Fee deduction method, system and device of intelligent transportation system and medium

Abstract

The invention provides a fee deduction method, system and device of an intelligent traffic system and a medium, and belongs to the technical field of intelligent traffic. The method comprises the following steps: acquiring a vehicle image, vehicle driving information and traffic flow information at a preset position of a traffic system; the vehicle image comprises a license plate image of a vehicle; identifying and analyzing the vehicle image by adopting a deep learning algorithm to obtain license plate number information and vehicle type information; predicting a driving path and passing time of the vehicle based on the historical driving data of the vehicle; dynamically calculating a fee deduction amount according to the driving path, the passing time and the real-time traffic flow information of the vehicle; and sending the deduction amount to the mobile terminal of the user, and providing payment service. According to the invention, the intelligent identification system is constructed, the vehicle information is obtained in real time, dynamic fee deduction is carried out in combination with various factors, and accurate and reasonable traffic and parking management is realized.

Description

Technical Field

[0001] This invention belongs to the field of intelligent transportation technology, and more specifically relates to a toll collection method, system, equipment and medium for an intelligent transportation system. Background Art

[0002] Against the backdrop of rapid urbanization, traffic congestion and parking shortages have become significant bottlenecks restricting urban development. Traditional traffic toll collection systems mostly rely on manual operation or traditional sensor equipment to record and calculate fees. These methods are not only inefficient but also costly. Furthermore, due to technological limitations, these systems often cannot provide high-precision toll collection services and have slow response times, making it difficult to meet the needs of modern urban traffic management.

[0003] Traditional parking and road toll systems often have fixed pricing standards, lacking sufficient flexibility and real-time updates. This rigid pricing model cannot be dynamically adjusted according to changes in traffic flow, time of day, and traffic pressure in specific areas, resulting in wasted resources and low traffic efficiency.

[0004] More importantly, existing traffic toll collection systems generally lack the ability to intelligently analyze vehicle behavior and routes. This means that traffic management departments cannot accurately grasp vehicle trajectories, parking habits, and real-time locations, making it difficult to effectively predict and manage traffic flow. This lack of information not only limits the improvement of traffic management but also affects the smooth and efficient operation of urban traffic. Summary of the Invention

[0005] To address the above problems, the present invention aims to provide a toll collection method, system, device, and medium for an intelligent transportation system. By constructing an intelligent identification system, vehicle information is acquired in real time, and dynamic toll collection is performed in combination with multiple factors, thereby achieving accurate and reasonable traffic and parking management.

[0006] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, embodiments of this application provide a toll collection method for an intelligent transportation system, including: Vehicle images, vehicle driving information, and traffic flow information are collected at preset locations in the traffic system; the vehicle images include vehicle license plate images. Deep learning algorithms are used to identify and analyze vehicle images to obtain license plate number and vehicle model information; Based on the vehicle's historical driving data, predict the vehicle's driving route and travel time; The toll amount is dynamically calculated based on the vehicle's travel route, travel time, and real-time traffic flow information. The deducted amount is sent to the user's mobile device, and payment services are provided.

[0007] In an optional implementation, the acquisition of vehicle images, vehicle location, and time information at a preset location within the traffic system; the vehicle images include license plate images, comprising: Vehicle images are captured by cameras installed at major traffic arteries, parking lot entrances and exits, and toll stations, and the camera parameters are automatically adjusted according to real-time lighting conditions. Traffic flow information for the current road segment is collected by sensor modules installed at major traffic arteries, parking lot entrances and exits, and toll stations. The entry time of vehicles is recorded by RFID card readers installed at major traffic arteries, parking lot entrances and exits, and toll stations; The collected vehicle images, current road traffic flow information, and vehicle entry times are sent to the central processor via the network.

[0008] In an optional implementation, the step of using a deep learning algorithm to recognize and analyze vehicle images to obtain license plate information and vehicle model information includes: Using a convolutional neural network (CNN) to detect vehicle positions and determine vehicle regions in vehicle images; The vehicle area is processed using a pre-trained OCR model to identify the license plate number; Based on the vehicle region, deep learning algorithms are used to analyze vehicle features, and vehicle model information is determined based on the analysis results; Record the vehicle's entry time and corresponding entrance location; The license plate number, vehicle model information, and entrance location are encrypted and stored in the database.

[0009] In an optional implementation, predicting the vehicle's travel route and travel time based on the vehicle's historical driving data includes: Based on the license plate number, extract the vehicle's historical travel route information and parking location information from the traffic system as historical driving data; Clustering algorithms are used to group historical travel route information, identify vehicle driving patterns, and construct vehicle driving models. Key features are extracted from the vehicle's historical route information, including driving speed, dwell time, and frequently traversed road segments. Based on these key features, a classification algorithm is used to analyze the vehicle's driving patterns, and a deep learning algorithm is used to predict the vehicle's future driving path. Based on the future travel paths of vehicles, historical and real-time traffic flow data of relevant road segments are extracted from the traffic system; an LSTM neural network model is constructed, inputting historical and real-time traffic flow data to predict traffic flow information of relevant road segments in future time periods and generate prediction results; Predict the vehicle's travel time based on its future travel route and traffic flow in the future.

[0010] In an optional implementation, the step of dynamically calculating the toll amount based on the vehicle's travel route, travel time, and real-time traffic flow information includes: Real-time acquisition of vehicle entry and exit times in specific road sections or parking areas, and calculation of vehicle dwell time; A dynamic charging calculation model for vehicles is constructed, the dynamic charging calculation model including: Y = B × L × C × D × T; Where Y is the predicted toll amount for the vehicle, B is the basic rate, L is the road segment coefficient, C is the vehicle type coefficient, D is the time period coefficient, and T is the vehicle's dwell time. The road segment coefficient of the vehicle is determined based on the traffic flow information for the future time period; the vehicle type coefficient is determined based on the vehicle type information; the peak traffic duration included in the travel time is identified based on the travel time to determine the time period coefficient of the vehicle; and the toll amount is calculated using the vehicle's dynamic toll calculation model.

[0011] In an optional implementation, the vehicle's dynamic charging calculation model is optimized using a loss function; The loss function includes:

[0012] in, This represents the actual amount deducted from vehicle A. The predicted deduction amount is calculated using a dynamic deduction calculation model, where n is the number of samples.

[0013] In an optional implementation, sending the deducted amount to the user's mobile terminal and providing payment services includes: The deduction information is sent to the user's mobile terminal; the deduction information includes the deduction amount, as well as the deduction amount, deduction section information and deduction time generated based on the vehicle's travel route, travel time and real-time traffic flow information; The system connects the user's mobile device to the payment platform, automatically uploads the deduction amount, generates a deduction interface, and completes the deduction after user confirmation.

[0014] Secondly, embodiments of this application also provide a toll collection system for an intelligent transportation system, comprising: The data acquisition module is used to acquire vehicle images, vehicle driving information, and traffic flow information at preset locations in the traffic system; the vehicle images include vehicle license plate images. The data processing module is used to identify and analyze vehicle images using deep learning algorithms to obtain license plate number information and vehicle model information; The prediction module is used to predict the vehicle's travel route and travel time based on the vehicle's historical driving data; The dynamic toll deduction module is used to dynamically calculate the toll amount based on the vehicle's travel route, travel time, and real-time traffic flow information. The payment module is used to send the deducted amount to the user's mobile terminal and provide payment services.

[0015] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the toll collection method of the intelligent transportation system as described in any of the above.

[0016] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the toll deduction steps of the intelligent transportation system as described in any of the above.

[0017] As can be seen from the above technical solutions, the present invention has the following advantages: This application utilizes deep learning algorithms for efficient and accurate recognition and analysis of vehicle images, enabling rapid extraction of license plate numbers and vehicle model information. Simultaneously, by collecting multi-dimensional data such as vehicle location, time, and traffic flow in real time, a solid data foundation is laid for subsequent toll calculations, ensuring the accuracy and completeness of the data analysis.

[0018] This application, based on historical vehicle driving data, utilizes advanced clustering and deep learning algorithms to accurately predict vehicle travel routes and travel times. Combined with real-time traffic flow information, this application can dynamically calculate the toll amount, enabling real-time and flexible adjustment of the toll standard, reflecting both fairness and ensuring the reasonableness of the charges.

[0019] This application constructs a dynamic vehicle toll calculation model and introduces a loss function for continuous optimization, significantly improving the accuracy and precision of toll calculation. The model comprehensively considers multiple factors such as the basic toll rate, road segment coefficient, vehicle type coefficient, time period coefficient, and dwell time, ensuring the comprehensiveness and rationality of the toll standard and further enhancing user satisfaction.

[0020] This application greatly facilitates users' understanding of billing information by sending billing information to their mobile terminals, including detailed information such as the amount, reason for the billing, billing route, and time. Simultaneously, it seamlessly integrates the user's mobile terminal with the payment platform, enabling automatic uploading of billing amounts and generation of the payment interface, simplifying the payment process and enhancing the convenience and intelligence of the user experience.

[0021] This application not only enhances the intelligence level of traffic toll collection but also provides traffic management departments with abundant traffic data and insights. By collecting and analyzing traffic data in real time, management departments can promptly identify and resolve issues such as traffic congestion, optimize traffic planning and management strategies, improve traffic operation efficiency and service levels, and promote the intelligent development of the transportation sector. Attached Figure Description

[0022] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A flowchart illustrating the toll collection method for the intelligent transportation system provided in this application.

[0024] Figure 2 A schematic diagram of the toll collection system of the intelligent transportation system provided in this application.

[0025] Figure 3 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0026] The various embodiments of this disclosure will be described more fully in the detailed steps of the toll collection method for intelligent transportation systems described below. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0027] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0029] See also Figure 1 The diagram shows a flowchart of a toll collection method for an intelligent transportation system in a specific embodiment. The method includes: S1: Collect vehicle images, vehicle driving information, and traffic flow information at preset locations in the traffic system; the vehicle images include vehicle license plate images.

[0030] It should be noted that in the transportation system, high-definition cameras, sensors, RFID card readers and other equipment are deployed at key traffic routes, parking lot entrances / exits, toll stations and other locations.

[0031] In this step, vehicle images are captured by cameras installed at major traffic arteries, parking lot entrances and exits, and toll booths, with camera parameters automatically adjusted based on real-time lighting conditions. High-definition cameras are used to capture vehicle images. License plates are photographed by the cameras, and the vehicle images are transmitted to a central processing system. Simultaneously, image quality is automatically checked to ensure clear visibility even in low light or inclement weather. For blurry images, image quality is improved by automatically adjusting camera parameters or adding supplementary lighting.

[0032] Traffic flow information for the current road segment is collected by sensor modules installed at major traffic arteries, parking lot entrances and exits, and toll stations.

[0033] RFID readers installed at major traffic arteries, parking lot entrances and exits, and toll booths record the entry time of vehicles.

[0034] The collected vehicle images, traffic flow information for the current road segment, and vehicle entry time are sent to the central processor via the network for further processing.

[0035] S2: Use deep learning algorithms to recognize and analyze vehicle images to obtain license plate number and vehicle model information.

[0036] The purpose of this step is to identify and analyze the collected image data, transforming the raw data into useful traffic information.

[0037] S3: Based on the vehicle's historical driving data, predict the vehicle's driving route and travel time.

[0038] The purpose of this step is to learn from the vehicle's historical driving data and predict its possible driving routes and travel times in order to support dynamic toll collection strategies.

[0039] S4: Dynamically calculate the toll amount based on the vehicle's travel route, travel time, and real-time traffic flow information.

[0040] The purpose of this step is to dynamically calculate the toll amount based on the vehicle's route, vehicle type, dwell time, and real-time traffic conditions.

[0041] S5: Sends the deducted amount to the user's mobile terminal and provides payment services.

[0042] For example, the deduction information will be sent to the user's mobile app, SMS, or email. The user can view detailed deduction records on the app. The deduction information includes the amount deducted, the reason for the deduction, the route deducted, and the time.

[0043] The system connects users' mobile phones to payment platforms (such as bank cards and e-wallets), offering multiple payment methods. Users can choose their linked payment method to complete the deduction, which is then automatic. Additionally, if users have any questions about the deduction, they can submit feedback through the app, and the system will automatically review the deduction records and provide a detailed explanation.

[0044] In this embodiment, by collecting and analyzing vehicle information, combining historical driving data and real-time traffic flow, the deduction amount is dynamically calculated, and the user is conveniently notified to pay, which improves the accuracy and efficiency of charging and optimizes the user experience.

[0045] In one embodiment of the present invention, based on step S2, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0046] This embodiment discloses a vehicle image recognition and analysis method, which specifically includes the following steps: S201: Use a convolutional neural network (CNN) to detect the vehicle's location in a vehicle image and determine the vehicle region.

[0047] As an example, a deep learning algorithm (convolutional neural network CNN) is used to first detect the vehicle's location in the vehicle image, ensuring that subsequent processing is only performed on the vehicle area.

[0048] S202: Use a pre-trained OCR model to perform OCR processing on the vehicle area and identify the license plate number.

[0049] As an example, OCR processing is performed on the detected vehicle area to identify the license plate number. This step utilizes a trained OCR model to accurately recognize the license plate text and store the license plate information in a database.

[0050] S203: Based on the vehicle region, use deep learning algorithms to analyze vehicle features and determine vehicle model information based on the analysis results.

[0051] As an example, vehicle characteristics (size, color, shape) are analyzed, and deep learning algorithms are used to determine the vehicle model. This model information can then be used for subsequent differentiated pricing strategies.

[0052] S204: Record the vehicle's entry time and corresponding entrance location.

[0053] As an example, information such as the entry time and entrance location of each vehicle is recorded to calculate its driving route and dwell time.

[0054] S205: The license plate number, vehicle model information, and entrance location are encrypted and stored in the database.

[0055] As an example, the identified sensitive data such as license plate number, vehicle model, and location are encrypted and stored in a database to protect user privacy.

[0056] In one embodiment of the present invention, based on step S3, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0057] This embodiment discloses a method for predicting vehicle travel routes and travel times, specifically including the following steps: S301: Extract the vehicle's historical travel route information and parking location information from the traffic system based on the license plate number, as historical driving data.

[0058] S302: Use clustering algorithms to group historical travel route information, identify vehicle driving patterns, and construct vehicle driving models.

[0059] S303: Extract key features from the vehicle's historical route information, including driving speed, dwell time, and frequently traversed road segments; based on the key features, use a classification algorithm to analyze the vehicle's driving patterns, and use a deep learning algorithm to predict the vehicle's future driving path.

[0060] This step uses machine learning algorithms to analyze vehicle driving patterns and predict their future routes. For example, it can predict peak-hour routes using traffic flow data or identify abnormal driving behaviors (such as repeatedly entering and exiting specific road sections).

[0061] As an example, key features such as speed, dwell time, and frequently traversed road sections are extracted from vehicle driving data. Then, classification algorithms (such as decision trees and random forests) or regression algorithms (such as linear regression and support vector machines) are used to analyze driving patterns. Finally, reinforcement learning or deep learning algorithms (such as LSTM and GRU) are used to predict the vehicle's future driving path.

[0062] To predict vehicle travel paths, a Markov chain is used for modeling. Assuming vehicles have different transition probabilities between nodes (such as intersections and toll booths), the transition probability matrix for each node is:

[0063] Among them, P ij This represents the probability that a vehicle will move from node i to node j. Using historical driving data, the transition probability matrix P can be trained to predict the driving paths of vehicles between different road segments, thereby optimizing traffic flow and resource allocation.

[0064] S304: Based on the future travel paths of vehicles, extract historical and real-time traffic flow data of relevant road segments from the traffic system; construct an LSTM neural network model, input historical and real-time traffic flow data, predict traffic flow information of relevant road segments in future time periods, and generate prediction results.

[0065] In this step, based on historical traffic flow data and real-time traffic information, the system uses machine learning models (such as time series analysis or LSTM networks) to predict traffic flow in the next few hours, providing a basis for toll collection decisions.

[0066] First, historical traffic data is analyzed using time series models such as ARIMA and Prophet. Then, an LSTM neural network model is constructed, taking historical and real-time traffic data as input, to predict future traffic. By fusing historical and real-time data, the accuracy of the prediction can be improved.

[0067] S305: Predict the travel time of vehicles based on their future travel routes and traffic flow in the future.

[0068] In this step, vehicle travel time can be predicted using various algorithmic models. These models include: time series analysis, Kalman filtering, neural networks, support vector machines (SVM), hybrid model prediction algorithms, and prediction models based on graph convolutional networks (GCN).

[0069] In one embodiment of the present invention, based on step S4, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0070] First, the entry and exit times of vehicles in specific road segments or parking areas are acquired in real time, and the vehicle's dwell time is calculated. Specifically, the timestamps of vehicles entering and leaving specific road segments or parking areas are recorded. The difference between the two timestamps is calculated to obtain the vehicle's dwell time. The dwell time data is stored in a database for subsequent analysis.

[0071] Then, a dynamic charging calculation model for the vehicle is constructed, the dynamic charging calculation model including: Y = B × L × C × D × T; Where Y is the predicted toll amount for the vehicle, B is the basic rate, L is the road segment coefficient, C is the vehicle type coefficient, D is the time period coefficient, and T is the vehicle's dwell time.

[0072] Finally, the road segment coefficient of the vehicle is determined based on the traffic flow information of the future time period; the vehicle type coefficient is determined based on the vehicle type information; the peak traffic duration included in the travel time is identified based on the travel time to determine the time period coefficient of the vehicle; and the toll amount is calculated using the vehicle's dynamic toll calculation model.

[0073] The dynamic billing calculation model is continuously optimized using machine learning methods. The loss function used is the mean squared error (MSE), which is defined as:

[0074] in, This represents the actual amount deducted from vehicle A. The predicted deduction amount is calculated using a dynamic deduction calculation model, where n is the number of samples.

[0075] By minimizing the loss function, the predicted charge amount is made closer to the actual charge amount, thereby optimizing the dynamic pricing strategy.

[0076] In a specific implementation, this method can also self-optimize the charging model through continuous updates of user feedback and charging data, ensuring that the system adapts to changes in different traffic environments. The main implementation steps include: 1. Feedback Data Collection: Record user feedback on billing information, including payment success rate, billing accuracy, user satisfaction, etc.

[0077] 2. Model Optimization: Analyze the feedback data using machine learning algorithms and improve the billing algorithm by optimizing the parameters of the dynamic billing calculation model (such as pricing coefficients).

[0078] 3. Traffic flow adjustment feedback: Information such as traffic flow and congestion is used as an important basis for model optimization, and pricing strategies are dynamically adjusted to make them more reasonable and adaptable.

[0079] 4. Self-learning: By gradually accumulating historical deduction data, the system automatically learns and adjusts parameters to adapt the deduction strategy to different roads and time periods, thereby improving the flexibility and accuracy of the deduction system.

[0080] like Figure 2 As shown, the following is an embodiment of the toll collection system of the intelligent transportation system provided in this disclosure. This system and the toll collection methods of the intelligent transportation system in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the toll collection system of the intelligent transportation system, please refer to the embodiments of the toll collection methods of the intelligent transportation system described above.

[0081] A toll collection system for an intelligent transportation system includes: a data acquisition module 1, a data processing module 2, a prediction module 3, a dynamic toll collection module 4, and a payment module 5.

[0082] Data acquisition module 1 is used to acquire vehicle images, vehicle driving information and traffic flow information at preset locations in the traffic system; the vehicle images include vehicle license plate images.

[0083] Data processing module 2 is used to identify and analyze vehicle images using deep learning algorithms to obtain license plate number information and vehicle model information.

[0084] Prediction module 3 is used to predict the vehicle's travel route and travel time based on the vehicle's historical driving data.

[0085] The dynamic deduction module 4 is used to dynamically calculate the deduction amount based on the vehicle's travel route, travel time, and real-time traffic flow information.

[0086] Payment module 5 is used to send the deducted amount to the user's mobile terminal and provide payment services.

[0087] The intelligent transportation system toll collection system provided in this embodiment integrates functional modules such as data collection, deep learning processing, driving prediction, dynamic toll collection, and mobile payment to achieve intelligent and dynamic management of vehicle tolls. This not only improves toll collection efficiency and accuracy but also provides users with a more convenient and transparent payment experience, effectively promoting the intelligent upgrade of traffic management.

[0088] Figure 3 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0089] The toll collection method for intelligent transportation systems provided in this application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0090] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0091] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0092] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0093] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0094] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0095] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0096] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0097] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0098] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0099] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0100] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0101] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0102] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0103] The aforementioned electronic device realizes the charging method of the intelligent transportation system of this application by constructing an intelligent identification system, acquiring vehicle information in real time, and dynamically charging by combining multiple factors, thereby achieving accurate and reasonable traffic and parking management.

[0104] The storage medium provided in this application stores a program product capable of implementing a toll collection method for an intelligent transportation system.

[0105] The toll collection method of the intelligent transportation system includes: collecting vehicle images, vehicle driving information, and traffic flow information at preset locations in the transportation system; the vehicle images include vehicle license plate images; using deep learning algorithms to identify and analyze the vehicle images to obtain license plate number information and vehicle model information; predicting the vehicle's driving path and travel time based on the vehicle's historical driving data; dynamically calculating the toll amount based on the vehicle's driving path, travel time, and real-time traffic flow information; sending the toll amount to the user's mobile terminal and providing payment services.

[0106] In some possible implementations, the toll collection method of the intelligent transportation system disclosed herein can be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0107] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0108] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fee deduction method for an intelligent transportation system, characterized in that: include: Collect vehicle images, vehicle driving information and traffic flow information at preset locations in the traffic system; The vehicle image includes a license plate image of the vehicle; Use deep learning algorithms to identify and analyze vehicle images to obtain license plate number and vehicle model information; Predict the vehicle's travel path and travel time based on the vehicle's historical travel data; Dynamically calculate the deduction amount based on the vehicle's driving path, travel time and real-time traffic flow information; The deducted amount is sent to the user's mobile terminal and payment services are provided.

2. The fee deduction method of the intelligent transportation system according to claim 1, characterized in that: The collecting of vehicle images, vehicle location and time information at a preset location of the traffic system; wherein the vehicle images include vehicle license plate images, includes: The cameras installed at traffic arteries, parking lot entrances and exits, and toll booths collect vehicle images and automatically adjust camera parameters according to real-time lighting conditions; The traffic flow information of the current road section is collected through sensor modules installed at traffic arteries, parking lot entrances and exits, and toll booths; The entry time of vehicles is recorded through RFID readers installed at traffic arteries, parking lot entrances and exits, and toll booths; The collected vehicle images, the traffic flow information of the current road section and the vehicle's entry time are sent to the central processor through the network.

3. The fee deduction method of the intelligent transportation system according to claim 2, characterized in that: The deep learning algorithm is used to identify and analyze the vehicle image to obtain the license plate number information and vehicle model information, including: Use convolutional neural network (CNN) to detect the vehicle position in the vehicle image and determine the vehicle area; Use the pre-trained OCR model to perform OCR processing on the vehicle area and identify the license plate number; Based on the vehicle area, the deep learning algorithm is used to analyze the vehicle characteristics and determine the vehicle model information based on the analysis results; Record the vehicle's entry time and corresponding entrance location; The license plate number, vehicle model information and entrance location are encrypted and stored in the database.

4. The fee deduction method of the intelligent transportation system according to claim 3, characterized in that: The method of predicting the vehicle's travel path and travel time based on the vehicle's historical travel data includes: Extract the vehicle's historical route information and stop location information from the traffic system based on the license plate number as historical driving data; Clustering algorithms are used to group historical route information, identify vehicle driving patterns, and build vehicle driving models; Extract key features from the vehicle's historical route information, including driving speed, dwell time, and frequently traveled sections; based on the key features, use a classification algorithm to analyze the vehicle's driving patterns, and use a deep learning algorithm to predict the vehicle's future driving path; Based on the future driving path of the vehicle, the historical traffic data and real-time traffic data of the relevant road sections are extracted from the traffic system; an LSTM neural network model is constructed, and the historical traffic data and real-time traffic data are input to predict the traffic flow information of the relevant road sections in the future period and generate the prediction results; The vehicle's travel time is predicted based on the vehicle's future travel path and traffic flow in the future period.

5. The fee deduction method of the intelligent transportation system according to claim 4, characterized in that: The dynamically calculating the deduction amount according to the vehicle's travel path, travel time and real-time traffic flow information includes: Obtain the entry and exit time of vehicles in a specific road section or parking area in real time and calculate the vehicle's stay time; Construct a dynamic fee calculation model for the vehicle, the dynamic fee calculation model comprising: Y = B × L × C × D × T; Among them, Y is the predicted deduction amount of the vehicle, B is the basic rate, L is the road section coefficient, C is the vehicle type coefficient, D is the time period coefficient, and T is the vehicle's stay time; The road section coefficient of the vehicle is determined according to the traffic flow information of the future time period; the vehicle model coefficient is determined according to the vehicle model information; the peak traffic time included in the travel time is identified according to the travel time to determine the vehicle's time period coefficient; and the toll amount is calculated using the vehicle's dynamic toll calculation model.

6. The fee deduction method of the intelligent transportation system according to claim 5, characterized in that: The dynamic fee deduction calculation model of the vehicle is optimized through a loss function; The loss function includes: in, is the actual deduction amount for vehicle a, It is the predicted deduction amount calculated by the dynamic deduction calculation model, and n is the number of samples.

7. The fee deduction method of the intelligent transportation system according to claim 6, characterized in that: The deduction amount is sent to the user's mobile terminal and payment services are provided, including: Sending deduction information to the user's mobile terminal; the deduction information includes the deduction amount, as well as the deduction willingness, deduction section information and deduction time generated according to the vehicle's driving path, travel time and real-time traffic flow information; Connect the user's mobile terminal to the payment platform, automatically upload the deduction amount, and generate a deduction operation interface. After the user confirms, the deduction is completed.

8. A fee deduction system for an intelligent transportation system, characterized in that: The system adopts the fee deduction method of the intelligent transportation system as claimed in any one of claims 1 to 7; The system comprises: A data acquisition module, used to collect vehicle images, vehicle driving information and traffic flow information at a preset position in the traffic system; the vehicle image includes a license plate image of the vehicle; The data processing module is used to identify and analyze vehicle images using deep learning algorithms to obtain license plate number information and vehicle model information; A prediction module is used to predict the vehicle's travel path and travel time based on the vehicle's historical travel data; Dynamic fee deduction module, used to dynamically calculate the fee deduction amount based on the vehicle's driving path, travel time and real-time traffic flow information; The payment module is used to send the deducted amount to the user's mobile terminal and provide payment services.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the fee deduction method of the intelligent transportation system as described in any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the fee deduction method of the intelligent transportation system as claimed in any one of claims 1 to 7 are implemented.

Images