Battery swapping position recommendation method and device for battery swapping station, equipment and storage medium

Abstract

The application provides a battery replacement position recommendation method and device for a battery replacement station, equipment and a storage medium. The method comprises: acquiring feature information of a target object, and performing query matching on the feature information of the target object; predicting first waiting time information required for the target object to replace a battery from a current position to any battery replacement area in a first battery replacement station according to a result of the query matching; and providing a recommended first battery replacement area to a driving user of the target object according to the first waiting time information. Therefore, the application can provide a better battery replacement scheme for the user, so as to distribute the target objects to be replaced, thereby reducing the waiting time of the user, improving the battery replacement experience of the user, and also helping to reasonably and evenly distribute the resources of each battery replacement station and battery replacement area, so as to improve the utilization rate of the battery replacement station and the battery replacement area.

Description

Technical Field

[0001] This application relates to the field of battery swapping station navigation technology, specifically to a method, apparatus, equipment, and storage medium for recommending battery swapping locations at battery swapping stations. Background Technology

[0002] Currently, there are two main ways to replenish the power of electric vehicles: charging at charging stations and battery swapping at battery swapping stations. Compared to charging at charging stations, battery swapping at battery swapping stations allows users to quickly regain a fully charged vehicle without damaging the battery. The replaced battery can be repaired and maintained to extend its lifespan or used for other purposes.

[0003] However, the road conditions in front of the battery swapping stations are quite complex. Without proper planning, congestion can easily occur when there are many users needing battery swaps. Users at the back of the queue will not be able to observe the operation of all swapping bays and will be forced to wait blindly. This could lead to situations where users wait a long time at one swapping bay only to find there are no batteries available. In this case, users have no choice but to try another swapping bay or drive to another station. This not only wastes a lot of users' time but also prevents the efficient allocation of swapping bay resources within the station. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and storage medium for recommending battery swapping locations at battery swapping stations, in order to improve battery swapping efficiency.

[0005] This application provides a method for recommending battery swapping locations for battery swapping stations. The method includes: acquiring feature information of a target object and querying and matching the feature information of the target object in a preset database; predicting, based on the query and matching results, the first waiting time information required for the target object to swap batteries from its current location to any battery swapping area in a first battery swapping station; and providing a recommended first battery swapping area to the driver of the target object based on the first waiting time information.

[0006] In some embodiments, the feature information includes the appearance features and size parameters of the target object, and the method for querying and matching the feature information of the target object includes: performing vehicle model recognition on the target object based on the appearance features and the size parameters, and querying and matching the result of vehicle model recognition with a preset vehicle model in a preset database.

[0007] In some embodiments, a pre-diversion area is provided at the first battery swapping station, and the step of acquiring the appearance image and size parameters of the target object is performed in the pre-diversion area. The appearance image is used to extract the appearance features, and the current position is the location of the pre-diversion area.

[0008] In some embodiments, when the first waiting time information conforms to a preset rule, the following steps are performed: predicting the second waiting time information required for the target object to swap batteries from its current location to any of the battery swapping areas in a second battery swapping station; and providing the target object's driver with recommended second battery swapping areas based on the second waiting time information.

[0009] In some embodiments, the step of predicting the second waiting time information required for the target object to swap batteries from its current location to a battery swapping area in the second battery swapping station includes: inputting second battery swapping parameters into a second trained machine learning model, wherein the second battery swapping parameters include the location information of the second battery swapping station, and further include any of the following: the current remaining battery power of the target object, the time required for the target object to move to the second battery swapping station, the location information of the battery swapping area in the second battery swapping station, the number of battery swapping areas in the second battery swapping station, the number of vehicles waiting for battery swapping at the second battery swapping station, and the number of batteries in stock at the second battery swapping station; and calculating the second waiting time information based on the second trained machine learning model.

[0010] In some embodiments, the step of obtaining the appearance features of the target object includes: obtaining an appearance image of the target object; performing grayscale processing on the appearance image; and using the Canny edge detection operator to extract edge features to obtain the appearance features.

[0011] In some embodiments, the dimensional parameters include vehicle length, vehicle width, and vehicle height. A pre-diversion area is provided at the first battery swapping station. The vehicle length parameter of the target object is obtained based on a first ranging device set along the length direction at the pre-diversion area; the vehicle width parameter of the target object is obtained based on a second ranging device set along the width direction at the pre-diversion area; and the vehicle height parameter of the target object is obtained based on a third ranging device set along the height direction at the pre-diversion area.

[0012] In some embodiments, the step of identifying the vehicle type of the target object includes: inputting the appearance image of the target object into a trained network model; obtaining the appearance features of the appearance image based on the trained network model; inputting the appearance features and the size parameters into a trained classifier model; and identifying the vehicle type information of the target object based on the trained classifier model, wherein the preset condition is that the vehicle type information belongs to the range of battery swapping vehicle types of the first battery swapping station.

[0013] In some embodiments, the method further includes the following steps: determining whether the target object is a vehicle based on the appearance features; if the target object is not a vehicle, issuing a first prompt message; if the target object is a vehicle, obtaining the size parameters of the target object and performing vehicle model recognition; if the result of the vehicle model recognition does not meet a preset condition, issuing a second prompt message; if the result of the vehicle model recognition is that there are interfering objects, issuing a third prompt message.

[0014] In some embodiments, after the query matching result meets a preset condition, a corresponding target state parameter is established for the target object. The target state parameter is used to characterize the current battery swapping state of the target object. The battery swapping state includes waiting for battery swapping, battery swapping in progress, and battery swapping completed.

[0015] In some embodiments, the step of predicting the first waiting time information required for the target object to swap batteries from its current location to a battery swapping area in the first battery swapping station includes: inputting first battery swapping parameters into a first trained machine learning model, wherein the first battery swapping parameters include location information of the battery swapping area in the first battery swapping station, and further include any of the following: the number of battery swapping areas in the first battery swapping station, the time required for the target object to move from its current location to the battery swapping area, the number of vehicles waiting for battery swapping at the battery swapping area in the first battery swapping station, the battery swapping time required for a vehicle currently swapping batteries at the first battery swapping station, and the number of batteries in stock at the first battery swapping station; and calculating the first waiting time information based on the first trained machine learning model.

[0016] Accordingly, this application also provides a battery swapping location recommendation device for a battery swapping station, comprising an acquisition unit, an identification unit, a first prediction unit, and a recommendation unit. The acquisition unit is used to acquire the appearance features and size parameters of a target object; the identification unit is used to identify the vehicle type of the target object based on the appearance features and size parameters; the first prediction unit is used to predict the first waiting time information required for the target object to swap batteries from its current location to a battery swapping area in a first battery swapping station; and the recommendation unit is used to provide a recommended first battery swapping area to the driver of the target object based on the first waiting time information.

[0017] In some embodiments, a pre-diversion area is provided at the first battery swapping station. The acquisition unit includes an image acquisition device and a ranging device disposed in the pre-diversion area. The image acquisition device is used to acquire an appearance image of the target object, and the appearance image is used to extract the appearance features. The ranging device is used to acquire the size parameters of the target object.

[0018] In some embodiments, the recommendation device further includes a second prediction unit, which is configured to predict second waiting time information required for the target object to swap batteries from its current location to a battery swapping area in a second battery swapping station; the recommendation unit is also configured to provide a recommended second battery swapping area to the target object's driver based on the second waiting time information.

[0019] Accordingly, this application also provides a computer 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 battery swapping location recommendation method for any of the preceding claims.

[0020] Accordingly, this application also provides a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to execute the battery swapping location recommendation method for any of the preceding claims.

[0021] This application has the following beneficial effects: This application provides a method, apparatus, equipment and storage medium for recommending battery swapping locations for battery swapping stations, which can provide users with better battery swapping solutions so as to divert the target objects to be swapped, thereby reducing user waiting time, improving user battery swapping experience, and also helping to reasonably and evenly allocate resources of each battery swapping station and battery swapping area to improve the utilization rate of battery swapping stations and battery swapping areas. Attached Figure Description

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

[0023] Figure 1 An exemplary flowchart illustrates a method for recommending battery swapping locations for battery swapping stations.

[0024] Figure 2 Example shown Figure 1 A detailed flowchart of step 100;

[0025] Figure 3 Example shown Figure 2 A detailed flowchart of step 140;

[0026] Figure 4 Example shown Figure 1 A detailed flowchart of step 200;

[0027] Figure 5An exemplary flowchart of steps 400-500 is shown;

[0028] Figure 6 Example shown Figure 5 Detailed flowchart of step 400;

[0029] Figure 7 An exemplary schematic diagram of the structure of a first battery swapping station is shown;

[0030] Figure 8 This example illustrates a flowchart of the process for obtaining the vehicle type in an application example.

[0031] Figure 9 The example illustrates a flowchart of a process for determining whether a target object belongs to a preset vehicle model range in an application example;

[0032] Figure 10 An example diagram illustrating a vehicle-specific identification number is shown below.

[0033] Figure 11 An exemplary schematic diagram of a battery swapping location recommendation device for a battery swapping station is shown.

[0034] Figure 12 An exemplary schematic diagram of another battery swapping location recommendation device for a battery swapping station is shown.

[0035] Figure 13 An exemplary schematic diagram of a computer device is shown. Detailed Implementation

[0036] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. In addition, it should be understood that the specific embodiments described herein are only for illustration and explanation of this application and are not intended to limit this application. In this application, unless otherwise stated, directional terms such as "up," "down," "left," and "right" generally refer to up, down, left, and right in the actual use or working state of the device, specifically the drawing directions in the accompanying drawings.

[0037] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of those features. Moreover, the step numbers in this embodiment do not completely limit the order in which the steps are performed; in some embodiments, related steps may be performed in an order different from that of the step numbers. The examples in the embodiments of this application do not constitute an undue limitation on this application.

[0038] This application provides a method, apparatus, device, and storage medium for recommending battery swapping locations at battery swapping stations, which are described in detail below. It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments of this application. Furthermore, the descriptions of each embodiment have their own emphasis; parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments.

[0039] This application provides a method, apparatus, device, and storage medium for recommending battery swapping locations at battery swapping stations. Specifically, the battery swapping location recommendation method of this application can be executed by a computer device, which can be a terminal or a server. The terminal can be a smartphone, tablet, laptop, touchscreen, personal computer (PC), personal digital assistant (PDA), or other terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0040] For example, the computer device can be a server, which can: acquire the feature information of the target object, and query and match the feature information of the target object in a preset database; based on the query and matching results, predict the first waiting time information required for the target object to swap batteries from its current location to any battery swapping area in a first battery swapping station; and provide the target object's driver with a recommended first battery swapping area based on the first waiting time information.

[0041] Therefore, the battery swapping location recommendation method, apparatus, equipment and storage medium provided in this application embodiment can reduce users' ineffective queuing time and improve the battery swapping efficiency of the battery swapping station.

[0042] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the preferred order of the embodiments.

[0043] This application provides a method for recommending battery swapping locations for battery swapping stations. This method can be executed by a terminal or a server. This application example illustrates the method for recommending battery swapping locations by a server.

[0044] Please see Figure 1 , Figure 1 This is a flowchart illustrating a battery swapping location recommendation method provided in an embodiment of this application. The specific steps of this battery swapping location recommendation method may include the following:

[0045] 100. Obtain the feature information of the target object, and query and match the feature information of the target object in a preset database.

[0046] In some embodiments of this application, the feature information includes the appearance features and size parameters of the target object. This allows for vehicle model identification of the target object based on its appearance features and size parameters, and the identification result can be matched against preset vehicle models in a preset database. Of course, it is understood that in other embodiments, the feature information may also be vehicle logo information or other information; the examples in this embodiment do not constitute an undue limitation.

[0047] Here, in step 100, specifically, please refer to Figure 2 The steps for obtaining the appearance features of a target object may include the following process:

[0048] 110. Obtain the appearance image of the target object.

[0049] Here, in step 110, an image of the target object's appearance can be acquired using an image acquisition device. The image acquisition device may include a camera, etc. Furthermore, the image acquisition device may also include a light source, allowing it to be activated in dimly lit environments to more clearly capture the target object's appearance. For example, a pre-diversion area may be provided in a first battery swapping station, with image acquisition devices arranged in front, behind, to the left, right, and above the pre-diversion area to capture images of the target object's appearance and obtain photographs of the target object from various angles. Of course, the example in this embodiment does not constitute an undue limitation on this application; in other embodiments, the arrangement of the image acquisition devices is not limited to the above.

[0050] 120. The appearance image is converted to grayscale, and the Canny edge detection operator is used to extract edge features to obtain the appearance features of the target object.

[0051] Here, typically, the appearance image acquired in step 110 is a color image, containing three color components: R, G, and B. This color image will result in high computational load and low processing efficiency in subsequent processing. Therefore, in step 120, to reduce computational load and improve the processing efficiency of the appearance image, the server first performs grayscale processing on the appearance image after receiving it. It is understood that in some embodiments, to meet the subsequent usage requirements of the appearance image or because the appearance image acquired by the image acquisition device is a black and white image, grayscale processing may not be performed. The example in this embodiment does not constitute an undue limitation on this application. For example, here, a weighted average method is used to perform grayscale operation on the image. The weighted average method simulates the human eye's perception of different colors by setting different weights for the three color components, making the grayscale processing result more reasonable. Here, the calculation formula is as follows:

[0052] gray=0.299*R+0.587*G+0.114*B

[0053] In the formula, gray represents the grayscale value of the processed appearance image, and R, G, and B represent the RGB components at the pixel.

[0054] Here, the edges of the target object in the appearance image exhibit discontinuities in grayscale, which can be used to extract the edge features of the target object. In the embodiments of this application, the Canny edge detection operator is used for edge feature extraction because the Canny edge detection operator has high accuracy and low false detection rate, which can improve the effectiveness of subsequent steps such as vehicle recognition.

[0055] Although different brands of vehicles may have different models, their edge contours (i.e. edge features) are generally similar. Therefore, similarity comparison can be performed based on edge features. Specifically, the edge features here are the gray values ​​of the edge contours.

[0056] Here, if the similarity comparison result is less than a preset threshold, the target object is determined not to be a vehicle. In some embodiments, after determining that the target is not a vehicle, the server may issue a first prompt message. For example, the first prompt message is sent to the staff at the battery swapping station to remind them of the abnormality. The staff then make a manual judgment and take relevant actions based on the appearance image returned by the image acquisition device.

[0057] If the similarity comparison result is greater than the preset threshold, the target object is determined to be a vehicle. In this case, proceed to step 130 below.

[0058] 130. Obtain the size parameters of the target object.

[0059] In some embodiments, in step 130, the server sends a ranging command to the ranging device, which responds to the ranging command and measures the target object. Exemplarily, the size parameters of the target object include vehicle length, vehicle width, and vehicle height. Here, the vehicle length parameter is obtained using a first ranging device positioned along the length direction; the vehicle width parameter is obtained using a second ranging device positioned along the width direction; and the vehicle height parameter is obtained using a third ranging device positioned along the height direction.

[0060] It should be mentioned here that a pre-shunting area can be set up at the first battery swapping station for vehicles. The image acquisition device in step 110 and the ranging device in step 130 can both be set up in the pre-shunting area. Furthermore, a sensing detection device, such as an infrared detection device, can also be set up in the pre-shunting area. Thus, the sensing detection device can detect the presence of a target object in the pre-shunting area, and based on the signal sent back by the sensing detection device, the server can control the image acquisition device in the corresponding pre-shunting area to perform image acquisition and the ranging device to perform distance measurement. In other words, in some embodiments of this application, the steps of acquiring the appearance image and size parameters of the target object are performed in the pre-shunting area. Therefore, the above operations can be completed with fixed equipment, thereby reducing equipment costs and simplifying the acquisition operation.

[0061] Furthermore, the system focuses on recommending battery swapping stations to each target user in the pre-diversion area of ​​the first battery swapping station. Each target user waits for the recommendation result in the pre-diversion area before proceeding to the corresponding battery swapping area. This prevents the target users from crowding the roads between battery swapping areas within the battery swapping station, thereby reducing congestion.

[0062] Furthermore, since each target object waits in the pre-shunting area before obtaining the recommended battery swapping area, the subsequent path planning from the pre-shunting area to the battery swapping area is more efficient. Compared to path planning for real-time moving target objects, it can reduce the steps of obtaining the real-time location of the target objects and effectively reduce the amount of computation.

[0063] Of course, it is understood that in other embodiments, the pre-diversion area described above may not be set; the real-time location of the target object may be collected and a path to the battery swapping area may be planned. The examples in this embodiment do not constitute an undue limitation on this application.

[0064] Based on the above, it can be seen that the server has obtained the appearance features and size parameters of the target object, and the subsequent steps can be used to identify the vehicle model of the target object.

[0065] 140. Recognize vehicle models of target objects based on their appearance features and size parameters.

[0066] Here, in some embodiments, please refer to Figure 3 The steps for vehicle model recognition of the target object in step 140 specifically include the following steps 141-144.

[0067] 141. Input the appearance image of the target object into the trained network model.

[0068] Here, the trained network model has a raw database that stores vehicle images from various angles of the models compatible with the first battery swapping station, as well as the corresponding vehicle length, width, and height parameters for each model. These vehicle images and size parameters in the raw database are categorized by model and labeled accordingly. These vehicle images and size parameters can be provided by vehicle manufacturers or dealers, or obtained from other channels; the embodiments of this application do not constitute an undue limitation on them.

[0069] Here, the post-trained network model is a network model that has already been trained. Based on the input vehicle image and size parameters of the target object, it can output the vehicle model recognition result of the target object.

[0070] For example, the trained network model is trained using the following method. Here, the original database is divided into a training set and a test set, with no overlap between them. The training set is used to train the network model and adjust parameters based on the training results, while the test set is used to evaluate the predictive performance of the network model. Here, the trained network model is trained based on a convolutional neural network. That is, a convolutional neural network is used to extract features from the vehicle images in the training set to obtain the appearance features of the vehicle images in the training set and a feature extraction model.

[0071] In machine learning, a Convolutional Neural Network (CNN) is a feedforward neural network whose artificial neurons can respond to surrounding units within a certain coverage area, exhibiting excellent performance in large image processing. It includes convolutional layers. For example, the CNN model used for training to obtain the aforementioned trained network model includes 5 convolutional layers and 3 fully connected layers, with the initial input appearance image size being 227×227×3. Here, fewer convolutional layers result in more fundamental extracted features; however, setting too many convolutional layers may lead to data loss. To achieve better appearance feature extraction, this embodiment uses 5 convolutional layers, the structure of which is as follows:

[0072] (1) Convolutional layer C1: Convolution kernel: 11×11, stride: 4, after convolution, ReLU activation function is called, then max pooling is performed, size is 2×2, after pooling, LRN processing is performed, output size is 55×55×96.

[0073] (2) Convolutional layer C2: Convolution kernel: 5×5, stride: 1, after convolution, the ReLU activation function is called, and then max pooling is performed with a size of 2×2. After pooling, LRN processing is performed, and the output size is 27×27×256.

[0074] (3) Convolutional layer C3: Convolution kernel: 3×3, stride: 1, after convolution, the ReLU activation function is called, and the output size is 13×13×384.

[0075] (4) Convolutional layer C4: Convolution kernel: 3×3, stride: 1, after convolution, the ReLU activation function is called, and the output size is: 13×13×384.

[0076] (5) Convolutional layer C5: Convolution kernel: 3×3, stride: 4, after convolution, ReLU activation function is called, and then max pooling is performed, size is 2×2, output size is 6×6×256.

[0077] Among them, convolutional layers C3, C4, and C5 are interconnected, and there are no pooling or normalization layers in between.

[0078] 142. Based on the trained network model, obtain the appearance features of the appearance image.

[0079] In step 142, based on the trained network model obtained from the aforementioned training, such as the aforementioned trained network model based on a convolutional neural network, the appearance features of the image containing the target object can be obtained by inputting the image. Then, it can be further identified using a trained classifier model.

[0080] 143. Input the appearance features and size parameters into the trained classifier model.

[0081] The trained classifier model here is used to identify the vehicle model of the target object. In some embodiments, the trained classifier model can be a Support Vector Machine (SVM) classifier model. The SVM classifier model is a generalized linear classifier that performs binary classification of data using supervised learning. It can solve nonlinear problems well and has high robustness and prediction accuracy.

[0082] During training, the appearance features extracted by the aforementioned network model (e.g., a convolutional neural network model) and their corresponding vehicle size parameters are used as input to train the SVM classifier model. The SVM classifier model then identifies and obtains the vehicle models corresponding to the appearance images in the test set. Similarly, after training, appearance features are extracted from the appearance images in the test set using the aforementioned network model, and the corresponding vehicle size parameters are input. The SVM classifier model then outputs the corresponding vehicle model for testing. It is understood that the aforementioned training set may include appearance images and size parameters of target objects containing interfering elements, so as to facilitate subsequent identification of target objects containing interfering elements. This embodiment does not constitute an undue limitation.

[0083] Here, exemplarily, the SVM classifier model can select the RBF kernel function, because the RBF kernel function tested by the inventors has good applicability in the application of this embodiment. Here, the penalty factor C and the width r of the RBF kernel function of the SVM classifier model have a significant impact on the prediction performance of the SVM classifier model. In this embodiment, the Particle Swarm Optimization (PSO) algorithm is used for parameter tuning. The PSO algorithm model is: y = f(C, r), which takes the penalty factor C and the width r of the RBF kernel function as inputs, adjusts them, and outputs the adjusted penalty factor C and the width r of the RBF kernel function. This model has an inertia weight coefficient ω.

[0084]

[0085] The inertia weight coefficient ω adopts an inertia weight that changes linearly, and the adjustment formula for the inertia weight coefficient ω is as follows:

[0086] Where ω1 and ω2 are the initial and final values ​​of the inertia weight, iter is the current iteration number, and MAXITER is the maximum number of iterations. For example, ω1 = 0.9 and ω2 = 0.4.

[0087] 144. Based on the trained classifier model, identify the vehicle model information of the target object.

[0088] After the aforementioned training and testing, by inputting appearance features and vehicle size parameters into the trained classifier model, the trained classifier model can output vehicle model information.

[0089] After completing the vehicle model recognition steps, please refer to [link / reference]. Figure 1 The following steps 200 will be performed.

[0090] 200. Based on the query matching results, predict the first waiting time required for the target object to travel from its current location to any battery swapping area in the first battery swapping station for battery swapping.

[0091] Once the vehicle model information is obtained, corresponding operations can be performed based on that information. Here, the aforementioned preset database contains information on battery swapping vehicles belonging to the first battery swapping station. The query matching process checks whether the vehicle model information of the target object falls within the scope of the aforementioned preset database. Alternatively, a preset condition is set here: the vehicle model information must belong to the range of battery swapping vehicles of the first battery swapping station.

[0092] If the query result is negative, meaning the vehicle model identification result does not meet the preset condition, the server issues a second prompt message. Here, exemplarily, the second prompt message is sent to the target user's terminal to inform the user that the current first battery swapping station cannot provide battery swapping services. In some embodiments, route planning may also be provided to guide the user away from the first battery swapping station.

[0093] If the query result is positive, but there are interfering objects on the target object, such as the target object's size parameters exceeding the range of size parameters in the original database but the excess proportion is still within a preset range, it indicates that there may be interfering accessories on the exterior of the vehicle body, and the server will issue a third prompt message. For example, the third prompt message is sent to the user terminal of the target object, and in some embodiments, route planning can also be provided to guide it to the manual battery swapping area.

[0094] If the query result is yes, meaning the vehicle model identification meets the preset conditions and there are no interfering objects, it indicates that the target object meets the battery swapping conditions. In some embodiments, to facilitate the counting of target objects in different battery swapping states at the first battery swapping station for subsequent battery swapping location recommendations, corresponding target state parameters can be established for each target object. These target state parameters characterize the current battery swapping state of the target object, including waiting for battery swapping, battery swapping in progress, and battery swapping completed. The target state parameters are uploaded to the server to count the number of target objects in each charging state.

[0095] For example, all eligible battery-swapping vehicles have their own unique target status parameters in the server. Based on the different battery-swapping states of the vehicles, the target status parameters generate a first status number, a second status number, and a third status number, representing the three battery-swapping states: waiting for battery swapping, swapping in progress, and battery swapping completed, respectively. Each vehicle corresponds to only one unique number in each state. The system will use these numbers to count the number of vehicles currently waiting for battery swapping, swapping in progress, and battery swapping completed at the current battery-swapping station.

[0096] Of course, it is understood that in other embodiments, the number of target objects in different battery swapping states in the first battery swapping station can also be counted in other ways, and the example in this embodiment does not constitute an undue limitation on it.

[0097] Typically, in step 200, the first waiting time information required for the target object to swap batteries from its current location to all available battery swapping areas in the first battery swapping station is predicted, so as to make recommendations for battery swapping areas in the future. In this case, the first waiting time information of some battery swapping areas that have exhausted their batteries, have malfunctioned, or are not used for some reason is not predicted or is predicted to be the maximum value.

[0098] Here, for example, please refer to Figure 4 The steps for predicting the first waiting time required for the target object to travel from its current location to the battery swapping area in the first battery swapping station include the following steps 210 and 220.

[0099] 210. Input the first battery swapping parameters into the first trained machine learning model. The first battery swapping parameters include at least the location information of the battery swapping area in the first battery swapping station.

[0100] Of course, it is understood that in other embodiments, the first battery swapping parameter may also include any of the following: the number of battery swapping areas in the first battery swapping station, the time required for the target object to move from its current location to the battery swapping area, the number of vehicles waiting for battery swapping at the first battery swapping station, the battery swapping time required for vehicles currently swapping batteries at each battery swapping area in the first battery swapping station, and the number of batteries in stock at the first battery swapping station. For example, the first battery swapping parameter may be the location information of the battery swapping areas in the first battery swapping station and the time required for the target object to move from its current location to each battery swapping area. As another example, the first battery swapping parameter may be the location information of the battery swapping areas in the first battery swapping station, the time required for the target object to move from its current location to each battery swapping area, and the battery swapping time required for vehicles currently swapping batteries at each battery swapping area in the first battery swapping station. It is understood that the above does not provide all examples of the first battery swapping parameter, and the relevant examples in the embodiments of this application do not constitute an undue limitation on this application.

[0101] Here, the first post-training machine learning model can be a least squares support vector machine model, but this embodiment does not impose undue restrictions on it. Here, the first post-training machine learning model is a machine learning model that has already been trained and can output the first waiting time information based on the input first battery swapping parameters.

[0102] For example, the first post-trained machine learning model is trained using the following method. Here, a training set and a test set for the first post-trained machine learning model are provided, with no overlap between them. The training set is used to train the first post-trained machine learning model to adjust parameters based on the training results, while the test set is used to evaluate the predictive performance of the first post-trained machine learning model. The training set includes first battery swapping parameters and corresponding first waiting time information, while the test set includes other first battery swapping parameters and corresponding first waiting time information. The first waiting time information is the waiting time required for the target object to reach a battery swapping area for battery swapping, specifically including the time required for the target object to move to the corresponding battery swapping area and the time required to wait in the battery swapping area. After training the first post-trained machine learning model using the training set, the test set can be used to test the first post-trained machine learning model to evaluate its predictive results.

[0103] 220. Calculate the first waiting time information based on the first trained machine learning model.

[0104] As previously stated, the first post-training machine learning model has already been trained. Therefore, when in use, the first post-training machine learning model can output the first waiting time information based on the first battery swapping parameters input in the previous step 210.

[0105] Please refer to this again. Figure 1 After obtaining the first waiting time information, the following steps 300 can be performed.

[0106] 300. Based on the first waiting time information, provide the target driver with a recommended first battery swapping area.

[0107] For example, here, a recommended first battery swapping station can be provided to the target driver based on the length of the first waiting time information, i.e., the waiting time required to reach a battery swapping area. For instance, based on the first waiting time information, a ranking of battery swapping areas can be established from shortest to longest waiting time, and several battery swapping areas with shorter waiting times can be recommended to the user according to this ranking. Specifically, for example, the battery swapping area with the shortest waiting time can be selected as the recommended first battery swapping area and provided to the target driver. Of course, in other embodiments, multiple battery swapping areas can be provided as the recommended first battery swapping area; the example in this embodiment does not constitute an undue limitation.

[0108] Furthermore, in some embodiments, in addition to providing the user with a recommended first battery swapping area, a planned path from the target object's current location to the first battery swapping area can also be provided. Here, if the aforementioned pre-diversion area is set, the current location is the location of the pre-diversion area. Therefore, the server only needs to provide two geographically fixed locations, i.e., the planned path between the pre-diversion area and the first battery swapping area. Compared to obtaining the target object's location in real time and planning the path, this method requires less communication data transmission and less data processing because it does not require collecting the target object's real-time location. Of course, it is understood that in other embodiments, path planning can also be based on the target object's real-time location; the examples in this embodiment do not constitute an undue limitation.

[0109] Furthermore, it is understood that the embodiments of this application do not impose specific limitations on the path planning methods used. For example, they may employ sampling-based algorithms such as Rapid Random Tree Exploration (RRT), node-based optimal algorithms such as grid search, or methods based on mathematical modeling of the environment and system, such as linear algorithms and optimal control. In practical applications, they may use path planning methods employed in Baidu Maps and Gaode Maps, or directly perform path planning based on map software such as Baidu Maps and Gaode Maps. The examples in this embodiment do not constitute undue limitations.

[0110] Furthermore, due to insufficient battery quantity at the first battery swapping station or excessive queues of vehicles, the initial waiting time for the target may be excessively long. Therefore, in some embodiments, please refer to... Figure 5 When the first waiting time information meets a preset rule, steps 400-500 can be performed. The preset rule may be that the first waiting time information exceeds a preset threshold. Furthermore, steps 400-500 can be performed before or after step 300, and the examples in this application embodiment do not constitute an undue limitation.

[0111] 400. Predict the second waiting time information required for the target object to swap batteries from its current location to any swapping area in a second battery swapping station.

[0112] Here, the second battery swapping station is a battery swapping station other than the first battery swapping station. The number of second battery swapping stations can be one or more. The description of "a second battery swapping station" in step 400 of this application embodiment does not constitute a limitation on the number of second battery swapping stations.

[0113] For example, please refer to Figure 6Step 400 includes the following steps 410-420.

[0114] 410. Input the second battery swapping parameters into the second trained machine learning model. The second battery swapping parameters shall include at least the location information of the second battery swapping station.

[0115] Of course, it is understood that in other embodiments, the second battery swapping parameter may also include any of the following: the current remaining battery power of the target object, the time required for the target object to move from its current location to the second battery swapping station, the location information of the battery swapping area in the second battery swapping station, the number of battery swapping areas in the second battery swapping station, the number of vehicles waiting for battery swapping at each swapping point location of the second battery swapping station, and the number of batteries in stock at the second battery swapping station. For example, the second battery swapping parameter may be the location information of the second battery swapping station, the current remaining battery power of the target object, and the time required for the target object to move from its current location to the second battery swapping station; or, for example, the second battery swapping parameter may be the location information of the second battery swapping station, the number of vehicles waiting for battery swapping at each swapping point location of the second battery swapping station, and the number of batteries in stock at the second battery swapping station. It is understood that the above does not provide all examples of the second battery swapping parameter, and the relevant examples in the embodiments of this application do not constitute an undue limitation on this application.

[0116] Here, the second post-trained machine learning model can be a least squares support vector machine model, but this embodiment does not impose undue restrictions on it. In this context, the second post-trained machine learning model is a pre-trained machine learning model that can output the second waiting time information based on the input second battery swapping parameters.

[0117] For example, the second post-trained machine learning model is trained using the following method. Here, a training set and a test set for the second post-trained machine learning model are provided, with no overlap between them. The training set is used to train the second post-trained machine learning model to adjust parameters based on the training results, while the test set is used to evaluate the predictive performance of the second post-trained machine learning model. The training set includes second battery swapping parameters and corresponding second waiting time information, while the test set includes other second battery swapping parameters and corresponding second waiting time information. The second waiting time information refers to the waiting time required for the target object to swap batteries at a battery swapping area in a second battery swapping station. This waiting time specifically includes the sum of the time required for the target object to move to the corresponding battery swapping area and the time required to wait in that area. After training the second post-trained machine learning model using the training set, it can be tested using the test set to evaluate its predictive results.

[0118] 420. Calculate the second waiting time information based on the second trained machine learning model.

[0119] As mentioned above, the second post-training machine learning model has already been trained. Therefore, when in use, the second post-training machine learning model can output the second waiting time information by using the second battery swapping parameters input in the previous step 410.

[0120] Please refer to this again. Figure 5 After obtaining the first waiting time information, the following steps 500 can be performed.

[0121] 500. Based on the second waiting time information, provide the target driver with a recommended second battery swapping area.

[0122] For example, here, a recommended second battery swapping station can be provided to the target driver based on the length of the second waiting time information, i.e., the waiting time required to reach the battery swapping area in the second battery swapping station. For instance, based on the second waiting time information, a ranking of the waiting times of each battery swapping area in the second battery swapping station can be established from shortest to longest, and several battery swapping areas with shorter waiting times can be recommended to the user as second battery swapping areas according to this ranking. Specifically, for example, the battery swapping area with the shortest waiting time can be selected as the recommended second battery swapping area and provided to the target driver. Of course, in other embodiments, multiple battery swapping areas can also be provided as recommended second battery swapping areas, and the example in this embodiment does not constitute an undue limitation.

[0123] Here, users can choose whether to go to the first battery swapping area or the second battery swapping area for battery swapping. Therefore, this embodiment of the application can divert the target objects for battery swapping and provide users with better battery swapping solutions for them to choose from. This can reduce user waiting time, improve the user battery swapping experience, and also help to reasonably and evenly allocate resources among various battery swapping stations and areas, thereby improving the utilization rate of battery swapping stations and areas.

[0124] Application Examples

[0125] The following is a practical application example to better illustrate the content of this application.

[0126] Please see Figure 7 This section provides a schematic diagram of the first battery swapping station. The station has nine swapping compartments, each serving as a swapping location for vehicles requiring battery swapping. In addition to the swapping locations, the station also includes a manual swapping area and a pre-shunting area. The pre-shunting area can be located at the station's entrance.

[0127] Here, the first battery swapping station is also equipped with a server and a first communication module. A terminal can be installed at the target location, and the terminal is equipped with a second communication module. The first and second communication modules can communicate with each other to realize information exchange between the server and the terminal. The terminal can be a vehicle-mounted terminal or a mobile terminal held by the driver or passenger of the target location, such as a mobile phone, tablet, or laptop.

[0128] Here, an infrared sensor is installed in the pre-shunting area to detect whether a target object exists within the pre-shunting area. If the infrared sensor detects an object in the pre-shunting area, it sends a shooting request to the server. Upon receiving the request, the server issues a shooting command to the image acquisition device, which then captures an image of the target object's appearance and transmits the image back to the server.

[0129] Here, the server's acquisition unit further processes the appearance image into grayscale and uses the Canny edge detection operator to extract edge features to obtain the appearance features of the target object. The appearance features are then compared with the edge features of vehicles in the server's database. If the comparison result indicates that the target object is not a vehicle, a first alert is issued to remind staff that an anomaly exists in the pre-diversion area.

[0130] If the comparison result indicates that the target object is a vehicle, the server sends a ranging command to the ranging device. The ranging device responds to the command by measuring the target object within the pre-splitting area to obtain its length, width, and height parameters. The ranging device then transmits these parameters back to the server. The server's recognition unit (or image recognition module) extracts appearance features from the obtained image and size parameters using a trained network model, and performs vehicle type recognition using a classifier model to obtain the vehicle type information of the target object.

[0131] After obtaining the vehicle model information, it is queried and matched against preset vehicle model information in the preset database. Please refer to [link / reference]. Figure 9 If the query result is negative, it means that the target object is not a partner vehicle of the first battery swapping station. The server sends a second prompt message to the terminal, which is a message to guide the vehicle to leave the battery swapping station.

[0132] If the query result is yes, but the target object is found to have interference that could hinder the battery swapping operation based on the size parameters, the server sends a third prompt message to the terminal. Here, the third prompt message guides the vehicle to the manual battery swapping area.

[0133] If the query result is positive, and the size parameters indicate the absence of interfering objects, then the corresponding target status parameters are created for the target object and uploaded to the server. Please refer to [link / reference here]. Figure 10 The target status parameter is a unique identifier, including a first identifier, a second identifier, and a third identifier. The value of the first identifier indicates that the target object is in a battery swapping state (waiting for swapping), the value of the second identifier indicates that the target object is in a battery swapping process, and the value of the third identifier indicates that the target object is in a battery swapping completed state. Therefore, the number of target objects in each swapping state at the first battery swapping station can be counted using this target status parameter. For example, a target status parameter of 100 indicates that the target object is in a waiting-for-swap state. Of course, this example in the application documentation does not constitute an undue limitation on this application.

[0134] Here, the server's first prediction unit inputs the first battery swapping parameters into the first trained machine learning model. The first trained machine learning model then calculates the first waiting time information.

[0135] Here, the first post-training machine learning model adopts the least squares support vector machine model. The first battery swapping parameters include the location information of the battery swapping area in the first battery swapping station, the number of battery swapping areas in the first battery swapping station, the time required for the target object to move from its current location to the battery swapping area, the number of vehicles waiting for battery swapping at the first battery swapping station, the battery swapping time required for vehicles currently swapping batteries at each battery swapping area in the first battery swapping station, and the number of batteries in stock at the first battery swapping station.

[0136] Then, the server's recommendation unit provides the target driver with a recommended first battery swapping area based on the first waiting time information. For example, the battery swapping area corresponding to the shortest first waiting time is selected as the first battery swapping area and recommended to the user. For instance, the recommendation unit sends the first battery swapping area and the planned path from the pre-diversion area to the target's terminal.

[0137] Here, if the first waiting time information for all nine battery swapping areas in the first battery swapping station is relatively long, for example, if the first waiting time exceeds 30 minutes as a preset rule, then when this preset rule is met, the server's second prediction unit predicts the second waiting time information required for the target object to swap batteries from its current location to each battery swapping area in a second battery swapping station. It is understood that in the embodiments of this application, the first prediction unit and the second prediction unit can also be the same module unit, used to perform two functions, and the examples in this embodiment do not constitute an undue limitation.

[0138] The server's second prediction unit inputs the second battery swapping parameters into the second trained machine learning model to calculate the second waiting time information through the second trained machine learning model.

[0139] Here, the second post-trained machine learning model adopts the least squares support vector machine model. The second battery swapping parameters include the location information of the second battery swapping station, the current remaining battery power of the target object, the time required for the target object to move from its current location to the second battery swapping station, the location information of the battery swapping areas in the second battery swapping station, the number of battery swapping areas in the second battery swapping station, the number of vehicles waiting for battery swapping at each swapping point location of the second battery swapping station, and the number of batteries in stock at the second battery swapping station.

[0140] Then, the server's recommendation unit provides a recommended second battery swapping area to the target user's terminal based on the second waiting time information. For example, the battery swapping area corresponding to the second waiting time with the shortest waiting time is selected as the second battery swapping area and recommended to the user. For instance, the recommendation unit sends the second battery swapping area and the planned path from the pre-diversion area to the second battery swapping station to the target user's terminal.

[0141] To facilitate better implementation of the battery swapping location recommendation method provided in this application embodiment, this application embodiment also provides a battery swapping location recommendation device based on the above-described battery swapping location recommendation method. The meanings of the terms used are the same as in the above-described battery swapping location recommendation method, and specific implementation details can be found in the description of the method embodiment.

[0142] Please see Figure 11 , Figure 11 This application provides a structural block diagram of a battery swapping location recommendation device, which includes:

[0143] The acquisition unit is used to acquire the appearance features and size parameters of the target object;

[0144] The recognition unit is used to identify the vehicle type of the target object based on its appearance features and size parameters.

[0145] The first prediction unit is used to predict the first waiting time information required for the target object to go from its current location to the battery swapping area in a first battery swapping station for battery swapping.

[0146] The recommendation unit is used to provide the target driver with a recommended first battery swapping area based on the first waiting time information.

[0147] In some embodiments, a pre-diversion area is provided at the first battery swapping station. The acquisition unit includes an image acquisition device and a ranging device provided in the pre-diversion area. The image acquisition device is used to acquire an appearance image of the target object, and the appearance image is used to extract appearance features. The ranging device is used to acquire the size parameters of the target object.

[0148] In some embodiments, please refer to Figure 12The device also includes a second prediction unit, which is used to predict the second waiting time information required for the target object to go from its current location to the battery swapping area in a second battery swapping station for battery swapping; the recommendation unit is also used to provide the target object's driver user with a recommended second battery swapping area based on the second waiting time information.

[0149] Here, this application discloses a battery swapping location recommendation device, which is used to: acquire feature information of a target object, and query and match the feature information of the target object in a preset database; predict the first waiting time information required for the target object to swap batteries from its current location to any battery swapping area in a first battery swapping station based on the query and matching results; and provide a recommended first battery swapping area to the driver of the target object based on the first waiting time information.

[0150] Accordingly, embodiments of this application also provide a computer device, which can be a server. For example... Figure 13 As shown, Figure 13 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. The computer device 1300 includes a processor 1301 with one or more processing cores, a memory 1302 with one or more computer-readable storage media, and a computer program stored on the memory 1302 and executable on the processor. The processor 1301 and the memory 1302 are electrically connected. Those skilled in the art will understand that the computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0151] The processor 1301 is the control center of the computer device 1300. It connects various parts of the computer device 1300 through various interfaces and lines. By running or loading software programs and / or modules stored in the memory 1302, and calling data stored in the memory 1302, it performs various functions of the computer device 1300 and processes data, thereby monitoring the computer device 1300 as a whole.

[0152] In this embodiment, the processor 1301 in the computer device 1300 loads the instructions corresponding to the processes of one or more applications into the memory 1302 according to the following steps, and the processor 1301 runs the applications stored in the memory 1302 to achieve various functions: obtaining the feature information of the target object, and querying and matching the feature information of the target object in a preset database; predicting the first waiting time information required for the target object to swap batteries from its current location to any battery swapping area in a first battery swapping station based on the query and matching results; and providing the target object's driver with a recommended first battery swapping area based on the first waiting time information.

[0153] It is understood that the computer device 1300 may also include other structures electrically connected to the processor 1301, such as an input unit, a display screen, a power supply, etc. The examples in this embodiment do not constitute an undue limitation on this application.

[0154] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0155] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0156] As can be seen from the above, the computer device provided in this embodiment acquires the feature information of the target object and performs query matching on the feature information of the target object in a preset database; based on the query matching result, it predicts the first waiting time information required for the target object to swap batteries from its current location to any battery swapping area in a first battery swapping station; and based on the first waiting time information, it provides the driver of the target object with a recommended first battery swapping area.

[0157] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0158] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of computer programs that can be loaded by a processor to execute steps in any of the battery swapping location recommendation methods provided in embodiments of this application. For example, the computer program can execute the following steps:

[0159] The system acquires the feature information of the target object and performs a query and matching operation on the feature information of the target object in a preset database. Based on the query and matching results, it predicts the first waiting time information required for the target object to go from its current location to any battery swapping area in a first battery swapping station for battery swapping. Based on the first waiting time information, it provides the target object's driver with a recommended first battery swapping area.

[0160] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0161] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0162] Since the computer program stored in the storage medium can execute the steps in any of the battery swapping location recommendation methods provided in the embodiments of this application, the beneficial effects that any of the battery swapping location recommendation methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0163] It is understood that the terms used in the various embodiments of this application have the same meaning. For any content not described in detail in a particular embodiment, the specific implementation details can be found in the descriptions in other embodiments. The examples and technical effects shown in the foregoing embodiments can be implemented accordingly. For repeated parts, this embodiment will not elaborate further.

[0164] The foregoing has provided a detailed description of the method, apparatus, equipment, and storage medium for recommending battery swapping locations for battery swapping stations. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for recommending battery swapping locations for battery swapping stations, characterized in that, The method includes: Obtain the feature information of the target object, and query and match the feature information of the target object in a preset database; Based on the query matching results, predict the first waiting time information required for the target object to swap batteries from its current location to any swapping area in a first battery swapping station; Based on the first waiting time information, a recommended first battery swapping area is provided to the target driver. When the first waiting time information conforms to a preset rule, the second battery swapping parameter is input into the second trained machine learning model. Based on the second trained machine learning model, the second waiting time information required for the target object to swap batteries from its current location to any battery swapping area in a second battery swapping station is predicted. The second battery swapping parameter includes the location information of the second battery swapping station, and also includes any of the following: the target object's current remaining battery power, the time required for the target object to move to the second battery swapping station, the location information of the battery swapping areas in the second battery swapping station, the number of battery swapping areas in the second battery swapping station, the number of vehicles waiting for battery swapping at the second battery swapping station, and the number of batteries in stock at the second battery swapping station. Based on the second waiting time information, a recommended second battery swapping area is provided to the target driver.

2. The method for recommending battery swapping locations for battery swapping stations as described in claim 1, characterized in that, The feature information includes the appearance features and size parameters of the target object. The method for querying and matching the feature information of the target object includes: identifying the vehicle model of the target object based on the appearance features and the size parameters, and querying and matching the result of the vehicle model identification with a preset vehicle model in a preset database.

3. The method for recommending battery swapping locations for battery swapping stations as described in claim 2, characterized in that, A pre-diversion area is set up at the first battery swapping station. The step of obtaining the feature information of the target object is performed in the pre-diversion area. The current position is the location of the pre-diversion area.

4. The method for recommending battery swapping locations for battery swapping stations as described in claim 2, characterized in that, The steps for obtaining the appearance features of the target object include: Obtain the appearance image of the target object; The appearance image is converted to grayscale, and edge features are extracted using the Canny edge detection operator to obtain the appearance features; and / or, The dimensional parameters include vehicle length, width, and height. A pre-diversion area is provided at the first battery swapping station. Based on a first ranging device set along the length direction in the pre-diversion area, the vehicle length parameters of the target object are obtained; Based on a second ranging device set along the width direction in the pre-diversion area, the vehicle width parameters of the target object are obtained; Based on a third ranging device positioned along the height direction in the pre-diversion area, the vehicle height parameters of the target object are obtained; and / or, The steps for vehicle model recognition of the target object include: The appearance image of the target object is input into the trained network model; Based on the trained network model, the appearance features of the appearance image are obtained; The appearance features and the size parameters are input into the trained classifier model; Based on the trained classifier model, identify the vehicle model information of the target object; and / or, The method further includes the following steps: Based on the appearance features, determine whether the target object is a vehicle. If the target object is not a vehicle, issue a first prompt message. If the target object is a vehicle, obtain the size parameters of the target object and perform vehicle type recognition. If the vehicle model identification result does not meet a preset condition, a second prompt message will be issued; If the vehicle model identification result indicates the presence of interference, a third prompt message will be issued; and / or, After the query matching results meet a preset condition, a corresponding target state parameter is established for the target object. The target state parameter is used to characterize the current battery swapping state of the target object, including waiting for battery swapping, battery swapping in progress, and battery swapping completed; and / or, The step of predicting the first waiting time information required for the target object to travel from its current location to the battery swapping area in the first battery swapping station for battery swapping includes: The first battery swapping parameter is input into the first trained machine learning model. The first battery swapping parameter includes the location information of the battery swapping area in the first battery swapping station. The first battery swapping parameter also includes any of the following: the number of battery swapping areas in the first battery swapping station, the time required for the target object to move from its current location to the battery swapping area, the number of vehicles waiting for battery swapping at the battery swapping area in the first battery swapping station, the battery swapping time required for the vehicle currently swapping batteries in the first battery swapping station, and the number of batteries in stock at the first battery swapping station. The first waiting time information is calculated based on the first trained machine learning model.

5. A battery swapping location recommendation device for a battery swapping station, characterized in that, include, The acquisition unit is used to acquire the appearance features and size parameters of the target object; A recognition unit is used to identify the vehicle type of the target object based on the appearance features and the size parameters. The first prediction unit is used to predict the first waiting time information required for the target object to go from its current location to the battery swapping area in a first battery swapping station for battery swapping. The second prediction unit is used to input the second battery swapping parameters into the second trained machine learning model when the first waiting time information meets a preset rule, and predict the second waiting time information required for the target object to swap batteries from its current location to any battery swapping area in a second battery swapping station based on the second trained machine learning model; the second battery swapping parameters include the location information of the second battery swapping station, and also include any of the following: the current remaining battery power of the target object, the time required for the target object to move to the second battery swapping station, the location information of the battery swapping areas in the second battery swapping station, the number of battery swapping areas in the second battery swapping station, the number of vehicles waiting for battery swapping at the second battery swapping station, and the number of batteries in stock at the second battery swapping station; The recommendation unit is used to provide a recommended first battery swapping area to the driver of the target object based on the first waiting time information; Based on the second waiting time information, a recommended second battery swapping area is provided to the target driver.

6. The battery swapping location recommendation device for a battery swapping station as described in claim 5, characterized in that, A pre-diversion area is set up at the first battery swapping station. The acquisition unit includes an image acquisition device and a ranging device set in the pre-diversion area. The image acquisition device is used to acquire the appearance image of the target object, and the appearance image is used to extract the appearance features. The ranging device is used to acquire the size parameters of the target object.

7. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method for recommending battery swapping locations for a battery swapping station as described in any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a plurality of instructions adapted for loading by a processor to execute the battery swapping location recommendation method for a battery swapping station as described in any one of claims 1 to 4.

Images