efficiency is generated, such as "avoid sudden acceleration" or "maintain a constant speed."

[1788] Terminal

[1789] Advice sent from the server is provided to the user in real time, using audio guidance and on-screen displays.

[1790] User

[1791] The user can review the provided advice and apply it to their driving. For example, they can try to avoid sudden acceleration and accelerate slowly.

[1792] User Emotion Recognition

[1793] Terminal

[1794] Using sensors such as cameras and microphones installed in the vehicle, the system analyzes the driver's emotions from facial expressions, tone of voice, etc. This determines whether the driver is feeling stressed or relaxed.

[1795] server

[1796] The acquired emotional data is analyzed to understand the user's emotional state, which is then used to adjust the content of advice and the form of incentives.

[1797] History storage and visualization

[1798] server

[1799] The driving data and advice history is stored in a database, which is later used to evaluate driving performance.

[1800] The stored data can be analyzed to calculate statistics and trends.

[1801] Terminal

[1802] The saved data is visualized and provided to the user. Specifically, past driving data can be displayed using graphs and charts.

[1803] User

[1804] By checking the visualized data, you can objectively evaluate your own driving style, which will help you understand what kind of driving has affected your fuel economy.

[1805] Advice adjustment

[1806] server

[1807] The emotion engine adjusts the content and tone of advice based on the user's emotions. For example, if the user is feeling stressed, the advice will be given in a calmer tone.

[1808] Terminal

[1809] Providing tailored advice to users in real time.

[1810] Providing incentives

[1811] server

[1812] The type of incentive provided is adjusted based on the emotions recognized by the emotion engine. A points system is applied to reward fuel-efficient driving, and the points are calculated based on the evaluation score of the driving data.

[1813] Terminal

[1814] Notify the user that points have been awarded and apply the points to any connected incentive programs.

[1815] User

[1816] Users can view their earned points and use them for rewards and discounts, which motivates them to drive more efficiently.

[1817] As a concrete example, driving data is collected while a driver is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data to understand the driver's emotional state. If the driver is feeling stressed, the server provides specific advice in a calm tone, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining an appropriate speed, thereby improving fuel efficiency. Furthermore, if the driver is determined to be relaxed, incentives can be actively provided to further motivate them. This allows users to save on fuel costs and contribute to the environment.

[1818] The above is an embodiment of the present invention.

[1819] The processing flow will be explained below.

[1820] Step 1: Acquiring Sensor Data

[1821] The terminal acquires driving data in real time from various sensors installed in the vehicle (speed sensor, acceleration sensor, GPS sensor, etc.).

[1822] Specific operation: Obtain speed data from the speed sensor every second, obtain location information from the GPS sensor every second, and collect acceleration data from the acceleration sensor.

[1823] Step 2: Compress and send the data

[1824] The terminal compresses the collected driving data at regular intervals (for example, every minute) and transmits it to the server.

[1825] Specific operation: Collected data is compressed into CSV format and sent to the server using HTTPS.

[1826] Step 3: Receiving and storing data

[1827] The server receives the data sent from the terminal and stores it in a database.

[1828] Specific operation: The received data is inserted into a database for analysis (e.g. MongoDB) and stored using the session ID as a key.

[1829] Step 4: Analysis by generative AI model

[1830] The server inputs the stored data into a generative AI model to analyze driving style.

[1831] Specific operation: Data is input into a generative AI model to extract features such as patterns of sudden acceleration and deceleration, average speed, and distance traveled.

[1832] Step 5: Emotion Recognition with the Emotion Engine

[1833] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from facial expressions, tone of voice, etc.

[1834] Specific operation: Using a facial expression recognition algorithm, analyzes the user's facial expression data to determine emotions such as anger, joy, stress, etc. Analyzes audio data from the microphone to complement the emotional state.

[1835] Step 6: Evaluate driving and generate advice

[1836] The server evaluates the driver's driving style based on the analysis results and generates specific advice for improving fuel efficiency, incorporating the results of the emotion engine.

[1837] Specific behavior: If the AI ​​model evaluates the driving style as 70 / 100 and the user feels stressed, it generates advice in a gentle tone such as "avoid sudden acceleration" and "maintain a constant speed."

[1838] Step 7: Submitting Advice

[1839] The server transmits the generated advice to the terminal.

[1840] Specific behavior: Advice is encoded in JSON format and sent to the device via an HTTP POST request.

[1841] Step 8: Viewing Advice

[1842] The device displays the received advice to the user in real time, using various display methods including text, graphics, and audio guidance.

[1843] Specific operation: A text message saying "Avoid sudden acceleration" is displayed on the screen, and the same advice is spoken aloud using voice synthesis.

[1844] Step 9: User execution

[1845] The user checks the advice provided and applies it to their actual driving.

[1846] Specific actions: The user follows the advice and presses the accelerator pedal slowly to avoid sudden acceleration.

[1847] Step 10: Save historical data

[1848] The server stores the data and advice history for each driving session in a database.

[1849] Specific operation: Driving data and generated advice are saved together so that the user can check them later.

[1850] Step 11: Visualize the data

[1851] The server calculates statistics and trends based on historical data and provides the data in a format that can be visually confirmed by the user.

[1852] What it does: Create monthly reports of driving data and generate graphs and charts.

[1853] Step 12: Send visualization data

[1854] The server transmits the generated visualization data to the terminal.

[1855] Specific behavior: Convert the report to PDF format and send it to the device.

[1856] Step 13: View the report

[1857] The terminal displays the received report on a user interface.

[1858] What it does: Opens the monthly report on the device and displays past driving data as graphs and charts.

[1859] Step 14: Calculate and award incentives

[1860] The server calculates incentives (points) based on the driving evaluation and assigns them to the user's account, taking into account the results of the emotion engine.

[1861] Specific operation: Incentive points are calculated based on the evaluation score, and additional points are awarded for less stressful driving.

[1862] Step 15: Points Notification

[1863] The terminal notifies the user that the points have been awarded.

[1864] Specific behavior: Display a pop-up notification such as "50 eco-driving points have been awarded."

[1865] Step 16: Use your points

[1866] Users can check their accumulated points and use them for special offers and discounts at partner stores.

[1867] Specific operation: Check points through the terminal and use them for discounts at online shops.

[1868] Example 2

[1869] 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."

[1870] There are limitations to methods for improving driving efficiency and reducing fuel consumption. Existing technologies lack real-time driver advice and incentive systems that take into account the driver's emotional state. Furthermore, drivers lack the opportunity and means to objectively evaluate and improve their own driving style, making it difficult to comprehensively improve their driving performance.

[1871] 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.

[1872] In this invention, the server includes: means for acquiring driving data from sensors installed in the vehicle; means for periodically compressing the acquired driving data and transmitting the compressed data to the server; means for analyzing the acquired driving data using a generative AI model; means for generating specific advice for improving driving based on the analysis results; means for providing the generated advice to the driver in real time; means for storing the driving data and advice history in a database and visualizing driving performance; means for adjusting the content and tone of the advice using an emotion engine that recognizes the user's emotions; and means for providing incentives for fuel-efficient driving. This allows the system to analyze driving data in real time and provide specific advice to the driver, thereby improving driving performance and fuel efficiency. Furthermore, the emotion recognition function can be used to reduce driver stress and improve driving efficiency.

[1873] "Driving data" refers to data such as speed, acceleration, and position information obtained from sensors installed in the vehicle.

[1874] "Generative AI model" refers to an artificial intelligence model that learns from past driving data and analyzes driving patterns that contribute to improved fuel efficiency.

[1875] "Advice" refers to instructions or suggestions for improving driving that are generated based on the analysis of driving data and provided to the driver.

[1876] "Real-time" refers to a situation where data is acquired, analyzed, and advice is provided almost simultaneously, with very little delay.

[1877] "Emotion engine" refers to technology that analyzes emotions from the user's facial expressions, tone of voice, and other information obtained from sensors installed in the vehicle.

[1878] "Incentives" refer to points or rewards awarded to encourage improved driving performance and more fuel-efficient driving.

[1879] "Database" refers to an information system for storing and managing driving data and advice history.

[1880] "Sensor" refers to a device installed in a vehicle and used to acquire driving data, including speed sensors, acceleration sensors, and GPS sensors.

[1881] "Compression" refers to the process of reducing the size of collected data so that it can be stored or transmitted efficiently.

[1882] The present invention relates to a system for improving driving efficiency and reducing fuel consumption in a vehicle. This system acquires driving data from sensors mounted on the vehicle and analyzes the data based on a generative AI model to provide real-time advice to the driver. Specifically, hardware such as a speed sensor, an acceleration sensor, and a GPS sensor is used. The software used includes the AI ​​model (e.g., TensorFlow or PyTorch) required to analyze the data.

[1883] Data collection

[1884] The server centrally collects driving data acquired from the vehicle's speed sensor, acceleration sensor, GPS sensor, etc. This allows speed, acceleration, location information, etc. to be recorded in real time.

[1885] The terminal compresses the collected data and periodically (for example, every minute) transmits it to the server. The transmitted data is in a compressed format (for example, ZIP format) and is uploaded to the server using an HTTP POST request.

[1886] The user simply drives as usual and data is collected automatically, with no special operations or confirmations required.

[1887] Analyzing the data

[1888] The server analyzes the acquired driving data based on a generative AI model. The generative AI model learns from past driving data and can extract driving patterns that contribute to improving fuel efficiency. As a result of the analysis, it can identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops. TensorFlow and PyTorch are used as AI libraries for the analysis.

[1889] Providing advice

[1890] Based on the analysis results, the server generates specific advice for improving fuel efficiency, such as "avoid sudden acceleration" and "maintain a constant speed."

[1891] The device provides the user with advice sent from the server in real time, using voice guidance (using a speech synthesis engine) and on-screen displays.

[1892] The user can check the provided advice and apply it to their driving. For example, they can learn to refrain from sudden acceleration and to step on the accelerator slowly.

[1893] User Emotion Recognition

[1894] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from their facial expressions and tone of voice, determining whether they are stressed or relaxed. Facial recognition software and voice analysis software are used.

[1895] The server analyzes the acquired emotional data to understand the user's emotional state, which is then used to adjust the content of advice and the form of incentives.

[1896] History storage and visualization

[1897] The server stores driving data and advice history in a database, which allows for later evaluation of driving performance. SQL is typically used to manage the database.

[1898] The device visualizes the stored driving data and provides it to the user. Graph generation libraries such as Chart.js and D3.js are used to display historical driving data using graphs and charts.

[1899] Users can view the visualized data and objectively evaluate their own driving style, thereby understanding how their driving habits affect fuel economy.

[1900] Advice adjustment

[1901] The server adjusts the content and tone of advice based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, the server will provide advice in a calm tone. Emotion data is used to select templates for advice messages and adjust the tone.

[1902] The device provides tailored advice to the user in real time, and if the user is not stressed, the advice is provided in a normal tone.

[1903] Providing incentives

[1904] The server adjusts the type of incentive to provide based on the emotions recognized by the emotion engine. A points system is applied to fuel-efficient driving to provide incentives to users. These points are calculated based on the evaluation score of the driving data. An evaluation algorithm is used to calculate and apply the points.

[1905] The terminal notifies the user that points have been awarded and applies the points to an incentive program, which is integrated into the incentive program using an API.

[1906] Users can view the points they have earned and use them for rewards and discounts, which motivates them to drive more efficiently.

[1907] Specific examples

[1908] For example, driving data is collected while a driver is driving on a highway. This data includes the number of times the speed exceeded 100 km / h, the number of sudden accelerations and decelerations, and the distance traveled. The server analyzes this data to understand the driver's emotional state. If the driver appears stressed, the server provides specific advice in a calm tone, such as "Maintaining a constant speed will improve fuel efficiency." The driver then follows the advice and continues driving while maintaining an appropriate speed, thereby improving fuel efficiency. Furthermore, if the driver is determined to be relaxed, incentives can be actively provided to further motivate them. This allows users to save on fuel costs and contribute to the environment.

[1909] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1910] Step 1:

[1911] Acquire driving data from sensors installed in the vehicle

[1912] The server acquires driving data in real time from the vehicle's speed sensor, acceleration sensor, and GPS sensor. Specifically, it continuously monitors the data stream from each sensor and converts the collected data into a specified format (for example, JSON format).

[1913] Input: Speed, acceleration, position information

[1914] Output: Format converted operation data

[1915] Step 2:

[1916] Compression and transmission of driving data

[1917] The terminal compresses the collected data and sends it to the server periodically (for example, every minute). Specifically, the terminal compresses the collected data in ZIP format or similar and sends an HTTP POST request to the specified server endpoint.

[1918] Input: Format converted operation data

[1919] Output: Compressed driving data

[1920] Step 3:

[1921] Analysis of driving data

[1922] The server analyzes the received driving data based on the generated AI model. Specifically, the data is input into the AI ​​model to identify driving styles such as sudden acceleration, sudden deceleration, average speed, and number of stops in real time.

[1923] Input: Decompressed driving data

[1924] Output: Driving style analysis results

[1925] Step 4:

[1926] Generating Advice

[1927] The server generates specific advice for improving fuel efficiency based on the analysis results. Specifically, it generates advice messages based on templates and stores them in a database.

[1928] Input: Driving style analysis results

[1929] Output: Specific advice message

[1930] Step 5:

[1931] Providing advice

[1932] The device provides the user with advice sent from the server in real time, specifically by generating audio guidance using a speech synthesis engine and displaying the advice visually on a display.

[1933] Input: Specific advice message

[1934] Output: Providing advice to the user (audio and display)

[1935] Step 6:

[1936] Reflecting user driving

[1937] The user confirms the advice provided and applies it to their driving, specifically by operating the accelerator and adjusting speed according to the advice.

[1938] Input: Specific advice

[1939] Output: Driving operation based on advice

[1940] Step 7:

[1941] Emotional Data Analysis

[1942] The device uses sensors such as cameras and microphones installed in the vehicle to analyze the user's emotions from their facial expressions and tone of voice. Specifically, it uses facial recognition software and voice analysis software to analyze the user's emotions in real time.

[1943] Input: User's facial expression data, tone of voice

[1944] Output: Parsed emotion data

[1945] Step 8:

[1946] Tailoring advice based on emotions

[1947] The server adjusts the content and tone of advice based on the analyzed emotional data. Specifically, it references the emotional data to select a template for the advice message and adjust the tone.

[1948] Input: Parsed emotion data

[1949] Output: Adjusted advice message

[1950] Step 9:

[1951] Incentive calculation and awarding

[1952] The server applies a point system to fuel-efficient driving and gives incentives to users. Specifically, it calculates points based on driving data and evaluation scores and stores them in a database.

[1953] Input: Driving data, evaluation score

[1954] Output: Incentive points

[1955] Step 10:

[1956] Incentive notification and use

[1957] The terminal notifies the user that points have been awarded and applies them to incentive programs. The user can then check the points they have earned and use them for rewards and discounts.

[1958] Input: Incentive points

[1959] Output: Incentive notification, point usage

[1960] (Application example 2)

[1961] 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."

[1962] Conventional vehicle driver assistance systems focused on collecting and analyzing driving data, and were unable to recognize and respond to driver emotions in real time. This made it difficult to respond appropriately to the driver's stress state and emotional changes, leading to a demand for further improvements in driving efficiency and ensuring safety. There was also a lack of incentive systems that could simultaneously improve fuel efficiency and increase driver motivation.

[1963] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring driving data from sensors installed in the vehicle, means for analyzing the acquired driving data using a generative AI model, means for generating advice for improving driving based on the analysis results, means for providing the generated advice to the driver in real time, means for saving the driving data and advice history and visualizing driving performance, means for providing incentives for fuel-efficient driving, means for recognizing the driver's emotions using sensors such as an installed camera and microphone, and means for adjusting the content and tone of the advice based on the emotional data. This makes it possible to grasp the driver's emotional state in real time and provide appropriate advice depending on the situation. This reduces driver stress, improves driving efficiency, and further reduces costs and protects the environment by improving fuel efficiency.

[1964] "Vehicle sensors" refer to various sensors installed in a vehicle, such as speed sensors, acceleration sensors, and GPS sensors, and have the function of acquiring driving data.

[1965] A "generative AI model" is an artificial intelligence model that learns from past driving data and analyzes and predicts driving patterns.

[1966] "Analysis means" refers to a device or software that analyzes acquired driving data based on a generative AI model and identifies driving tendencies and patterns.

[1967] The "advice generating means" has a function of automatically generating specific advice for improving driving based on the analysis results obtained by the analysis means.

[1968] The "real-time providing means" refers to a method or system for immediately providing the generated advice to the driver, and includes voice guidance and display.

[1969] The "history storage means" refers to a storage device such as a memory or database that records and stores the driving data and advice history so that it can be referenced at a later date.

[1970] The "driving performance visualization means" has a function to display the saved driving data and advice history in a visual format such as a graph or chart so that the driver can check it.

[1971] An "incentive granting means" is a method or system that provides points or rewards for fuel-efficient driving, and serves to keep drivers motivated.

[1972] The "emotion recognition means" has the function of analyzing the driver's facial expression and tone of voice using sensors such as cameras and microphones mounted on the vehicle, and identifying the driver's emotional state.

[1973] The "tone adjustment means" has a function of appropriately adjusting the content and tone of advice based on the emotion data obtained by the emotion recognition means.

[1974] System Overview

[1975] This system is realized by combining multiple sensors installed in the vehicle, a server, and the driver's device such as a smartphone or tablet. Its main functions include collecting and analyzing driving data, providing real-time advice, recognizing emotions, storing and visualizing history, and providing incentives.

[1976] Data collection

[1977] The server acquires driving data from various sensors installed in the vehicle, such as speed sensors, acceleration sensors, and GPS sensors. This data is sent to the server in real time via the terminal. To collect particularly accurate data, external sensor devices connected via Bluetooth or Wi-Fi can also be used.

[1978] Data analysis

[1979] The server analyzes the acquired driving data based on a generative AI model. The generative AI model learns from past driving data to identify driving trends such as sudden acceleration and deceleration, average speed, and number of stops. This allows it to extract driving patterns that lead to improved fuel efficiency.

[1980] Providing advice

[1981] The server generates appropriate driving advice based on the analysis results. The advice is provided to the driver in real time via the terminal. The terminal communicates the advice to the driver using voice guidance and on-screen displays.

[1982] User Emotion Recognition

[1983] The device uses the smartphone or tablet's camera and microphone to analyze the driver's facial expressions and tone of voice to recognize their emotional state. The server analyzes the acquired emotional data and evaluates the user's emotional state. Machine learning models are used to improve the accuracy of emotion recognition.

[1984] Advice adjustment

[1985] The server adjusts the content and tone of the advice based on the driver's emotional data. For example, if the driver is feeling stressed, the server will provide advice in a calm tone such as, "Drive calmly. Avoid sudden acceleration to improve fuel efficiency."

[1986] History storage and visualization

[1987] The server stores driving data and advice history in a database. The device visualizes the stored data in graphs and charts and provides them to the driver, allowing the driver to review past driving data and objectively evaluate their own driving style.

[1988] Providing incentives

[1989] The server provides a function to award points for fuel-efficient driving. The terminal notifies the driver that points have been awarded and allows the driver to exchange the points for rewards in cooperation with an incentive program. This motivates the driver to drive more fuel-efficiently.

[1990] Specific examples

[1991] While the driver is driving on the highway, the system collects speed and acceleration data in real time and sends it to a server. The server then analyzes the collected data using a generative AI model, taking into account the driver's facial expressions and voice data, and provides specific advice such as "maintaining a constant speed will improve fuel efficiency." Additionally, if the driver is relaxed, points are actively awarded to maintain the driver's motivation.

[1992] Prompt Sentence Examples

[1993] The driver's emotion has been identified as "Angry." Provide driving advice in a calm tone. For example, "Drive calmly. Avoiding sudden acceleration will improve fuel economy."

[1994] This allows for driving assistance that takes the driver's emotional state into appropriate consideration.

[1995] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1996] Step 1:

[1997] Input: Driving data from the vehicle's speed sensor, acceleration sensor, and GPS sensor.

[1998] Example: Obtaining speed, acceleration, position information, etc.

[1999] Processing: The device collects and compresses these driving data in real time.

[2000] Output: Compressed driving data.

[2001] Step 2:

[2002] Input: Compressed driving data.

[2003] Example: Collected data, such as speed, acceleration, and position per second.

[2004] Processing: The device periodically transmits the compressed driving data to the server, for example, every minute.

[2005] Output: Driving data sent to the server.

[2006] Step 3:

[2007] Input: Driving data sent to the server.

[2008] Example: Data received by the server, such as speed, acceleration, and location information from the start to the end of a driving session.

[2009] Processing: The server analyzes the received driving data based on the generative AI model.

[2010] Output: Driving style analysis results (sudden acceleration, sudden deceleration, average speed, number of stops, etc.).

[2011] Step 4:

[2012] Input: Analysis results.

[2013] Examples include: number of sudden accelerations, average speed, number of stops, etc.

[2014] Processing: The server generates appropriate driving advice based on the analysis results, such as "avoid sudden acceleration" or "maintain a constant speed."

[2015] Output: The generated driving advice.

[2016] Step 5:

[2017] Input: Generated driving advice.

[2018] Examples: Specific advice such as "avoid sudden acceleration" or "maintain a steady speed."

[2019] Processing: The device provides real-time advice to the driver, conveying the advice through voice prompts and on-screen displays.

[2020] Output: Advice provided in a form that the user can understand.

[2021] Step 6:

[2022] Input: Driver facial expressions and tone of voice captured from cameras and microphones.

[2023] Example: Facial images and audio data of a driver while driving.

[2024] Processing: The device performs emotion recognition based on data acquired through the camera and microphone.

[2025] Output: Perceived driver emotional state (anger, joy, stress, etc.).

[2026] Step 7:

[2027] Input: Perceived driver emotional state.

[2028] Example: A driver is identified as "Angry."

[2029] Processing: The server adjusts the content and tone of the advice based on the emotional data. For example, if the user is feeling stressed, the server will provide advice in a calmer tone.

[2030] Output: Tailored advice.

[2031] Step 8:

[2032] Input: Driving data, advice history.

[2033] Example: Data from past driving sessions and advice provided.

[2034] Processing: The server stores the driving data and advice history in a database.

[2035] Output: Driving history and advice history stored in a database.

[2036] Step 9:

[2037] Input: Driving history and advice history stored in a database.

[2038] Example: Visual data formats such as graphs and charts.

[2039] Processing: The device visualizes the stored data and provides it to the driver, for example by providing trend analysis and graphical representations of historical data.

[2040] Output: Visualized driving data and advice history.

[2041] Step 10:

[2042] Input: Driving data rating score.

[2043] Example: Points calculation based on fuel-efficient driving.

[2044] Processing: The server awards points for fuel-efficient driving and links to incentive programs.

[2045] Output: Points awarded and notification to the user.

[2046] 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.

[2047] 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.

[2048] 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.

[2049] 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.

[2050] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2051] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2052] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2053] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2054] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2055] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2056] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2057] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2058] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2059] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2060] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2061] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2062] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2063] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resourc...

Claims

1. means for acquiring driving data from sensors mounted on the vehicle; A means for analyzing the acquired driving data based on a generative AI model; A means for generating advice for improving driving based on the analysis results; a means for providing the generated advice to the driver in real time; A means of storing driving data and advice history and visualizing driving performance; a means for providing incentives for fuel-efficient driving; A system including:

2. 10. The system of claim 1, further comprising means for periodically compressing the vehicle driving data and transmitting the compressed data to a server.

3. 10. The system of claim 1, further comprising means for storing driving data and advice history in a database.

Images