Internet-of-vehicles enterprise application system integration and intelligent collaboration method based on AI large model

Abstract

The invention belongs to the technical field of Internet of Vehicles, and discloses an Internet of Vehicles enterprise application system integration and intelligent collaboration method based on an AI large model, and the method comprises the following steps: a data collection layer obtains real-time data from a vehicle-mounted sensor, vehicle-mounted equipment and an external network; data cleaning and preprocessing are carried out on the collected real-time data; after data cleaning and preprocessing, the system fuses multi-dimensional data from different modules to realize intelligent decision making; all analysis and decision results are fed back to a vehicle owner or a platform administrator through a user interface; and realizing data collaboration and integration among the subsystems based on an AI large model. According to the Internet of Vehicles enterprise application system integration and intelligent collaboration method based on the AI large model, the AI large model is utilized to carry out intelligent fusion and collaboration work on each subsystem in an Internet of Vehicles remote supervision platform, so that information islands between different data sources and systems are broken; and the automation, intelligence and optimization capabilities of the Internet of Vehicles platform are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle networking, and particularly to an integrated and intelligent collaborative method for vehicle networking enterprise application systems based on an AI large model. Background Art

[0002] With the rapid development of vehicle networking technology, the vehicle remote supervision platform has become an important part of vehicle networking enterprises. This platform provides vehicle status information for vehicle owners, enterprises, and government departments by real-time monitoring data such as vehicle location, speed, fuel consumption, and driving behavior, and supports remote management functions. However, there are still many deficiencies in the existing vehicle remote supervision platform in terms of system integration, data collaboration, and intelligent decision-making, which limit the overall efficiency and business value of the platform.

[0003] Currently, most of the application systems within vehicle networking enterprises operate independently. Although some systems exchange data through standardized interfaces (such as APIs, web services), there is a lack of intelligent collaborative working mechanisms. The integration, data sharing, and real-time collaboration between different systems usually rely on manual configuration or rule-based middleware, resulting in increased system complexity, high maintenance costs, and poor flexibility. Specifically, the existing technical solutions have the following main problems:

[0004] Lack of intelligent and automated collaboration: Existing systems usually rely on hard-coded rules and manual intervention to coordinate the work processes between systems, and cannot intelligently optimize the collaboration of each system according to real-time data and business requirements. Due to the lack of AI technology, vehicle networking application systems are difficult to automatically adapt to and optimize collaborative work in the face of complex and dynamically changing environments. This way of relying on static rules and manual operations leads to low system response speed and collaborative efficiency, and cannot meet the high-efficiency requirements of modern vehicle networking services.

[0005] Serious information silo phenomenon: There is a widespread information silo problem between vehicle networking application systems, and data and functions cannot be effectively shared, resulting in information asymmetry or redundant processing. For example, vehicle location data is processed by the GPS system, and driving behavior data is processed by the behavior analysis system, but there is no effective linkage and sharing between these data. This isolated operation mode not only reduces the overall business efficiency and data utilization rate, but also leads to decision-making lag and resource waste.

[0006] Difficult system integration and poor flexibility: With the continuous expansion of the business scope and technical architecture of vehicle networking enterprises, the difficulty of integrating different systems has increased significantly. Especially when the architectures and technology stacks of application systems vary greatly, the complexity of system integration is further exacerbated. This problem of difficult integration and poor flexibility makes it difficult for existing platforms to quickly respond to changes in business requirements, limiting their scalability and adaptability.

[0007] In summary, the existing vehicle remote monitoring platforms have significant deficiencies in system integration, data collaboration, and intelligent decision-making, making it difficult to meet the efficient, flexible, and intelligent requirements of modern vehicle networking services. Therefore, there is an urgent need for a technical solution that can achieve intelligent data fusion, dynamic decision-making and adjustment, as well as real-time feedback and optimization, in order to enhance the overall efficiency and business value of the vehicle networking remote monitoring platform. Summary of the Invention

[0008] The objective of the present invention is to provide a method for integrating and intelligently collaborating vehicle networking enterprise application systems based on an AI large model, which uses the AI large model to connect and integrate various application systems within the vehicle networking enterprise, and automatically and intelligently optimizes the collaboration and data flow between systems; the AI large model can adaptively adjust the workflow according to real-time environmental changes, efficiently eliminate information silos, break down system barriers, and achieve seamless collaboration and data sharing between systems, thereby significantly enhancing the flexibility, response speed, and overall efficiency of the vehicle networking enterprise systems.

[0009] To achieve the above objective, the present invention provides a method for integrating and intelligently collaborating vehicle networking enterprise application systems based on an AI large model, including the following steps:

[0010] Step S1: The data acquisition layer obtains real-time data from in-vehicle sensors, in-vehicle devices, and external networks;

[0011] Step S2: Clean and preprocess the acquired real-time data;

[0012] Step S3: After data cleaning and preprocessing, the system fuses multi-dimensional data from different modules to achieve intelligent decision-making;

[0013] Step S4: The results of all analyses and decisions are fed back to the vehicle owner or platform administrator through the user interface;

[0014] Step S5: Achieve data collaboration and integration between each subsystem based on the AI large model.

[0015] Preferably, in step S1, in the implementation of the vehicle networking platform, the data acquisition layer is responsible for obtaining real-time data from in-vehicle sensors, in-vehicle devices, and external networks, and these data include but are not limited to:

[0016] (1) Vehicle data: such as position GPS, speed, engine status, fuel consumption;

[0017] (2) Driver data: such as driver behavior, physiological status;

[0018] (3) Environmental data: such as road conditions, traffic flow, weather conditions;

[0019] All collected data are transmitted to the cloud platform or remote monitoring center via wireless communication technology to ensure efficient data transmission.

[0020] Preferably, in step S2, the collected real-time data is cleaned and preprocessed, and the specific process is as follows:

[0021] Step S21, denoising: removing irrelevant data or erroneous data through a signal filtering algorithm;

[0022] Step S22, filling missing values: inferring and filling missing data to ensure data integrity;

[0023] Step S23: Standardization processing: unifying the data formats of different sensors to ensure the compatibility of different data sources.

[0024] Preferably, in step S3, after data cleaning and preprocessing, the system fuses multidimensional data from different modules to achieve intelligent decision-making. The specific process is as follows:

[0025] Step S31, multi-source data fusion;

[0026] Step S32, AI large model analysis;

[0027] Step S33: Intelligent decision and response.

[0028] Preferably, in step S31, multi-source data fusion specifically includes:

[0029] (1) Driver behavior data: Analyze the driver's fatigue driving and distracted driving behavior through the DMS system;

[0030] (2) Vehicle health monitoring data: real-time data provided by vehicle sensors to monitor the vehicle’s engine status, battery charge, and fuel consumption information;

[0031] (3) For environmental and road condition data: Analyze current road and weather conditions based on positioning and traffic flow monitoring data.

[0032] Preferably, in step S32, the system uses the AI big model to perform in-depth analysis to mine the associations between multi-dimensional data, including but not limited to:

[0033] (1) Analyze the relationship between driver fatigue and road traffic flow to determine whether the current driver needs a rest;

[0034] (2) In vehicle fault detection, the AI big model combines vehicle health data and environmental data to predict the occurrence of faults and automatically adjust driving strategies or remind the driver.

[0035] Preferably, in step S33, intelligent decision-making and response specifically include:

[0036] (1) Dynamic adjustment strategy: When the AI model detects that the driver is fatigued, the system automatically reminds and even intervenes through the autonomous driving system to adjust the vehicle driving mode;

[0037] (2) Real-time response: When encountering sudden traffic conditions, the system adjusts the driving route in real time and notifies the driver to drive safely.

[0038] Preferably, for the vehicle networking enterprise application system integration and intelligent collaboration method of the model, in step S4, the results of all analyses and decisions will be fed back to the vehicle owner or platform administrator through the user interface. The vehicle owner can view real-time data, receive warning messages, and suggestions through the mobile application and Web platform;

[0039] On the vehicle owner side, the vehicle owner can view real-time vehicle conditions, driving behavior analysis, fault warnings, and route planning information, enhancing the driving experience and safety;

[0040] On the management side, enterprise managers conduct real-time monitoring and scheduling of the vehicle fleet through the backend management system for higher-level vehicle management and analysis.

[0041] Preferably, in step S5, data collaboration and integration among various subsystems are realized based on the AI large model. The specific implementation process is as follows:

[0042] Step S51, Cross-system data sharing: The driver behavior analysis module obtains the data of the vehicle status module to determine whether the driver needs to rest or switch the driving mode;

[0043] Step S52, Dynamic adjustment and feedback: Based on the analysis results of multiple systems, the AI large model dynamically adjusts the warning time, autonomous driving system, and remote maintenance service.

[0044] Preferably, the network architecture includes: data acquisition layer, data transmission layer, data processing and decision-making layer, feedback and interaction layer;

[0045] ① Data acquisition layer: First, the sensor devices on the vehicle collect various types of data about the vehicle, driver, and environment in real time; then, the data is uploaded to the platform through wireless communication technology;

[0046] ② Data transmission layer: Transmits the collected data to the data processing and decision-making layer through the communication network in real time;

[0047] ③ Data processing and decision-making layer: First, use the AI large model to conduct in-depth analysis and intelligent decision-making on the received data, perform data fusion and collaborative processing; then, output the decision results and provide them to the downstream user interaction layer through the data feedback interface;

[0048] ④ User interaction layer: Vehicle owners and managers can view real-time vehicle status, driving behavior, environmental information, and decision feedback information through mobile applications and web platforms.

[0049] Therefore, the present invention adopts the above-mentioned method for integrating and intelligent collaboration of vehicle networking enterprise application systems based on AI large models, and the beneficial effects are as follows:

[0050] (1) The present invention realizes intelligent data fusion. Through the real-time fusion of multi-dimensional data, the problem of data islands is completely eliminated;

[0051] (2) The present invention supports dynamic decision-making and adjustment, and can adjust behaviors in real time according to the data analysis results and make intelligent responses;

[0052] (3) The present invention provides real-time feedback and optimization functions. Vehicle owners and administrators can view monitoring and decision results in real time, enhancing the system transparency and response speed;

[0053] (4) The present invention significantly improves efficiency. Through intelligent data fusion and decision-making, efficient fleet management and driving behavior optimization are realized;

[0054] (5) The present invention improves safety. The AI model can detect dangerous behaviors such as driver fatigue and distraction in real time, and issue warnings or take automatic intervention measures in advance;

[0055] (6) The present invention realizes intelligent operation. The vehicle networking platform can not only monitor the vehicle status in real time, but also perform automated operations such as intelligent path planning and fault warning, reducing manual intervention.

[0056] Next, through the accompanying drawings and embodiments, the technical solution of the present invention will be further described in detail. Brief Description of the Drawings

[0057] Figure 1 is a flowchart of the method for integrating and intelligent collaboration of vehicle networking enterprise application systems based on AI large models of the present invention;

[0058] Figure 2 is a network architecture diagram of the method for integrating and intelligent collaboration of vehicle networking enterprise application systems based on AI large models of the present invention. Detailed Embodiments

[0059] The following further illustrates the technical solution of the present invention through the accompanying drawings and embodiments.

[0060] As Figure 1 shown, the method for integrating and intelligent collaboration of vehicle networking enterprise application systems based on AI large models of the present invention includes the following steps:

[0061] Step S1: The data acquisition layer obtains real-time data from in-vehicle sensors, in-vehicle devices, and external networks;

[0062] Step S2: Clean and preprocess the collected real-time data;

[0063] Step S3: After data cleaning and preprocessing, the system fuses multi-dimensional data from different modules to achieve intelligent decision-making;

[0064] Step S4: The results of all analyses and decisions are fed back to the vehicle owner or platform administrator through the user interface;

[0065] Step S5: Achieve data collaboration and integration among subsystems based on the AI large model.

[0066] Embodiment

[0067] The vehicle networking enterprise application system integration and intelligent collaboration method based on the AI large model of the present invention realizes seamless connection and data fusion between different in-vehicle systems (such as driver behavior monitoring, vehicle health monitoring, navigation and traffic information, etc.) through AI algorithms, thereby improving the efficiency, response speed, and accuracy of the overall system. The specific process is as follows:

[0068] Step S1: The data acquisition layer obtains real-time data from in-vehicle sensors, in-vehicle devices, and external networks.

[0069] In the implementation of the vehicle networking platform, the data acquisition layer is responsible for obtaining real-time data from in-vehicle sensors, in-vehicle devices, and external networks. These data include but are not limited to:

[0070] (1) Vehicle data: such as location (GPS), speed, engine status, fuel consumption, etc.

[0071] (2) Driver data: such as driver behavior (fatigue driving, driving mode), physiological status (detected through the DMS system), etc.

[0072] (3) Environmental data: such as road conditions, traffic flow, weather conditions, etc.

[0073] All the collected data is transmitted to the cloud platform or remote supervision center through wireless communication technologies (such as LTE, 5G, Wi-Fi, etc.) to ensure efficient data transmission.

[0074] Step S2: Clean and preprocess the collected real-time data.

[0075] The received raw data may contain noise, incomplete data, or redundant data. Therefore, data cleaning and preprocessing are required. The specific process is as follows:

[0076] Step S21, Denoising: Remove irrelevant data or incorrect data through signal filtering algorithms.

[0077] Step S22, Filling Missing Values: Estimate and fill in the missing data to ensure data integrity.

[0078] Step S23, Standardization Processing: Unify the data formats of different sensors to ensure compatibility between different data sources.

[0079] By performing data cleaning and preprocessing on real-time data, the data quality is guaranteed, providing a reliable basis for subsequent data analysis and fusion.

[0080] Step S3, After data cleaning and preprocessing, the system fuses multi-dimensional data from different modules to achieve intelligent decision-making.

[0081] After data cleaning and preprocessing, the data enters the data fusion and intelligent decision-making stage. This is the core link where the AI large model plays its role. Through AI algorithms (such as deep neural networks, decision trees, clustering algorithms, etc.), the system fuses multi-dimensional data from different modules to form a global and real-time vehicle state model. The specific process is as follows:

[0082] Step S31, Multi-source Data Fusion.

[0083] (1) For driver behavior data: Analyze driver behaviors such as fatigue driving and distracted driving through the DMS system.

[0084] (2) For vehicle health monitoring data: The real-time data provided by vehicle sensors to monitor information such as the engine state, battery power, and fuel consumption of the vehicle.

[0085] (3) For environment and road condition data: Analyze the current road conditions, weather conditions, etc. based on data such as GPS and traffic flow monitoring.

[0086] Step S32, AI Large Model Analysis.

[0087] The system uses the AI large model for in-depth analysis to explore the associations between multi-dimensional data, including but not limited to:

[0088] (1) Analyze the relationship between driver fatigue driving and road traffic flow to determine whether the current driver needs to rest.

[0089] (2) In vehicle fault detection, the AI large model combines vehicle health data and environmental data to predict possible faults and automatically adjust driving strategies or alert the driver.

[0090] Step S33, Intelligent Decision-making and Response.

[0091] (1) Dynamic adjustment strategy: If the AI model detects that the driver is fatigued, the system can automatically issue a reminder and even intervene through the autonomous driving system to adjust the vehicle driving mode.

[0092] (2) Real-time response: When encountering sudden traffic conditions, the system can adjust the driving route in real time or notify the driver to drive safely.

[0093] Step S4: The results of all analyses and decisions are fed back to the vehicle owner or platform administrator through the user interface.

[0094] The results of all analyses and decisions will be fed back to the vehicle owner or platform administrator through the user interface. The vehicle owner can view real-time data, receive warning messages, suggestions, etc. through a mobile application (such as a smartphone App) or a Web platform.

[0095] On the vehicle owner side, the vehicle owner can view real-time vehicle conditions, driving behavior analysis, fault warnings, route planning, etc., enhancing the driving experience and safety.

[0096] On the management side, enterprise managers can conduct real-time monitoring and scheduling of the vehicle fleet through the back-end management system for higher-level vehicle management and analysis.

[0097] Step S5: Achieve data collaboration and integration among various subsystems based on the AI large model.

[0098] In the technical solution proposed by the present invention, various subsystems (such as DMS, vehicle monitoring, environmental monitoring, etc.) do not work independently, but conduct collaborative analysis through the AI large model. The specific implementation process is as follows:

[0099] Step S51: Cross-system data sharing: The driver behavior analysis module can obtain the data of the vehicle status module to determine whether the driver needs to rest or switch the driving mode.

[0100] Step S52: Dynamic adjustment and feedback: Based on the analysis results of multiple systems, the AI large model can decide when to issue a warning to the driver through the driver interface, when to adjust the autonomous driving system, when to dispatch remote maintenance services, etc.

[0101] Therefore, through data analysis and decision support by the AI large model (such as deep learning, machine learning, etc.) in the present invention, the system can make intelligent decisions based on multi-dimensional data sources such as real-time vehicle status, driver behavior, and environmental information, and adjust the working strategies of the vehicle or platform in real time to improve safety, comfort, and vehicle operation efficiency.

[0102] Such as Figure 2As shown in the figure, the network architecture of the vehicle networking enterprise application system integration and intelligent collaboration method based on the AI large model of the present invention includes: a data collection layer, a data transmission layer, a data processing and decision-making layer, and a feedback and interaction layer.

[0103] ① Data collection layer: First, sensor devices on the vehicle (such as cameras, radars, GPS, etc.) collect various types of data about the vehicle, driver, and environment in real time. Then, the data is uploaded to the platform through wireless communication technologies (such as LTE, 5G).

[0104] ② Data transmission layer: The collected data is transmitted in real time to the data processing and decision-making layer through an efficient and reliable communication network (such as LTE, 5G).

[0105] ③ Data processing and decision-making layer: First, the AI large model is used to perform in-depth analysis and intelligent decision-making on the received data, and data fusion and collaborative processing are carried out. Then, the decision-making results are output and provided to the downstream user interaction layer through the data feedback interface.

[0106] ④ Feedback and interaction layer: Through the smartphone App or the Web platform, vehicle owners and managers can view real-time vehicle status, driving behavior, environmental information, decision-making feedback, etc.

[0107] Therefore, by adopting the above-mentioned vehicle networking enterprise application system integration and intelligent collaboration method based on the AI large model, the intelligence and automation levels of the vehicle networking remote supervision platform are greatly improved, the global optimization of vehicle management is realized, and safer and more efficient services are provided for vehicle owners, managers, and related parties; the present invention uses the AI large model to connect and integrate various application systems within the vehicle networking enterprise, and automatically and intelligently optimizes the collaboration and data flow between systems; the AI large model can adaptively adjust the work process according to real-time environmental changes, efficiently eliminate information islands, break system barriers, and achieve seamless collaboration and data sharing between systems, thereby greatly enhancing the flexibility, response speed, and overall efficiency of the vehicle networking enterprise system; through the integration of the AI large model, the system can automatically optimize collaboration, improve efficiency, and realize the intelligent integration and collaborative work of the vehicle networking system; this solution enables the vehicle networking enterprise to achieve more efficient, flexible, and intelligent system integration, reduce the need for manual intervention, improve data utilization rate, and thus enhance the efficiency and effectiveness of the overall business operation.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions of the present invention or make equivalent replacements, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. An integrated and intelligent collaboration method for vehicle networking enterprise application systems based on AI large models, characterized in that, The following steps are involved: Step S1, the data acquisition layer obtains real-time data from vehicle sensors, vehicle devices and external networks; Step S2: cleaning and preprocessing the collected real-time data; Step S3: After data cleaning and preprocessing, the system integrates multidimensional data from different modules to achieve intelligent decision-making; Step S4: All analysis and decision results are fed back to the car owner or platform administrator through the user interface; Step S5: Realize data collaboration and integration among subsystems based on the AI big model.

2. The method for integrating and intelligently collaborating vehicle networking enterprise application systems based on the AI large model according to claim 1, wherein In step S1, in the implementation of the Internet of Vehicles platform, the data acquisition layer is responsible for obtaining real-time data from vehicle sensors, vehicle devices and external networks. These data include but are not limited to: (1) Vehicle data: such as GPS location, speed, engine status, and fuel consumption; (2) Driver data: such as driver behavior and physiological status; (3) Environmental data: such as road conditions, traffic flow, and weather conditions; All collected data are transmitted to the cloud platform or remote monitoring center via wireless communication technology to ensure efficient data transmission.

3. The method for integrating and intelligent collaboration of vehicle networking enterprise application systems based on the AI large model according to claim 1, wherein In step S2, the collected real-time data is cleaned and preprocessed. The specific process is as follows: Step S21, denoising: removing irrelevant data or erroneous data through a signal filtering algorithm; Step S22, filling missing values: inferring and filling missing data to ensure data integrity; Step S23: Standardization processing: unifying the data formats of different sensors to ensure the compatibility of different data sources.

4. The method for integrating and intelligent collaboration of vehicle networking enterprise application systems based on the AI large model according to claim 1, characterized in that, In step S3, after data cleaning and preprocessing, the system integrates multidimensional data from different modules to achieve intelligent decision-making. The specific process is as follows: Step S31, multi-source data fusion; Step S32, AI large model analysis; Step S33: Intelligent decision and response.

5. The method for integrating and intelligent collaboration of vehicle networking enterprise application systems based on the AI large model according to claim 4, wherein, In step S31, multi-source data fusion specifically includes: (1) Driver behavior data: Analyze the driver's fatigue driving and distracted driving behavior through the DMS system; (2) Vehicle health monitoring data: real-time data provided by vehicle sensors to monitor the vehicle’s engine status, battery charge, and fuel consumption information; (3) For environmental and road condition data: Analyze current road and weather conditions based on positioning and traffic flow monitoring data.

6. The method for integrating and intelligently collaborating vehicle networking enterprise application systems based on an AI large model according to claim 4, wherein, In step S32, the system uses the AI big model to perform in-depth analysis and mine the associations between multi-dimensional data, including but not limited to: (1) Analyze the relationship between driver fatigue and road traffic flow to determine whether the current driver needs a rest; (2) In vehicle fault detection, the AI big model combines vehicle health data and environmental data to predict the occurrence of faults and automatically adjust driving strategies or remind the driver.

7. The method for integrating and intelligent collaboration of vehicle networking enterprise application systems based on the AI large model according to claim 4, wherein In step S33, intelligent decision making and response specifically include: (1) Dynamic adjustment strategy: When the AI model detects that the driver is driving fatigued, the system automatically reminds the driver and even intervenes through the autonomous driving system to adjust the vehicle's driving mode; (2) Real-time response: When encountering sudden traffic conditions, the system adjusts the driving route in real time and notifies the driver to drive safely.

8. The method for integrating and intelligently collaborating vehicle networking enterprise application systems based on an AI large model according to claim 1, wherein, In step S4, the results of all analyses and decisions will be fed back to the vehicle owner or platform administrator through the user interface. The vehicle owner can view real-time data, receive warning messages and suggestions through the mobile application and the Web platform. On the vehicle owner side, the vehicle owner can view real-time vehicle conditions, driving behavior analysis, fault warnings, and route planning information, enhancing the driving experience and safety. On the management side, enterprise managers can conduct real-time monitoring and scheduling of the fleet through the back-end management system for higher-level vehicle management and analysis.

9. The method for integrating and intelligent collaboration of an Internet of Vehicles enterprise application system based on an AI large model according to claim 1, wherein In step S5, data collaboration and integration among various subsystems are realized based on the AI large model. The specific implementation process is as follows: Step S51, Cross-system data sharing: The driver behavior analysis module obtains data from the vehicle status module to determine whether the driver needs to rest or switch the driving mode. Step S52, Dynamic adjustment and feedback: Based on the analysis results of multiple systems, the AI large model dynamically adjusts the warning time, the autonomous driving system, and the remote maintenance service.

10. The method for integrating and intelligently collaborating vehicle networking enterprise application systems based on an AI large model according to claim 1, wherein, The network architecture includes: a data collection layer, a data transmission layer, a data processing and decision-making layer, and a feedback and interaction layer. ① Data collection layer: First, sensor devices on the vehicle collect various types of data about the vehicle, the driver, and the environment in real time; then, the data is uploaded to the platform through wireless communication technology. ② Data transmission layer: Transmit the collected data to the data processing and decision-making layer in real time through the communication network. ③ Data processing and decision-making layer: First, use the AI large model to conduct in-depth analysis and intelligent decision-making on the received data, perform data fusion and collaborative processing; then, output the decision results and provide them to the downstream user interaction layer through the data feedback interface. ④ User interaction layer: Vehicle owners and managers can view real-time vehicle status, driving behavior, environmental information, and decision feedback information through the mobile application and the Web platform.

Images