Vehicle identification method and device applied to electric vehicle energy complementing scene

Abstract

The embodiment of the invention discloses a vehicle identification method and device applied to an electric vehicle energy complementing scene. A specific embodiment of the method comprises the following steps: performing vehicle identification on a real-time area video for a target area; in response to the condition that the vehicle parking description information and the first vehicle information meet a preset parking condition, information reading is carried out on the target vehicle through information reading equipment in a target vehicle parking area; in response to the matching of the first vehicle information and the second vehicle information and the power supply connection of an energy complementing device in the target vehicle parking area and the target vehicle, performing vehicle energy complementing on the target vehicle; in response to disconnection between the energy complementing equipment in the target vehicle parking area and the target vehicle, generating energy complementing description information, and reading information of the target vehicle again through information reading equipment in the target vehicle parking area; and generating complementary energy push information. According to the embodiment of the invention, the convenience and robustness of automobile energy compensation are improved.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the fields of computer technology, electric vehicle refueling, and vehicle identification, and specifically to vehicle identification methods and apparatus applied to electric vehicle refueling scenarios. Background Technology

[0002] In recent years, the number of electric vehicles (new energy vehicles) has increased significantly. Against this backdrop, improving the convenience of vehicle refueling is of great significance for further optimizing user experience and promoting the healthy and sustainable development of related industries. Currently, mainstream solutions mainly use static QR codes or specific software programs to invoke refueling services. However, these solutions have the following technical problems: When a static QR code is damaged, or when the network environment is poor, the calling method of the static QR code or a specific software program may cause the call to fail, which will prevent electric vehicles from being recharged in time, thus affecting the convenience and robustness of vehicle recharging. Summary of the Invention

[0003] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0004] Some embodiments of this disclosure propose a vehicle identification method and apparatus for electric vehicle refueling scenarios to solve the technical problems mentioned in the background section above.

[0005] In a first aspect, some embodiments of this disclosure provide a vehicle identification method applied to an electric vehicle refueling scenario. The method includes: performing vehicle identification on real-time area video of a target area to generate first vehicle information and vehicle parking description information, wherein the target area is used for parking electric vehicles awaiting refueling, and the target area includes at least two vehicle parking areas; in response to the vehicle parking description information and the first vehicle information satisfying preset parking conditions, reading information about the target vehicle through an information reading device within the target vehicle parking area to obtain second vehicle information, wherein the target vehicle parking area is a vehicle parking area corresponding to the vehicle parking description information. The target vehicle is an electric vehicle parked within the target vehicle parking area, corresponding to the first vehicle information. In response to the matching of the first vehicle information and the second vehicle information, and the connection of the charging equipment within the target vehicle parking area to the target vehicle's power supply, the target vehicle is charged. In response to the disconnection of the charging equipment within the target vehicle parking area from the target vehicle, charging description information is generated, and the target vehicle's information is read again through the information reading device within the target vehicle parking area to obtain third vehicle information. Based on the second vehicle information, the third vehicle information, and the charging description information, charging push information is generated.

[0006] Secondly, some embodiments of this disclosure provide a vehicle identification device applied to an electric vehicle refueling scenario. The device includes: a vehicle identification unit configured to perform vehicle identification on real-time area video of a target area to generate first vehicle information and vehicle parking description information, wherein the target area is used for parking electric vehicles waiting to be refueled, and the target area includes at least two vehicle parking areas; and an activation unit configured to, in response to the vehicle parking description information and the first vehicle information satisfying preset parking conditions, read information about a target vehicle through an information reading device within the target vehicle parking area to obtain second vehicle information, wherein the target vehicle parking area is a vehicle parking area corresponding to the vehicle parking description information, and the target vehicle is a vehicle parking area corresponding to the target vehicle parking description information. The first vehicle information corresponds to an electric vehicle parked within the target vehicle parking area; a vehicle charging unit is configured to, in response to the matching of the first vehicle information and the second vehicle information, and the charging equipment within the target vehicle parking area being connected to the target vehicle for power supply, charge the target vehicle; a first generation and reactivation unit is configured to, in response to the disconnection of the charging equipment within the target vehicle parking area from the target vehicle, generate charging description information, and, through the information reading device within the target vehicle parking area, re-read the information of the target vehicle to obtain third vehicle information; a second generation unit is configured to, based on the second vehicle information, the third vehicle information, and the charging description information, generate charging push information.

[0007] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0008] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0009] The various embodiments disclosed above have the following beneficial effects: the vehicle identification method applied to electric vehicle charging scenarios through some embodiments of this disclosure improves the convenience and robustness of vehicle charging. Specifically, for electric vehicle charging scenarios, the industry currently mainly has two solutions: "charging charging" and "battery swapping charging," with the "charging charging" solution accounting for a higher proportion of electric vehicles. For the "charging charging" solution, the industry mainly adopts a combination of "charging pile + parking space," where parking spaces (vehicle parking areas) are used to park electric vehicles for charging, and charging piles are used to charge the electric vehicles. Based on this solution, static QR codes or specific software programs are mainly used to invoke the charging service. However, when the static QR code is damaged, or when the network environment is poor, the invocation method using static QR codes or specific software programs may fail, resulting in the electric vehicle being unable to recharge in a timely manner, thus affecting the convenience and robustness of vehicle charging. Based on this, some embodiments of the vehicle identification method applied to electric vehicle charging scenarios disclosed herein firstly perform vehicle identification on real-time area video of a target area to generate first vehicle information and vehicle parking description information. The target area is used to park electric vehicles awaiting charging, and includes at least two vehicle parking areas. This automatically identifies the vehicle information and parking status of vehicles entering the target area through video recognition. Secondly, in response to the vehicle parking description information and the first vehicle information meeting preset parking conditions, the information of the target vehicle is read by an information reading device within the target vehicle parking area to obtain second vehicle information. The target vehicle parking area is the parking area corresponding to the vehicle parking description information, and the target vehicle is the electric vehicle parked within the target vehicle parking area, corresponding to the first vehicle information. The information reading device within the target vehicle parking area automatically acquires vehicle information related to the electric vehicle. Next, in response to the matching of the first vehicle information and the second vehicle information, and the charging device within the target vehicle parking area being connected to the target vehicle's power supply, the target vehicle is charged. Compared to using static QR codes or specific software programs, this method effectively optimizes and simplifies the usage logic. Furthermore, in response to the disconnection of the charging equipment within the target vehicle's parking area from the target vehicle, charging description information is generated. Additionally, information about the target vehicle is read again by the information reading device within the parking area to obtain third vehicle information. This automatically generates relevant charging data during the vehicle charging process, and by re-obtaining vehicle information, it avoids anomalies in charging push notification generation caused by malicious tampering of vehicle information during the charging phase. Finally, charging push notification information is generated based on the second vehicle information, the third vehicle information, and the charging description information.This approach effectively optimizes and simplifies the vehicle refueling logic, and improves the convenience and robustness of vehicle refueling. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0011] Figure 1 This is a flowchart of some embodiments of the vehicle identification method applied to electric vehicle refueling scenarios according to the present disclosure; Figure 2 These are schematic diagrams illustrating some embodiments of the vehicle identification method disclosed herein, applied to electric vehicle refueling scenarios. Figure 3 This is a schematic diagram of the network structure of the vehicle positioning network; Figure 4 These are schematic diagrams illustrating the structure of some embodiments of a vehicle identification device applied to electric vehicle refueling scenarios according to the present disclosure; Figure 5 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0012] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0013] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0014] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0015] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0016] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0017] Before performing any operations involving the collection, storage, or use of real-time regional video and other data as disclosed in this disclosure, the relevant organizations or individuals shall fulfill their obligations, including conducting information security impact assessments, informing the information subjects, and obtaining prior authorization and consent from the information subjects.

[0018] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0019] refer to Figure 1 The diagram illustrates a flow 100 of some embodiments of a vehicle identification method applied to an electric vehicle refueling scenario according to the present disclosure. This vehicle identification method for an electric vehicle refueling scenario includes the following steps: Step 101: Perform vehicle identification on the real-time area video of the target area to generate first vehicle information and vehicle parking description information.

[0020] In some embodiments, the execution subject (e.g., a computing device) of the vehicle identification method applied to electric vehicle refueling scenarios can perform vehicle identification on real-time area video of a target area to generate first vehicle information and vehicle parking description information.

[0021] The target area is used for parking electric vehicles awaiting charging. The target area includes at least two vehicle parking zones. These parking zones can be areas specifically for parking electric vehicles for charging. The electric vehicles can be any vehicles requiring charging. Specifically, electric vehicles can include pure electric vehicles and hybrid electric vehicles. Hybrid electric vehicles include series plug-in hybrid electric vehicles and series-parallel plug-in hybrid electric vehicles. Real-time area video is real-time video captured by cameras facing the target area. First vehicle information can represent a vehicle that has entered the target area and is awaiting charging. Specifically, the first vehicle information can include: license plate number, vehicle type, and other vehicle information associated with the license plate number. Vehicle parking description information represents the parking status of the vehicle corresponding to the first vehicle information within the target area. Specifically, the vehicle parking description information can include: vehicle parking location, vehicle parking orientation, vehicle parking area identifier, and vehicle crossing indicator. The vehicle parking location represents the parking position of the vehicle corresponding to the first vehicle information and can be represented using position coordinates (e.g., coordinates of four corner points and one center point). The vehicle parking orientation represents the parking direction of the vehicle corresponding to the first vehicle information, which can be represented by a direction vector. The vehicle parking area identifier represents the parking area where the vehicle corresponding to the first vehicle information is located. For example, the target area can include 5 vehicle parking areas, where the area identifiers corresponding to the 5 vehicle parking areas can be: "P001", "P002", "P003", "P004", and "P005". When the vehicle corresponding to the first vehicle information is located in the first vehicle parking area, the corresponding vehicle parking area identifier can be "P001". The vehicle crossing identifier represents whether the vehicle corresponding to the first vehicle information is completely located within the vehicle parking area corresponding to the vehicle parking area identifier. For example, the vehicle crossing identifier can be represented by "C001", "C002", "C003", and "C004", where "C001" indicates the left side of the vehicle body crossing the line, "C002" indicates the right side of the vehicle body crossing the line, "C003" indicates the front side of the vehicle body crossing the line, and "C004" indicates the rear side of the vehicle body crossing the line.

[0022] In practice, firstly, a target detection model (e.g., YOLO v3 (You Only Look Once Version 3)) can be used to identify vehicles in real-time area video to determine the parking location of the vehicle corresponding to the first vehicle information and extract the vehicle's license plate number. Secondly, the vehicle's parking direction is generated based on the coordinates of the four corner points and one center point of the parking location. Specifically, since the vehicle's projection on the ground is mainly rectangular, a direction vector can be generated based on the coordinates of two corner points (a set) of the corresponding long side of the rectangle, serving as the vehicle's parking orientation. Next, vehicle identity is queried based on the extracted license plate number to obtain the vehicle type included in the first vehicle information and other vehicle information associated with the license plate number. Further, region matching is performed based on the vehicle's parking location and at least two parking areas within the target area to determine the parking area where the vehicle corresponding to the first vehicle information is located, obtaining the vehicle parking area identifier included in the vehicle parking description information. Finally, a rectangular area is constructed based on the coordinates of the four corner points of the vehicle parking location, and the rectangular area is matched with the vehicle parking area corresponding to the vehicle parking area sign to determine whether the vehicle corresponding to the first vehicle information is completely located within the vehicle parking area corresponding to the vehicle parking area sign, thereby obtaining the vehicle crossing the line sign.

[0023] As an example, see Figure 2 The scene diagram shown is as follows, in which, Figure 2 The target area 201 shown includes five vehicle parking areas 202, each of which is equipped with a charging device 203. The charging device 203 can be a power device used to charge electric vehicles. For example, the charging device 203 can be a charging pile. The area identifiers for the five vehicle parking areas 202 from left to right are: “P001”, “P002”, “P003”, “P004”, and “P005”, respectively.

[0024] It should be noted that the aforementioned computing devices can be either hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed on the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0025] In some optional implementations of certain embodiments, the aforementioned executing entity performs vehicle identification on real-time area video of the target area to generate first vehicle information and vehicle parking description information, including: Step S1: Perform fixed-frequency frame extraction on the above real-time regional video to obtain a video image sequence.

[0026] Among them, the video images are image frames obtained by fixed-frequency frame extraction within a real-time regional video.

[0027] In practice, the frame rate of real-time area video can be 30 FPS (Frames Per Second). Assuming the video length of the real-time area video is N seconds, the number of image frames included in the real-time area video is 30×N. Therefore, a frame extraction frequency lower than the real-time area video's frame rate can be used to perform fixed-frequency frame extraction on the real-time area video. For example, the frame extraction frequency can be 10, that is, 3×N image frames are extracted from the real-time area video as a video image sequence.

[0028] Step S2: For each video image in the above video image sequence, perform the following processing steps: Step S21: Determine the image difference between the above video image and the background image to obtain the foreground image.

[0029] The background image is a static image of the target area. The background image and the video image have the same image specifications. The background image can be captured periodically to ensure its validity. For example, when a vehicle enters the target area and begins charging, the camera facing the target area captures a background image. When a vehicle finishes charging and re-enters the target area, the camera facing the target area captures another background image.

[0030] In practice, since the background image and the video image have the same image specifications, the image difference between the video image and the background image can be used as the foreground image.

[0031] Step S22: Perform image enhancement on the foreground image to obtain the enhanced image.

[0032] In practice, at least one of the following operations can be performed on the foreground image, including but not limited to: image quality enhancement, brightness enhancement, and exposure suppression, to achieve the purpose of image enhancement.

[0033] Step S23: Extract the edge contour features of the enhanced image.

[0034] Among them, edge contour features represent the image edge contours of the enhanced image.

[0035] In practice, since moving objects entering the target area have already been quickly separated through foreground and background separation in step S21, and vehicles have significantly different edge contour features compared to other moving objects, the extracted edge contour features are used to characterize moving objects entering the target area to avoid misidentification. Specifically, edge detection algorithms, such as those based on the Canny operator, can be used to extract the edge contour features of the enhanced image.

[0036] Step S3: Generate trajectory features based on the obtained edge contour feature set.

[0037] Among them, trajectory features represent the movement trajectory of a moving object entering the target area. Since the movement trajectory of a vehicle is continuous, it is possible to determine whether a moving object is a vehicle by combining trajectory features.

[0038] In practice, since the video images in a video image sequence are continuous, the edge contour features in the edge contour feature set are also continuous. Specifically, the edge contour features corresponding to the same moving object can be extracted by calculating the Intersection of Union (IOU), and trajectory features can be generated based on the displacement change of the center point of the edge contour features.

[0039] Step S4: Based on the above trajectory characteristics, determine whether any vehicles have entered the target area.

[0040] In practice, a binary classifier can be trained to determine whether a moving object corresponding to a trajectory feature is a vehicle, thereby confirming whether a vehicle has entered the target area. The binary classifier can be trained using supervised training. Specifically, it employs an LSTM (Long Short-Term Memory) as the backbone feature extraction network, and outputs the classification result through two sequentially connected fully connected layers and a Sigmoid activation function. The classification result indicates whether the moving object corresponding to the trajectory feature is a vehicle.

[0041] Specifically, firstly, considering the limited number of parking areas, vehicles entering the target area are often low-frequency scenarios. Directly and continuously performing overall vehicle recognition on the video of the entire area would result in a large data processing volume, significantly increasing hardware costs. Since vehicle movement is continuous, a fixed-frequency frame extraction method is used to reduce the number of image frames processed. Secondly, to effectively recognize vehicles, contour feature extraction and trajectory feature construction are combined to characterize the movement characteristics of moving objects, facilitating subsequent classification. Compared to the conventional method of recognizing the entire image, this significantly reduces data processing volume and improves recognition speed.

[0042] Step S5: In response to the presence of a vehicle entering the target area, vehicle identification is performed using a pre-trained vehicle recognition model and the real-time area video to obtain first vehicle information and vehicle parking description information.

[0043] The vehicle recognition model can be a machine learning model used for vehicle recognition. For example, the vehicle recognition model can use the YOLO v3 (You Only Look Once Version 3) model.

[0044] In practice, firstly, a vehicle recognition model (e.g., YOLO v3 (You Only Look Once Version 3) model) can be used to identify vehicles in real-time area video to determine the parking location of the vehicle corresponding to the first vehicle information and extract the vehicle's license plate number. Secondly, the vehicle's parking direction is generated based on the coordinates of the four corner points and one center point of the parking location. Specifically, since the vehicle's projection on the ground is mainly rectangular, a direction vector can be generated based on the coordinates of the two corner points of the corresponding long side of the rectangle, serving as the vehicle's parking orientation. Next, vehicle identity is queried based on the extracted license plate number to obtain the vehicle type included in the first vehicle information and other vehicle information associated with the license plate number. Further, region matching is performed based on the vehicle's parking location and at least two parking areas within the target area to determine the parking area where the vehicle corresponding to the first vehicle information is located, obtaining the vehicle parking area identifier included in the vehicle parking description information. Finally, a rectangular area is constructed based on the coordinates of the four corner points of the vehicle parking location, and the rectangular area is matched with the vehicle parking area corresponding to the vehicle parking area sign to determine whether the vehicle corresponding to the first vehicle information is completely located within the vehicle parking area corresponding to the vehicle parking area sign, thereby obtaining the vehicle crossing the line sign.

[0045] Optionally, the aforementioned vehicle recognition model includes a vehicle localization network and a vehicle identity information recognition network. The vehicle localization network is used for vehicle identification and localization based on real-time regional video. The vehicle identity information recognition network is used to extract the vehicle's corresponding identity identifier. The decoupled design of the vehicle localization network and the vehicle identity information recognition network facilitates flexible modular adjustments according to actual scenario requirements.

[0046] In some optional implementations of certain embodiments, the execution entity performs vehicle identification using a pre-trained vehicle recognition model and the aforementioned real-time area video to obtain first vehicle information and vehicle parking description information, including: Step S51: Based on the vehicle positioning network and the real-time regional video, perform vehicle positioning to obtain the target image sequence.

[0047] The target image is a partial image containing a vehicle, and each target image is labeled with a vehicle motion status indicator. The vehicle motion status indicator indicates whether the vehicle in the corresponding image frame is in motion. For example, when the vehicle motion status indicator is "1", it indicates that the vehicle in the corresponding image frame is in motion. When the vehicle motion status indicator is "0", it indicates that the vehicle in the corresponding image frame is stationary.

[0048] As an example, see Figure 3 The diagram shows the network structure of a vehicle localization network, where each image frame from a real-time regional video is taken as input. The vehicle localization network includes: convolutional layer A1, convolutional layer A2, normalization layer B1, linear layer C1, linear layer C2, downsampling layer D1, convolutional layer A3, normalization layer B2, linear layer C3, linear layer C4, encoder E1, downsampling layer D2, convolutional layer A4, normalization layer B3, linear layer C5, linear layer C6, encoder E2, fully connected layers, and activation functions. Convolutional layer A2, normalization layer B1, linear layer C1, and linear layer C2 constitute the first convolutional encoder. Convolutional layer A3, normalization layer B2, linear layer C3, and linear layer C4 constitute the second convolutional encoder. Convolutional layer A4, normalization layer B3, linear layer C5, and linear layer C6 constitute the third convolutional encoder. The output of the first convolutional encoder is 1 / 4 of the image size corresponding to the image frame. The output of encoder E1 is 1 / 8 of the image size corresponding to the image frame. The output of encoder E2 is 1 / 16 of the image size corresponding to the image frame. Specifically, convolutional layer A1 has a 4×4 kernel. Convolutional layer A2 is a deconvolutional layer with a 3×3 kernel. Convolutional layer A3 is a deconvolutional layer with a 5×5 kernel. Convolutional layer A4 is a deconvolutional layer with a 7×7 kernel. Normalization layers B1, B2, and B3 all use BatchNorm layers. Encoders E1 and E2 both use SDTA (Split Depth-wise Transpose Attention) encoders. The activation function used is the Sigmoid activation function. Taking a single image frame as an example, by limiting the output feature map size to 1 / 16, it is sufficient to effectively represent depth image features. This avoids the need for upsampling operations in subsequent processing for smaller output sizes such as 1 / 32, and also reduces the need for complex network structure design for unnecessary further image feature extraction. When an image frame contains a car, encoder E2 outputs a local image containing the vehicle and its location within that local image, which serves as the target image. Simultaneously, it outputs the corresponding vehicle motion state identifier through a fully connected layer and activation function.

[0049] Step S52: Perform vehicle identification based on the above vehicle identification information recognition network and the above target image sequence to obtain vehicle identification identifier.

[0050] The vehicle identification identifier represents the unique identity of the vehicle. Since the target image is a partial image containing the vehicle, the vehicle identification information recognition network uses the EasyOCR model to extract the license plate number within the target image as the vehicle identification identifier. The reason for using the EasyOCR model is that it has the advantage of low deployment dependency. Although its inference speed is slightly slower than that of hardware-accelerated inference models, the inference speed is sufficient to meet the usage requirements of this scenario.

[0051] Step S53: Perform a vehicle identity query based on the above vehicle identification identifier to obtain the first vehicle information.

[0052] In practice, since each vehicle has a unique vehicle identification identifier, the vehicle type corresponding to the vehicle identification identifier and other vehicle information associated with the license plate number can be queried through a vehicle identification query interface provided by a third party (such as an insurance service provider) in combination with the vehicle identification identifier, so as to obtain the first vehicle information.

[0053] Step S54: Traverse the above target image sequence in reverse to determine the first target image corresponding to the vehicle motion state identifier indicating that the vehicle is stationary, as a candidate image.

[0054] In practice, it is difficult to effectively determine the parking position of a vehicle when it is in motion. Therefore, by traversing the target image sequence in reverse, the first target image corresponding to the vehicle's motion state identifier indicating that the vehicle is stationary is determined, which is the latest target image corresponding to the vehicle's motion state identifier indicating that the vehicle is stationary.

[0055] Step S55: Map the vehicle position based on the above candidate images to obtain the vehicle position.

[0056] The vehicle position is represented by three-dimensional vehicle position coordinates in the geodetic coordinate system. Specifically, the vehicle position can be represented by the coordinates of multiple corner points of the vehicle boundary.

[0057] In practice, the candidate image is the target image, which is an image containing vehicles. The two-dimensional vehicle position coordinates in the image coordinate system of the target image have been identified by the vehicle localization network. Therefore, provided that the camera acquiring real-time regional video has been calibrated, the two-dimensional vehicle position coordinates in the candidate image can be converted into three-dimensional vehicle position coordinates using the camera's rotation matrix and translation vector, and these coordinates can be used as the vehicle positions.

[0058] Step S56: Obtain the area boundary information of the vehicle parking area that matches the above vehicle location.

[0059] Among them, the area boundary information represents the area boundary coordinates of the vehicle parking area that matches the above vehicle location.

[0060] In practice, since the number and location of parking areas within the target area are fixed, the regional coordinates of each parking area can be pre-defined in a geodetic coordinate system. Therefore, the regional boundary information of parking areas matching the aforementioned vehicle locations can be obtained through coordinate distance matching.

[0061] Step S57: Generate vehicle parking description information based on the vehicle location, the area boundary information, the candidate images, and the vehicle parking status recognition network.

[0062] In practice, since the vehicle localization network has already identified the two-dimensional vehicle position coordinates contained in the candidate image and mapped them to vehicle positions, the vehicle's parking orientation can be determined by combining the vehicle position and area boundary information, thus obtaining the vehicle parking orientation included in the vehicle parking description information. Furthermore, it is possible to determine whether the vehicle has crossed the line and, if so, the specific boundary of the line crossing, thereby obtaining a vehicle line crossing identifier. Simultaneously, the vehicle parking area identifier included in the vehicle parking description information can adopt the area identifier of the vehicle parking area that matches the aforementioned vehicle position.

[0063] Step 102: In response to the vehicle parking description information and the first vehicle information meeting the preset parking conditions, the information of the target vehicle is read by the information reading device in the target vehicle parking area to obtain the second vehicle information.

[0064] In some embodiments, the aforementioned executing entity may, in response to the vehicle parking description information and the first vehicle information meeting preset parking conditions, read the information of the target vehicle through an information reading device within the target vehicle parking area to obtain the second vehicle information.

[0065] The second vehicle information and the first vehicle information include the same content, namely: license plate number, vehicle type, and other vehicle information associated with the license plate number. The difference between the first vehicle information and the second vehicle information is that the first vehicle information relies on image recognition to obtain information. The second vehicle information relies on direct information reading by the information reading device. The above-mentioned target vehicle parking area is the vehicle parking area corresponding to the above-mentioned vehicle parking description information. The above-mentioned target vehicle is an electric vehicle parked in the above-mentioned target vehicle parking area, corresponding to the above-mentioned first vehicle information. The preset parking conditions include: (1) the vehicle parking area identifier is not empty, (2) the vehicle crossing the line identifier is empty, and (3) the vehicle type indicates that the vehicle is a vehicle that can be charged. "The vehicle parking area identifier is not empty" indicates that the vehicle is located in the vehicle parking area. "The vehicle crossing the line identifier is empty" indicates that the vehicle is parked reasonably and has not crossed the line. "The vehicle type indicates that the vehicle is a vehicle that can be charged" indicates that the vehicle can be charged to avoid the occupation of the vehicle parking area caused by fuel vehicles. The information reading device can be a roadside unit (RSU). The information reading device can be installed above the charging equipment within the vehicle parking area, facing the parking area. The information reading device can communicate with the onboard unit (OBU) of the target vehicle to obtain secondary vehicle information corresponding to the target vehicle.

[0066] In practice, when the vehicle parking description information and the aforementioned first vehicle information meet the preset parking conditions, the information reading device within the target vehicle's parking area can be activated to read the target vehicle's information and obtain the second vehicle information. Compared to the conventional method of triggering the information reading device through underground inductive loops, the method of extracting the first vehicle information and vehicle parking information based on image recognition and then triggering the information reading device is less costly. Furthermore, since the first vehicle information is extracted using image recognition, cross-validation can be performed to avoid mismatches between vehicles and their information.

[0067] In some optional implementations of certain embodiments, the execution entity, in response to the vehicle parking description information and the first vehicle information satisfying preset parking conditions, reads information about the target vehicle through an information reading device within the target vehicle parking area to obtain second vehicle information, including: Step S1: Activate the information reading device in the above-mentioned target vehicle parking area.

[0068] In practice, when the vehicle parking description information and the aforementioned first vehicle information meet the preset parking conditions, a start command can be sent to the information reading device within the target vehicle parking area to activate the information reading device. Compared to the method of continuous broadcast signals, the passive triggering mode of this disclosure can effectively improve recognition efficiency and reduce unnecessary resource consumption.

[0069] Step S2: In response to successful activation, broadcast the device identity signal through the information reading device in the aforementioned target vehicle parking area.

[0070] In practice, information reading devices can broadcast their own device identity signals at a specific frequency (e.g., 5.8Hz).

[0071] Step S3: In response to receiving the broadcast response information, a temporary communication channel is created.

[0072] The aforementioned broadcast response information is initiated by the on-board equipment included in the target vehicle upon receiving the broadcast device identification signal. The broadcast response information characterizes the response signal initiated by the on-board equipment (e.g., on-board unit) included in the target vehicle upon receiving the broadcast device identification signal. The temporary communication channel is a communication channel temporarily constructed for one-to-one communication between the information reading device and the on-board equipment included in the target vehicle.

[0073] In practice, microwave channels at specific frequencies can be created as temporary communication channels. Specifically, multiple parallel communication channels can be created, and the channel with the best signal-to-noise ratio can be selected as the temporary communication channel.

[0074] Step S4: In response to the successful creation of the temporary communication channel, initiate a device certificate request to the on-board equipment included in the target vehicle through the temporary communication channel, and receive the device certificate sent by the on-board equipment included in the target vehicle through the temporary communication channel.

[0075] Among them, the device certificate is the device authorization certificate corresponding to the on-board equipment of the target vehicle. When the on-board equipment is activated, the CA (Certificate Authority) will issue a unique device certificate to the on-board equipment included in the target vehicle.

[0076] Step S5: Perform anti-counterfeiting verification on the above equipment certificates.

[0077] In practice, the aforementioned device certificates can be verified online using a CA (Certificate Authority) to prevent counterfeiting.

[0078] Step S6: In response to the above device certificate passing the anti-counterfeiting verification, generate a session key.

[0079] The session key is an asymmetric key.

[0080] In practice, the national cryptographic algorithm SM2 can be used to generate asymmetric encryption keys, which can then be used as session keys.

[0081] Step S7: Using the aforementioned temporary communication channel and session key, encrypted vehicle information is obtained from the on-board equipment of the target vehicle to obtain the second vehicle information.

[0082] In practice, the information reading device can send the public key, which includes the session key, to the on-board equipment of the target vehicle via a temporary communication channel. Upon receiving the public key, the on-board equipment encrypts the vehicle information and sends it to the information reading device via the temporary communication channel. The information reading device, upon receiving the encrypted vehicle information, decrypts it using its private key to obtain the second vehicle information.

[0083] In some optional implementations of some embodiments, the above method further includes: Step S1: In response to the fact that the vehicle parking description information does not meet the above preset parking conditions, select the vehicle parking areas that are in an idle state from at least two vehicle parking areas included in the target area as candidate vehicle parking areas, and obtain a set of candidate vehicle parking areas.

[0084] In practice, firstly, the status (occupied or vacant) of the parking areas included in the target area can be determined. Then, from at least two parking areas included in the target area, parking areas that are vacant are selected as candidate parking areas, resulting in a set of candidate parking areas.

[0085] Step S2: Based on the above vehicle parking description information, determine the location recommendation degree corresponding to each candidate vehicle parking area in the above candidate vehicle parking area set.

[0086] Among them, the location recommendation degree represents the recommendation degree of the recommended vehicle parking location, and the value range of the location recommendation degree can be [0,1].

[0087] In practice, since vehicle parking description information includes the vehicle's parking location, and the closer the locations are, the higher the recommendation score (i.e., there is an inverse relationship between location distance and recommendation score), the location recommendation score can be calculated by taking the location distance between the vehicle's parking location and the candidate vehicle parking area, normalizing the location distance, and then taking the inverse ratio.

[0088] Step S3: Select candidate vehicle parking areas from the above set of candidate vehicle parking areas whose location recommendation scores meet the location selection criteria, and use them as recommended vehicle parking areas; The selection criterion is that the corresponding location has the highest recommendation score.

[0089] Step S4: Generate vehicle guidance information based on the recommended vehicle parking areas mentioned above.

[0090] The vehicle guidance information is used to guide vehicles to the recommended parking area. For example, the vehicle guidance information may include the area identifier corresponding to the recommended parking area.

[0091] Step S5: Based on the vehicle guidance information above, guide the electric vehicle corresponding to the first vehicle information above to move to the recommended vehicle parking area above.

[0092] In practice, the electric vehicle corresponding to the first vehicle information can be guided to the recommended parking area by voice broadcast based on the vehicle guidance information.

[0093] Step S6: In response to the electric vehicle corresponding to the first vehicle information moving to the recommended vehicle parking area, the updated vehicle parking description information is determined as the vehicle parking description information, and the recommended vehicle parking area is determined as the target vehicle parking area.

[0094] Step S7: In response to the fact that the first vehicle information does not meet the preset parking conditions, a drive-away prompt is initiated for the electric vehicle corresponding to the first vehicle information.

[0095] In practice, when the first vehicle information does not meet the above-mentioned preset parking conditions, that is, the vehicle type included in the first vehicle information does not meet the preset parking conditions that "the vehicle type indicates that the vehicle is a vehicle that can be charged and replenished", the vehicle needs to be removed in a timely manner to ensure the efficient use of the vehicle parking area and avoid unnecessary occupation of the vehicle parking area.

[0096] Step 103: In response to the matching of the first vehicle information and the second vehicle information, and the power replenishment equipment in the target vehicle parking area being connected to the power supply of the target vehicle, the target vehicle is powered.

[0097] In practice, matching the first vehicle information and the second vehicle information indicates that the vehicle information (first vehicle information) obtained through image recognition and the vehicle information (second vehicle information) obtained based on the information reading device are consistent. At the same time, when the energy replenishment device is connected to the target vehicle for power supply, it indicates that the vehicle meets the hardware conditions for charging and energy replenishment. Therefore, the target vehicle can be recharged by the energy replenishment device.

[0098] Step 104: In response to the disconnection of the charging equipment in the target vehicle parking area from the target vehicle, charge description information is generated, and the information of the target vehicle is read again by the information reading equipment in the target vehicle parking area to obtain the third vehicle information.

[0099] The charging description information represents the electricity consumption data of the target vehicle from the start to the end of the charging process. Specifically, the charging description information may include, but is not limited to, the power supply capacity and the duration of power supply.

[0100] In practice, the charging equipment can obtain charging description information from the electricity consumption data of the target vehicle from the start to the end of the charging process. Meanwhile, to prevent malicious replacement of the on-board unit to circumvent billing during the charging phase, it is necessary to read the target vehicle's information again through information reading devices in the target vehicle's parking area to obtain third vehicle information. The specific reading method is the same as that for the second vehicle information; details can be found in step 102, and will not be repeated here.

[0101] Step 105: Generate a recharge push notification based on the second vehicle information, the third vehicle information, and the recharge description information.

[0102] In some embodiments, the aforementioned executing entity may generate recharge push information based on the second vehicle information, the third vehicle information, and the recharge description information.

[0103] Among them, the energy replenishment push information represents the billing data related to the charging and energy replenishment of the target vehicle.

[0104] In practice, firstly, the information of the second and third vehicles can be matched to determine whether the on-board unit of the target vehicle has been maliciously replaced during the charging replenishment phase. Then, when the second and third vehicle information match, a charging replenishment push notification is generated based on the charging description information and preset billing rules.

[0105] Optionally, the energy replenishment push information includes: push type and energy replenishment bill. The push type represents the method of pushing the energy replenishment information. Specifically, the push type can include: a first push type and a second push type. The first push type represents the type of energy replenishment bill push via an ETC (Electronic Toll Collection) account. The second push type represents the type of energy replenishment bill push via a QR code. The energy replenishment bill represents specific billing data. Specifically, the energy replenishment bill may include, but is not limited to: billing price, electricity consumption, power supply capacity, power supply duration, and bill number.

[0106] In some optional implementations of certain embodiments, the execution entity generates replenishment push information based on the second vehicle information, the third vehicle information, and the replenishment description information, including: Step S1: Based on the above power replenishment description information and the preset billing rules, generate the power replenishment bill included in the power replenishment push information.

[0107] Among them, the billing generation rule represents the billing rules preset based on the power supply and power supply duration.

[0108] In practice, firstly, electricity consumption can be generated based on power supply capacity and duration. Then, a billing price is generated based on electricity consumption, power supply capacity, duration, and billing rules. Finally, an incremental billing number is generated to obtain the energy replenishment bill.

[0109] Step S2: In response to the matching of the second vehicle information and the third vehicle information, the push type included in the energy replenishment push information is determined as the first push type.

[0110] In practice, when the second vehicle information matches the aforementioned third vehicle information, it indicates that the target vehicle did not experience malicious replacement of its on-board unit during the charging and recharge phase.

[0111] Step S3: In response to the mismatch between the second vehicle information and the third vehicle information, the push type included in the energy replenishment push information is determined as the second push type.

[0112] In practice, when the information of the second vehicle does not match the information of the third vehicle mentioned above, it indicates that the on-board unit of the target vehicle has been maliciously replaced during the charging and recharging phase.

[0113] Specifically, by setting processing constraints for matching second and third vehicle information, the logical robustness of the entire charging and replenishment process is improved, thereby enhancing the user experience and minimizing malicious behavior.

[0114] In some optional implementations of some embodiments, the above method further includes: Step S1: In response to the above push type being the first push type, and the above second vehicle information and the above third vehicle information matching, a target request is initiated to the target account corresponding to the above second vehicle information based on the above refueling bill.

[0115] The target account is the ETC account corresponding to the on-board unit of the target vehicle. The target request is a toll deduction request.

[0116] In practice, given that the target account is known, a target request (deduction request) for the energy replenishment bill can be sent remotely to the target account.

[0117] Step S2: In response to receiving the first request response information for the above-mentioned target request, control the vehicle fixed ground lock set in the above-mentioned target vehicle parking area to close.

[0118] The first request response information represents a successful request response to the target request. The vehicle fixed parking lock is a parking lock device installed on the ground in the target vehicle parking area. When the vehicle fixed parking lock is open, the vehicle cannot drive out of the parking area. When the vehicle fixed parking lock is closed, the vehicle can drive out of the parking area.

[0119] In practice, when the first request response information is received, it indicates that the target account has been charged normally for the refueling bill. At this time, the vehicle's fixed ground lock set in the above-mentioned target vehicle parking area can be closed so that the target vehicle can drive out of the target vehicle parking area.

[0120] Step S3: In response to receiving the second request response information for the above target request, or the above push type is the second push type, or the above second vehicle information and the above third vehicle information do not match, generate a dynamic QR code according to the above energy replenishment bill, and push the above dynamic QR code to the information display screen.

[0121] The aforementioned information display screen is embedded in the charging equipment located within the parking area of ​​the target vehicles. The dynamic QR code is refreshed periodically. The information display screen faces the parking area. The dynamic QR code is a payment QR code generated based on the charging bill.

[0122] Step S4: In response to receiving the first scanning result information for the above dynamic QR code, control the vehicle fixed ground lock set in the above target vehicle parking area to close.

[0123] The first scan result indicates that the dynamic QR code has been scanned and the corresponding energy replenishment fee has been paid.

[0124] Step S5: In response to receiving the second scanning result information for the above dynamic QR code, display the second scanning result information on the above information display screen.

[0125] The second scan result indicates that the energy replenishment fee corresponding to the energy replenishment bill has not been paid or the payment failed.

[0126] In practice, this method improves the entire process logic of electric vehicle self-charging from start to finish, achieving vehicle charging as seamlessly as possible for users. At the same time, it overcomes the problem that static QR codes may fail to be called due to damage or poor network conditions, such as the calling method of static QR codes or specific software (e.g., mobile payment apps). This ensures the user experience and the convenience of charging.

[0127] The various embodiments disclosed above have the following beneficial effects: the vehicle identification method applied to electric vehicle charging scenarios through some embodiments of this disclosure improves the convenience and robustness of vehicle charging. Specifically, for electric vehicle charging scenarios, the industry currently mainly has two solutions: "charging charging" and "battery swapping charging," with the "charging charging" solution accounting for a higher proportion of electric vehicles. For the "charging charging" solution, the industry mainly adopts a combination of "charging pile + parking space," where parking spaces (vehicle parking areas) are used to park electric vehicles for charging, and charging piles are used to charge the electric vehicles. Based on this solution, static QR codes or specific software programs are mainly used to invoke the charging service. However, when the static QR code is damaged, or when the network environment is poor, the invocation method using static QR codes or specific software programs may fail, resulting in the electric vehicle being unable to recharge in a timely manner, thus affecting the convenience and robustness of vehicle charging. Based on this, some embodiments of the vehicle identification method applied to electric vehicle charging scenarios disclosed herein firstly perform vehicle identification on real-time area video of a target area to generate first vehicle information and vehicle parking description information. The target area is used to park electric vehicles awaiting charging, and includes at least two vehicle parking areas. This automatically identifies the vehicle information and parking status of vehicles entering the target area through video recognition. Secondly, in response to the vehicle parking description information and the first vehicle information meeting preset parking conditions, the information of the target vehicle is read by an information reading device within the target vehicle parking area to obtain second vehicle information. The target vehicle parking area is the parking area corresponding to the vehicle parking description information, and the target vehicle is the electric vehicle parked within the target vehicle parking area, corresponding to the first vehicle information. The information reading device within the target vehicle parking area automatically acquires vehicle information related to the electric vehicle. Next, in response to the matching of the first vehicle information and the second vehicle information, and the charging device within the target vehicle parking area being connected to the target vehicle's power supply, the target vehicle is charged.

[0128] Compared to using static QR codes or specific software programs, this method effectively optimizes and simplifies the usage logic. Furthermore, in response to the disconnection of the charging equipment from the target vehicle's parking area, charging description information is generated, and the target vehicle's information is read again by the information reading device within the parking area to obtain third vehicle information. This automatically generates relevant charging data during the vehicle charging process, and by re-obtaining vehicle information, it avoids anomalies in charging push information generation caused by malicious tampering of vehicle information during the charging phase. Finally, charging push information is generated based on the second vehicle information, the third vehicle information, and the charging description information. This method effectively optimizes and simplifies the vehicle charging logic, and improves the convenience and robustness of vehicle charging.

[0129] Further reference Figure 4 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a vehicle identification device applied to electric vehicle refueling scenarios. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, the vehicle identification device for electric vehicle charging scenarios can be specifically applied to various electronic devices.

[0130] like Figure 4As shown, a vehicle identification device 400 applied to an electric vehicle refueling scenario in some embodiments includes: a vehicle identification unit 401, an activation unit 402, a vehicle refueling unit 403, a first generation and reactivation unit 404, and a second generation unit 405. The vehicle identification unit 401 is configured to perform vehicle identification on real-time area video of a target area to generate first vehicle information and vehicle parking description information. The target area is used for parking electric vehicles awaiting refueling, and includes at least two vehicle parking areas. The activation unit 402 is configured to, in response to the vehicle parking description information and the first vehicle information meeting preset parking conditions, read information about the target vehicle through an information reading device within the target vehicle parking area to obtain second vehicle information. The target vehicle parking area is the area corresponding to the vehicle parking description information. The vehicle parking area corresponding to the aforementioned information, the target vehicle being an electric vehicle parked within the target vehicle parking area corresponding to the aforementioned first vehicle information; the vehicle charging unit 403 is configured to provide vehicle charging to the target vehicle in response to the matching of the aforementioned first vehicle information and the aforementioned second vehicle information, and the charging device in the aforementioned target vehicle parking area being connected to the power supply of the target vehicle; the first generation and reactivation unit 404 is configured to generate charging description information in response to the disconnection of the charging device in the aforementioned target vehicle parking area from the target vehicle, and to re-read the information of the target vehicle through the information reading device in the aforementioned target vehicle parking area to obtain third vehicle information; the second generation unit 405 is configured to generate charging push information based on the aforementioned second vehicle information, the aforementioned third vehicle information, and the aforementioned charging description information. It is understood that the units described in this vehicle identification device 400 applied to electric vehicle charging scenarios are similar to those in the reference... Figure 1 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method are also applicable to the vehicle identification device 400 and its constituent units used in electric vehicle refueling scenarios, and will not be repeated here.

[0131] The following is for reference. Figure 5 It shows a schematic diagram of the structure of an electronic device (e.g., a computing device) 500 suitable for implementing some embodiments of the present disclosure. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0132] like Figure 5As shown, the electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory 502 or a program loaded from a storage device 508 into a random access memory 503. The random access memory 503 also stores various programs and data required for the operation of the electronic device 500. The processing unit 501, the read-only memory 502, and the random access memory 503 are interconnected via a bus 504. An input / output interface 505 is also connected to the bus 504.

[0133] Typically, the following devices can be connected to the input / output interface 505: input devices 506 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 5 Each box shown can represent a device or multiple devices as needed.

[0134] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a read-only memory 502. When the computer program is executed by the processing device 501, it performs the functions defined above in the methods of some embodiments of this disclosure.

[0135] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-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 of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer 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. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0136] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0137] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: perform vehicle identification on real-time area video of a target area to generate first vehicle information and vehicle parking description information, wherein the target area is used for parking electric vehicles awaiting refueling, and the target area includes at least two vehicle parking areas; in response to the vehicle parking description information and the first vehicle information satisfying preset parking conditions, read information about the target vehicle through an information reading device within the target vehicle parking area to obtain second vehicle information, wherein the target vehicle parking area is the vehicle parking area corresponding to the vehicle parking description information. The target vehicle is an electric vehicle parked within the target vehicle parking area, corresponding to the first vehicle information. In response to a match between the first vehicle information and the second vehicle information, and a power replenishment device within the target vehicle parking area connecting to the target vehicle, the target vehicle is powered. In response to a disconnection between the power replenishment device within the target vehicle parking area and the target vehicle, power replenishment description information is generated, and information is read again from the target vehicle using an information reading device within the target vehicle parking area to obtain third vehicle information. Power replenishment push information is generated based on the second vehicle information, the third vehicle information, and the power replenishment description information.

[0138] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0139] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0140] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0141] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A vehicle identification method applied to electric vehicle refueling scenarios, characterized in that, include: Vehicle identification is performed on real-time area video of the target area to generate first vehicle information and vehicle parking description information, wherein the target area is used for parking electric vehicles waiting to be recharged, and the target area includes at least two vehicle parking areas; In response to the vehicle parking description information and the first vehicle information meeting the preset parking conditions, the information of the target vehicle is read by the information reading device in the target vehicle parking area to obtain the second vehicle information. The target vehicle parking area is the vehicle parking area corresponding to the vehicle parking description information, and the target vehicle is an electric vehicle parked in the target vehicle parking area corresponding to the first vehicle information. In response to the matching of the first vehicle information and the second vehicle information, and the power replenishment equipment in the target vehicle parking area being connected to the power supply of the target vehicle, the target vehicle is provided with vehicle power replenishment; In response to the disconnection of the charging device in the target vehicle parking area from the target vehicle, charging description information is generated, and the information reading device in the target vehicle parking area is used to read the information of the target vehicle again to obtain third vehicle information; Based on the second vehicle information, the third vehicle information, and the recharge description information, a recharge push notification is generated.

2. The vehicle identification method for electric vehicle refueling scenarios according to claim 1, characterized in that, The power replenishment push information includes: push type and power replenishment bill, wherein the method further includes: In response to the push type being the first push type, and the second vehicle information and the third vehicle information matching, a target request is initiated to the target account corresponding to the second vehicle information based on the refueling bill; In response to receiving a first request response information for the target request, the vehicle fixed ground lock set in the target vehicle parking area is controlled to close; In response to receiving a second request response information for the target request, or the push type is a second push type, or the second vehicle information and the third vehicle information do not match, a dynamic QR code is generated according to the charging bill, and the dynamic QR code is pushed to the information display screen, wherein the information display screen is embedded in the charging equipment set in the parking area of ​​the target vehicle, and the dynamic QR code is refreshed periodically; In response to receiving the first scanning result information for the dynamic QR code, the vehicle's fixed ground lock set in the target vehicle parking area is controlled to close; In response to receiving the second scanning result information for the dynamic QR code, the second scanning result information is displayed on the information display screen.

3. The vehicle identification method for electric vehicle refueling scenarios according to claim 2, characterized in that, The method further includes: In response to the fact that the vehicle parking description information does not meet the preset parking conditions, a vehicle parking area that is in an idle state is selected from at least two vehicle parking areas included in the target area as a candidate vehicle parking area, thereby obtaining a set of candidate vehicle parking areas. Based on the vehicle parking description information, determine the location recommendation degree corresponding to each candidate vehicle parking area in the candidate vehicle parking area set; From the set of candidate vehicle parking areas, select candidate vehicle parking areas whose location recommendation degree meets the location selection criteria, and use them as recommended vehicle parking areas; Based on the recommended vehicle parking areas, vehicle guidance information is generated; Based on the vehicle guidance information, guide the electric vehicle corresponding to the first vehicle information to move to the recommended vehicle parking area; In response to the electric vehicle corresponding to the first vehicle information moving to the recommended vehicle parking area, the updated vehicle parking description information is determined as the vehicle parking description information, and the recommended vehicle parking area is determined as the target vehicle parking area; In response to the fact that the first vehicle information does not meet the preset parking conditions, a prompt to remove the electric vehicle corresponding to the first vehicle information is initiated.

4. The vehicle identification method for electric vehicle refueling scenarios according to claim 3, characterized in that, In response to the vehicle parking description information and the first vehicle information satisfying preset parking conditions, the information reading device within the target vehicle parking area reads the information of the target vehicle to obtain the second vehicle information, including: Activate the information reading device within the parking area of ​​the target vehicle; Upon successful activation, the device identification signal is broadcast through the information reading device within the target vehicle's parking area; In response to receiving a broadcast response message, a temporary communication channel is created, wherein the broadcast response message is initiated by the on-board equipment included in the target vehicle after receiving the broadcast device identity signal; In response to the successful creation of the temporary communication channel, a device certificate request is initiated to the on-board equipment included in the target vehicle through the temporary communication channel, and a device certificate sent by the on-board equipment included in the target vehicle is received through the temporary communication channel. The device certificate is verified against counterfeiting. In response to the device certificate passing the anti-spoofing verification, a session key is generated; Encrypted vehicle information is obtained from the on-board equipment of the target vehicle through the temporary communication channel and the session key, thus obtaining the second vehicle information.

5. The vehicle identification method for electric vehicle refueling scenarios according to claim 4, characterized in that, The step of generating charging push information based on the second vehicle information, the third vehicle information, and the charging description information includes: Based on the aforementioned energy replenishment description information and the preset billing generation rules, generate the energy replenishment bill, which includes the energy replenishment push information. In response to the matching of the second vehicle information and the third vehicle information, the push type included in the energy replenishment push information is determined as the first push type; In response to the mismatch between the second vehicle information and the third vehicle information, the push type included in the energy replenishment push information is determined to be the second push type.

6. The vehicle identification method for electric vehicle refueling scenarios according to claim 5, characterized in that, The step of performing vehicle identification on real-time area video of the target area to generate first vehicle information and vehicle parking description information includes: The real-time regional video is subjected to fixed-frequency frame extraction to obtain a video image sequence; For each video image in the video image sequence, perform the following processing steps: The foreground image is obtained by determining the image difference between the video image and the background image; The foreground image is enhanced to obtain the enhanced image; Extract the edge contour features of the enhanced image; Based on the obtained set of edge contour features, trajectory features are generated; Based on the trajectory characteristics, determine whether a vehicle has entered the target area; In response to the presence of a vehicle entering the target area, vehicle identification is performed using a pre-trained vehicle recognition model and the real-time area video to obtain first vehicle information and vehicle parking description information.

7. The vehicle identification method for electric vehicle refueling scenarios according to claim 6, characterized in that, The vehicle recognition model includes a vehicle positioning network and a vehicle identity information recognition network. The process of identifying vehicles using a pre-trained vehicle recognition model and real-time area video to obtain first vehicle information and vehicle parking description information includes: Vehicle positioning is performed based on the vehicle positioning network and the real-time regional video to obtain a target image sequence, wherein the target image is a local image containing the vehicle and the target image is labeled with the vehicle motion status identifier. Vehicle identification is performed based on the vehicle identification information recognition network and the target image sequence to obtain a vehicle identification identifier; Based on the vehicle identification identifier, a vehicle identity query is performed to obtain the first vehicle information; The target image sequence is traversed in reverse order to determine the first target image that corresponds to the vehicle motion state identifier indicating that the vehicle is stationary, which is then used as a candidate image. The vehicle position is obtained by mapping the vehicle position based on the candidate image; Obtain the area boundary information of the vehicle parking area that matches the vehicle's location; Based on the vehicle location, the area boundary information, and the candidate image, vehicle parking description information is generated.

8. A vehicle identification device for electric vehicle refueling scenarios, characterized in that, include: The vehicle recognition unit is configured to perform vehicle recognition on real-time area video of a target area to generate first vehicle information and vehicle parking description information, wherein the target area is used for parking electric vehicles waiting to be recharged, and the target area includes at least two vehicle parking areas. The activation unit is configured to, in response to the vehicle parking description information and the first vehicle information satisfying preset parking conditions, read the information of the target vehicle through the information reading device in the target vehicle parking area to obtain the second vehicle information, wherein the target vehicle parking area is the vehicle parking area corresponding to the vehicle parking description information, and the target vehicle is an electric vehicle parked in the target vehicle parking area corresponding to the first vehicle information; The vehicle refueling unit is configured to respond to a match between the first vehicle information and the second vehicle information, and to provide vehicle refueling to the target vehicle by connecting the refueling equipment in the target vehicle parking area to the target vehicle's power supply. The first generation and reactivation unit is configured to generate power replenishment description information in response to the disconnection of the power replenishment device in the target vehicle parking area from the target vehicle, and to read the information of the target vehicle again through the information reading device in the target vehicle parking area to obtain third vehicle information. The second generation unit is configured to generate recharge push information based on the second vehicle information, the third vehicle information, and the recharge description information.

9. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 7.

10. A computer-readable medium, characterized in that, It stores a computer program thereon, wherein the computer program, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images