Battery swapping station queue number determination method and device, and reservation system

Abstract

Embodiments of the present application disclose a battery swap station queue number determination method, device and reservation system. The method comprises obtaining the queue number of a current time period; obtaining battery swap reservation information, the battery swap reservation information comprising a plurality of battery swap orders, each battery swap order comprising a reserved battery swap time, a reserved battery swap station identifier and a battery swap vehicle model; inputting the queue number of the current time period and the battery swap reservation information into a pre-trained prediction model for processing to determine the queue number of a future time period, the prediction model being determined based on historical battery swap information corresponding to historical battery swap orders of the battery swap station in different time periods. Thus, the embodiments can predict the queue situation of the battery swap station in the future time period and automatically determine the queue number of the battery swap station, thereby improving the battery swap experience and satisfaction.

Description

Technical Field

[0001] This invention relates to the field of battery swapping station technology, specifically to a method, apparatus, and reservation system for determining the number of people queuing at a battery swapping station. Background Technology

[0002] With the increasing popularity of electric vehicles, battery swapping stations, as a crucial facility for rapid range extension, are receiving growing attention from users for their efficiency and service quality. In daily operations, battery swapping stations frequently face the problem of users queuing for swaps, especially during peak hours, where the length of the queue directly impacts user experience and satisfaction. Summary of the Invention

[0003] In view of this, the purpose of this invention is to provide a method, apparatus and reservation system for determining the number of people queuing at a battery swapping station, so as to automatically determine the number of people queuing at a battery swapping station.

[0004] In a first aspect, embodiments of the present invention aim to provide a method for determining the number of people queuing at a battery swapping station, the method comprising:

[0005] Get the number of people in the queue for the current time period;

[0006] Obtain battery swap reservation information, which includes multiple battery swap orders, and each battery swap order includes the reserved battery swap time, the reserved battery swap station identifier, and the battery swap vehicle model;

[0007] The queue number for the current time period and the battery swapping reservation information are input into a pre-trained prediction model for processing to determine the queue number for future time periods. The prediction model is trained and determined based on historical battery swapping information corresponding to historical battery swapping orders at the battery swapping station in different time periods.

[0008] Furthermore, the historical battery swapping information includes the number of battery swapping orders, the number of scheduled battery swapping orders, the number of unscheduled battery swapping orders, the battery swapping duration, the battery swapping vehicle model, and the number of people in the queue.

[0009] Furthermore, the prediction model is determined based on the following method:

[0010] Obtain historical battery swapping information for different time periods;

[0011] The historical battery swapping information is preprocessed and feature-engineered to determine sample data, which includes a training set, a validation set, and a test set.

[0012] The training set is used to iteratively train the preset prediction model;

[0013] The output of the prediction model after iterative training is validated using the validation set.

[0014] The performance of the validated prediction model is evaluated using the test set.

[0015] Furthermore, the preprocessing and feature engineering of each of the historical battery swapping information to determine the sample data includes:

[0016] The historical battery swapping information is preprocessed to determine the first feature data. The preprocessing includes data cleaning, format conversion and / or standardization.

[0017] The first feature data is subjected to feature engineering processing to determine the second feature data, which includes time period label, average battery swapping time and reservation order ratio.

[0018] The first feature data and the second feature data corresponding to each of the historical battery swapping information are integrated to generate sample data.

[0019] Secondly, embodiments of the present invention aim to provide a method for determining the queue size at a battery swapping station, the method comprising:

[0020] Send a battery swapping order, which includes the scheduled battery swapping time, the identifier of the scheduled battery swapping station, and the vehicle model to be swapped.

[0021] The system receives and displays the queue number for the target time period to which the battery swapping order belongs. The queue number is determined by processing the battery swapping reservation information corresponding to the battery swapping order within the target time period and the queue number for the current time period using a pre-trained prediction model. The prediction model is trained and determined based on the historical battery swapping information corresponding to historical battery swapping orders at the battery swapping station in different time periods.

[0022] Thirdly, embodiments of the present invention aim to provide a battery swapping station reservation system, the system comprising:

[0023] At least one user terminal is configured to send a battery swapping order, the battery swapping order including a scheduled battery swapping time, a scheduled battery swapping station identifier, and a battery swapping vehicle model; and to receive and display the queue number for the target time period to which the battery swapping order belongs;

[0024] The server is configured to: obtain the queue count for the current time period; obtain battery swapping reservation information, which includes multiple battery swapping orders; input the queue count for the current time period and the battery swapping reservation information into a pre-trained prediction model for processing to determine the queue count for future time periods; and send the queue count for each battery swapping order corresponding to a target time period to the corresponding terminal; wherein the prediction model is trained and determined based on historical battery swapping information corresponding to historical battery swapping orders at the battery swapping station in different time periods, and the future time periods include the target time periods.

[0025] Fourthly, embodiments of the present invention aim to provide a device for determining the number of queues at a battery swapping station, the device comprising:

[0026] The acquisition unit is used to acquire the number of queues in the current time period; acquire battery swapping reservation information, which includes multiple battery swapping orders, and each battery swapping order includes the reserved battery swapping time, the reserved battery swapping station identifier, and the battery swapping vehicle model;

[0027] The processing unit is used to input the queue number of the current time period and the battery swap reservation information into a pre-trained prediction model for processing, and to determine the queue number of the future time period. The prediction model is trained and determined based on the historical battery swap information corresponding to the historical battery swap orders of the battery swap station in different time periods.

[0028] Fifthly, embodiments of the present invention aim to provide a device for determining the number of queues at a battery swapping station, the device comprising:

[0029] A sending unit is used to send a battery swapping order, which includes the scheduled battery swapping time, the identifier of the scheduled battery swapping station, and the vehicle model to be swapped.

[0030] The display unit is used to receive and display the queue number of the target time period to which the battery swapping order belongs. The queue number is determined by processing the battery swapping reservation information corresponding to the battery swapping order in the target time period and the queue number in the current time period through a pre-trained prediction model. The prediction model is trained and determined based on the historical battery swapping information corresponding to the historical battery swapping orders in different time periods of the battery swapping station.

[0031] Sixthly, embodiments of the present invention aim to provide a computer program product, the computer program product including a computer program / instruction, which, when executed by a processor, implements the method as described in any of the preceding claims.

[0032] In a seventh aspect, embodiments of the present invention aim to provide an electronic device, including a memory and a processor, the memory being used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in any of the preceding claims.

[0033] Eighthly, embodiments of the present invention aim to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the preceding claims.

[0034] The technical solution of this invention trains a prediction model based on historical battery swapping information corresponding to historical battery swapping orders at battery swapping stations in different time periods. After obtaining the queue count and battery swapping reservation information for the current time period, the model is input into the pre-trained prediction model for processing to determine the queue count for future time periods. This allows for the prediction of queuing conditions at battery swapping stations in future time periods, automatically determining queue counts and thus improving the battery swapping experience and satisfaction. Furthermore, by utilizing the queue count information for the current time period and real-time battery swapping reservation information for future time periods to determine the queue count for future time periods, the accuracy of the determined queue count for future time periods can be improved, further enhancing the user's battery swapping experience and satisfaction. Attached Figure Description

[0035] The above and other objects, features and advantages of the present invention will become clearer from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0036] Figure 1 This is a schematic diagram of the battery swapping reservation system according to an embodiment of the present invention;

[0037] Figure 2 This is a flowchart of the method for determining the queue size of a battery swapping station according to an embodiment of the present invention;

[0038] Figure 3 This is a flowchart illustrating the determination of the prediction model according to an embodiment of the present invention;

[0039] Figure 4 This is a flowchart illustrating the process of determining sample data according to an embodiment of the present invention;

[0040] Figure 5 This is a structural diagram of the prediction model according to an embodiment of the present invention;

[0041] Figure 6 This is another flowchart of the method for determining the queue size of a battery swapping station according to an embodiment of the present invention;

[0042] Figure 7 This is a schematic diagram of the battery swapping station queue number determination device according to an embodiment of the present invention;

[0043] Figure 8 This is another schematic diagram of the battery swapping station queue number determination device according to an embodiment of the present invention;

[0044] Figure 9 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0045] The present application is described below based on embodiments, but it is not limited to these embodiments. In the detailed description of the present application below, certain specific details are described in detail. Those skilled in the art can fully understand the present application without these details. To avoid obscuring the substance of the present application, well-known methods, processes, flows, elements, and circuits are not described in detail.

[0046] Furthermore, those skilled in the art should understand that the accompanying drawings provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0047] Unless the context explicitly requires it, words such as "including" or "contains" throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, meaning "including but not limited to".

[0048] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0049] The solutions described in this specification and embodiments, if involving information acquisition, will collect data under legal and compliant conditions, ensuring the legality of the data source, and will take appropriate technical and management measures to ensure data security. If involving personal information processing, processing will be carried out under legal grounds (e.g., obtaining the consent of the personal information subject, or being necessary for contract performance), and will only be conducted within the prescribed or agreed scope. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.

[0050] With the widespread use of battery swapping stations, users often face queuing when swapping batteries, and the length of the queue directly impacts their swapping experience and satisfaction. Therefore, this invention aims to provide a method for determining the queue length at battery swapping stations. This method automates the determination of queue lengths, allowing users to know the queue length before arriving at the station, providing decision-making information for choosing a suitable station and thus improving the user's battery swapping experience.

[0051] Figure 1 This is a schematic diagram of a battery swapping reservation system according to an embodiment of the present invention. Figure 1 As shown, the battery swapping reservation system in this embodiment includes a server 1 and at least one terminal 2. The server 1 and the terminal 2 are interconnected via a network 3 to achieve information and data exchange. It should be understood that... Figure 1 The image shows only a certain number of terminals, but this does not mean that the number of terminals is limited.

[0052] Server 1 should be understood as a device that provides data management, database, and communication facilities for providing battery swapping reservation and order management services. For example, Server 1 can refer to a single physical server with associated communication, data storage, and database facilities, or it can refer to a networked or aggregated collection of processors, associated networks, and storage devices, operating software and one or more database systems and application software that support the services provided by the server. The server can be a monolithic server or a distributed server spanning multiple computers or computer data centers, or it can be various types of cloud servers. In some embodiments, each server may include hardware, software, or embedded logical components for performing suitable functions supported or implemented by the server, or a combination of two or more such components.

[0053] Terminal 2 is a communication terminal capable of running computer programs. These communication terminals can be mobile phones, tablets, PDAs, wearable devices, or other terminal devices. Terminal 2 has a communication module, including at least one remote communication module, such as a communication circuit for WLAN, GPRS, or 2G / 3G / 4G / 5G remote communication. Terminal 2 also has a display device and an input device. The display device can be a liquid crystal display, an LED display, or a projection device. The input device can include, for example, a touchscreen, buttons, a pressure sensor, etc. Terminal 2 receives user commands through the input device and interacts with relevant personnel through the display device.

[0054] When making a battery swap reservation, each user submits their reservation information to server 1 through a battery swap reservation application (including an app or mini-program) on their corresponding terminal 2, checks the queue length of their order at a battery swap station, and then goes to the station to perform the swap. Server 1 receives battery swap orders from different users, estimates the queue length at each station based on the received reservation information, and sends the queue length for each order to the corresponding terminal. This allows users to know the queue length at each station in advance on their terminals, providing decision-making information for choosing a battery swap station, thus facilitating the selection of a suitable station and improving the battery swap experience and satisfaction.

[0055] In this embodiment, the determination of the queue size of one battery swapping station is used as an example. However, it should be understood that when it is necessary to determine the queue size of multiple battery swapping stations, the same method can be used to determine the queue size of each battery swapping station.

[0056] Figure 2 This is a flowchart of a method for determining the queue size of a battery swapping station according to an embodiment of the present invention. Figure 2 As shown, the method for determining the number of battery swapping stations in this embodiment is applied to the server and specifically includes the following steps.

[0057] In step S210, the number of queues for the current time period is obtained.

[0058] In this embodiment, the current time period is the time period preceding the time period corresponding to the time period for which the queue number of the battery swapping station to be determined is to be determined. The queue number in the current time period can be the actual queue number of the battery swapping station determined based on the current queue situation, or it can be the queue number of the battery swapping station determined by a pre-trained prediction model.

[0059] Optionally, when the current time period is the initial time (i.e., the moment when the pre-trained prediction model begins to determine the queue size of the battery swapping station), the queue size in this embodiment is the actual queue size of the battery swapping station determined based on the current queue situation. When the current time period is after the initial time, since the pre-trained prediction model stores information related to the battery swapping queue size for historical time periods, the queue size in this embodiment can be either the actual queue size of the battery swapping station determined based on the current queue situation, or the queue size of the battery swapping station determined by the pre-trained prediction model.

[0060] Furthermore, when the queue number for the current time period is the actual queue number of the battery swapping station determined based on the current queue situation, since vehicles need to enter the gate of the battery swapping station before swapping, this embodiment can determine the queue number based on the number of battery swapping orders where the vehicle's entry time is within the current time period and the time interval between the entry time and the start time of battery swapping is greater than a preset duration. Specifically, this embodiment first determines the battery swapping orders where the vehicle's entry time (i.e., the time the vehicle enters the gate) is within the current time period; then, it calculates the battery swapping orders within the current time period whose time interval between the entry time and the start time of battery swapping (i.e., the start time of battery swapping) is greater than a preset duration (e.g., 10 minutes); finally, the total number of all battery swapping orders is determined as the queue number for the current time period. This avoids interference from unregistered users on the estimated queue number, determines a more accurate queue number for the current time period, and thus improves the accuracy of the estimated queue number.

[0061] In step S220, battery swap reservation information is obtained. The battery swap reservation information includes multiple battery swap orders. Each battery swap order includes the reserved battery swap time, the reserved battery swap station identifier, and the battery swap vehicle model.

[0062] In this embodiment, the battery swapping reservation information can be all reserved battery swapping orders received by the server for the current battery swapping station. Reservation orders for different battery swapping stations can be determined based on the reserved battery swapping station identifier in the order. Furthermore, all battery swapping orders for the current station can be battery swapping orders for all future time periods after the current time period, or all battery swapping orders for future time periods with reservation times in the next time period after the current time period. All battery swapping orders corresponding to each time period can be determined based on the reserved battery swapping time in the order.

[0063] In step S230, the queue number and battery swap reservation information for the current time period are input into the pre-trained prediction model for processing to determine the queue number for the future time period. The prediction model is trained and determined based on the historical battery swap information corresponding to the historical battery swap orders of the battery swap station in different time periods.

[0064] In this embodiment, to improve the accuracy of the determined queue size, when predicting the queue size of battery swapping stations in future time periods after the current time period, the queue size in the current time period and the battery swapping reservation information for the next time period (i.e., the future time period closest to the current time period) are used to determine the queue size in the next time period. Therefore, this embodiment can use the queue size in the most recent future time period and more real-time battery swapping reservation information within the future time period to determine the queue size in the future time period, thus improving the accuracy of the determined queue size for the future time period.

[0065] Optionally, to ensure that the data input into the prediction model is high-quality, uniformly formatted, and suitable for model processing, in this embodiment, after the queue number for the current time period is the actual queue number of the battery swapping station determined based on the current queue situation and the battery swapping reservation information for the future time period is obtained, the queue number and battery swapping reservation information for the current time period will be preprocessed first, and then the preprocessed queue number and battery swapping reservation information for the current time period will be input into the pre-trained prediction model for processing to determine the queue number for the future time period.

[0066] Optionally, the preprocessing operations in this embodiment include data cleaning, format conversion, and / or standardization. Data cleaning removes information lacking key data, duplicates, or containing outliers to ensure data quality. Format conversion transforms the data into a format unsuitable for the model's input, such as converting the date and time in a battery swapping appointment to a timestamp format so the model can process time-series data. Standardization uses the Z-core method (i.e., subtracting the mean and dividing by the standard deviation) or other standardization methods to ensure that each data feature has the same influence in the model's internal processing.

[0067] Optionally, the prediction model in this embodiment can employ an LSTM model or other types of time series processing models to estimate the queuing length at battery swapping stations based on historical battery swapping information and real-time reservation information. Furthermore, this embodiment preferentially uses an LSTM model for prediction; however, it should be understood that a suitable prediction model can be selected based on the specific application scenario. The examples provided here are merely illustrative and do not limit the type of prediction model.

[0068] Figure 3This is a flowchart illustrating the determination of the prediction model in an embodiment of the present invention. For example... Figure 3 As shown, the prediction model is determined in this embodiment using the following method.

[0069] In step S310, historical battery swapping information for different time periods is obtained.

[0070] In this embodiment, historical battery swapping information includes information affecting the number of battery swapping orders, the number of reserved battery swapping orders, the number of unreserved battery swapping orders, the battery swapping duration, the battery swapping vehicle models, the number of queues, and the maximum capacity of the battery swapping station. The number of queues represents the actual number of queues for a given time period, which can be determined based on the number of battery swapping queue orders where the vehicle's entry time falls within the corresponding time period and the time interval between the entry time and the start time of the battery swapping is greater than a preset duration.

[0071] Optionally, when acquiring historical battery swapping information, this embodiment first acquires battery swapping orders from different historical time periods, then analyzes the information of each order to determine the historical battery swapping information for each time period. The battery swapping orders can be pre-booked or unbooked orders that directly enter the battery swapping station. The information in a battery swapping order includes the vehicle model, station identifier, entry time, start time, end time, and departure time. For pre-booked orders, in addition to the aforementioned information, the order information also includes the pre-booked swapping time, station identifier, and vehicle model.

[0072] In step S320, the historical battery swapping information is preprocessed and feature engineering is performed to determine the sample data, which includes the training set, validation set and test set.

[0073] In this embodiment, after obtaining historical battery swapping information for different time periods, sample data for training the prediction model is determined by preprocessing and feature engineering of each historical battery swapping information.

[0074] Figure 4 This is a flowchart illustrating the process of determining sample data according to an embodiment of the present invention. Figure 4 As shown, sample data is determined in this embodiment using the following method.

[0075] In step S410, the historical battery swapping information is preprocessed to determine the first characteristic data. The preprocessing includes data cleaning, format conversion, and / or standardization.

[0076] In step S420, feature engineering is performed on the first feature data to determine the second feature data, which includes time period labels, average battery swapping duration, and the percentage of pre-orders.

[0077] In this embodiment, the time period label is used to indicate whether the corresponding time period is a peak or off-peak period. The average battery swapping time is used to indicate the average battery swapping time of the corresponding time period at the battery swapping station. The reserved order percentage is used to indicate the percentage of reserved battery swapping orders in all battery swapping orders within the corresponding time period.

[0078] Optionally, in this embodiment, the time period label can be determined based on the busy / idle status of the battery swapping station in each time period according to historical time cycles (such as the past 7 days), which can be determined based on the number of battery swapping orders. For example, when the number of battery swapping orders in a time period reaches a preset threshold, the time period label is determined to be a peak period; and when the number of battery swapping orders in a time period does not reach the preset threshold, the time period label is determined to be an off-peak period.

[0079] Optionally, in determining the proportion of reserved orders, this embodiment automatically adds a reservation tag to battery swap orders that users had reserved before the swap. Then, the ratio of the number of battery swap orders with reservation tags to the total number of battery swap orders is calculated as the proportion of reserved orders for the corresponding time period. This allows for a more accurate estimation of the actual offline queue size using the proportion of reserved orders.

[0080] In step S430, the first feature data and the second feature data corresponding to each historical battery swapping information are integrated to generate sample data.

[0081] Therefore, in this embodiment, sample data is determined by preprocessing and feature engineering the acquired historical battery swapping information, so that the sample data can include more feature data related to the number of queues, thereby improving the accuracy of the prediction model determined based on the sample data, and thus improving the accuracy of the number of queues at the battery swapping station determined by the prediction model.

[0082] In this embodiment, after determining the sample data, the sample data will be randomly divided into training set, validation set and test set according to a certain proportion.

[0083] In step S330, the preset prediction model is iteratively trained using the training set.

[0084] Figure 5 This is a structural diagram of the prediction model according to an embodiment of the present invention. Figure 5 As shown, the prediction model in this embodiment is an LSTM model, including a forget gate 51, an input gate 52, and an output gate 53. The input to the forget gate 51 includes the queue size h for the current time period. t-1 Battery swapping reservation information for the next time period (i.e., the future time period) x t The output f of the forget gate is obtained through the activation function σ. t f tThis represents the probability of forgetting long-term memories from the current time period. The input to gate 52 consists of two parts; one part uses the activation function σ, and the output is i. t The other part uses the activation function tanh; then the outputs of the two parts are multiplied before updating the long-term memory for the current time period. Thus, the long-term memory c for the future time period is obtained. t Long-term memory of the future time period c t It consists of two parts. The first part is the long-term memory of the current time period. t-1 And the Forgotten Gate 51 output f t The first part is the product of the two parts of the output from input gate 52. Finally, in output gate 53, one part uses the activation function σ to calculate the queue size h for the current time period. t-1 Battery swapping appointment information for future time periods x t The process involves processing the data to obtain the corresponding output; another step involves using the activation function tanh to activate the long-term memory c for future time periods. t The process is performed to obtain the corresponding output; finally, the two outputs are multiplied together to obtain the queue length h for the future time period. t .

[0085] In this embodiment, when iteratively training a preset prediction model using a training set, in each iteration step, a batch of data is input into the prediction to calculate the value of the loss function, and the weights and biases of the model are updated through the backpropagation algorithm and the optimizer.

[0086] Optionally, in this embodiment, the mean squared error function (MSE) is selected to measure the difference between the number of queues predicted by the model and the actual number of queues for battery swapping, and stochastic gradient descent (SGD) or Adam is selected as the optimizer to adjust the model's weights and configuration.

[0087] In step S340, the output of the prediction model after iterative training is validated using a validation set.

[0088] In this embodiment, after iterative training, the data in the validation set is input into the prediction model for processing, and the estimated queue size for the corresponding input data is obtained. Then, the validation result of the prediction model is determined by calculating the difference between the estimated queue size output by the model under the input data and the actual queue size corresponding to that input data, as well as the proportion of sample data with a difference less than a preset difference in the total sample data of the validation set. This validation result is used to verify the model's prediction accuracy. The smaller the difference and the higher the proportion of sample data with a difference less than the preset difference in the total sample data of the validation set, the higher the accuracy of the queue size predicted by the prediction model.

[0089] Furthermore, if the validation results of the prediction model show that the model's prediction accuracy does not meet the preset conditions, such as a large difference between the predicted queue number and the actual queue number, or the proportion of accurate predictions in the total number of predictions not reaching the preset number, necessary adjustments will be made to the prediction model parameters, such as optimizing the learning rate, to improve the model's prediction performance. Afterwards, the prediction model will continue to be iteratively trained until the prediction accuracy meets the preset conditions.

[0090] In step S350, the performance of the validated prediction model is evaluated using a test set.

[0091] In this embodiment, after the prediction accuracy of the prediction model reaches the preset condition, the generalization ability of the prediction model will be evaluated using a test set to determine whether the prediction model can achieve the expected effect in practical applications.

[0092] Optionally, in this embodiment, evaluation metrics such as mean squared error (MSE), mean absolute error (MAE), and root mean square error (RMSE) can be used to evaluate the performance of the prediction model. This allows the better-performing prediction model after evaluation to be applied to predicting queue lengths at battery swapping stations.

[0093] Therefore, in this embodiment, by acquiring historical battery swapping information for different time periods, preprocessing and feature engineering the historical battery swapping information, determining sample data, using the training set in the sample data to iteratively train the preset prediction model, using the validation set in the sample data to verify the output results of the iteratively trained prediction model, and using the test set in the sample data to evaluate the performance of the verified prediction model, a prediction model with high prediction accuracy and more reliable prediction results can be trained. This enables the subsequent use of the trained prediction model to automatically and accurately determine the queuing number of battery swapping stations.

[0094] Furthermore, in this embodiment, after the trained prediction model is applied to determine the number of queues, the number of queues corresponding to each battery swap order will be sent to the user so that the user can know the battery swap queue status in advance and provide battery swap guidance to the user.

[0095] Optionally, in this embodiment, the prediction model will be continuously optimized based on user battery swapping feedback information after the model is applied, so as to continuously improve the performance of the prediction model and the accuracy of queuing number prediction.

[0096] The technical solution of this embodiment trains and determines a prediction model based on historical battery swapping information corresponding to historical battery swapping orders at the battery swapping station in different time periods. After obtaining the queue number and battery swapping reservation information for the current time period, the queue number and the battery swapping reservation information for the current time period are input into the pre-trained prediction model for processing to determine the queue number for the future time period. This enables the prediction of the queuing situation of the battery swapping station in the future time period and automatically determines the queue number of the battery swapping station, thereby improving the battery swapping experience and satisfaction.

[0097] Figure 6 This is another flowchart of the method for determining the queue size of a battery swapping station according to an embodiment of the present invention. For example... Figure 6 As shown, the terminal in this embodiment determines the queue number of the battery swapping station through the following method, which specifically includes the following steps.

[0098] In step S610, a battery swapping order is sent, which includes the scheduled battery swapping time, the identifier of the scheduled battery swapping station, and the vehicle model to be swapped.

[0099] In this embodiment, when a user needs to swap batteries, the terminal receives the battery swap reservation information input by the user and generates a corresponding battery swap order, which is then sent to the server.

[0100] In step S620, the queue number of the battery swapping order to which the target time period belongs is received and displayed. The queue number is determined by processing the battery swapping reservation information corresponding to the battery swapping order in the target time period and the queue number in the current time period through a pre-trained prediction model. The prediction model is trained and determined based on the historical battery swapping information corresponding to the historical battery swapping orders in different time periods of the battery swapping station.

[0101] In this embodiment, after receiving a battery swap order from a user, the server determines the number of battery swap queues for the target time period to which the scheduled battery swap time in the order belongs, based on the method described above, and sends this number of queues to the corresponding terminal. The terminal receives the queue number for the corresponding battery swap order and displays it to the user on the terminal's display page.

[0102] Optionally, to facilitate users' quick selection of battery swapping stations, this embodiment can automatically display nearby (within a certain distance) and / or historically used battery swapping stations, along with their queue numbers, even when the user has not entered battery swapping reservation information. Alternatively, it can display the queue number of the target battery swapping station in the reservation order, as well as nearby and / or historically used battery swapping stations and their queue numbers, while simultaneously showing the queue number of the target station. Therefore, displaying queue numbers for different swapping stations through the above method provides users with different battery swapping station options, positively contributing to their quick selection of a battery swapping station.

[0103] The technical method in this embodiment visualizes the queue number corresponding to the battery swap order after the user sends the order, enabling the user to know the queue status of the battery swap station in advance, thereby making a reasonable battery swap decision and improving the user's battery swap experience and satisfaction.

[0104] Figure 7 This is a schematic diagram of a battery swapping station queue number determination device according to an embodiment of the present invention. Figure 7 As shown, the device for determining the queue size of a battery swapping station in this embodiment includes an acquisition unit 71 and a processing unit 72. The acquisition unit 71 acquires the queue size for the current time period and battery swapping reservation information, which includes multiple battery swapping orders. Each battery swapping order includes a reserved battery swapping time, a reserved battery swapping station identifier, and a battery swapping vehicle model. The processing unit 72 inputs the queue size and battery swapping reservation information for the current time period into a pre-trained prediction model for processing, determining the queue size for future time periods. The prediction model is trained and determined based on historical battery swapping information corresponding to historical battery swapping orders at the battery swapping station in different time periods.

[0105] Optionally, the historical battery swapping information in this embodiment includes the number of battery swapping orders, the number of scheduled battery swapping orders, the number of unscheduled battery swapping orders, the battery swapping duration, the battery swapping vehicle model, and the number of people in the queue.

[0106] Optionally, the processing unit 72 in this embodiment is further configured to train and determine a prediction model based on historical battery swapping information. Specifically, during the training and determination of the prediction model, the processing unit 72 is configured to acquire historical battery swapping information for different time periods; perform preprocessing and feature engineering on each piece of historical battery swapping information to determine sample data, which includes a training set, a validation set, and a test set; use the training set to iteratively train the preset prediction model; use the validation set to validate the output of the iteratively trained prediction model; and use the test set to evaluate the performance of the validated prediction model.

[0107] Furthermore, when determining sample data, the processing unit 72 is also used to preprocess the historical battery swapping information to determine the first feature data, the preprocessing including data cleaning, format conversion and / or standardization; to perform feature engineering processing on the first feature data to determine the second feature data, the second feature data including time period label, average battery swapping duration and reservation order ratio; and to integrate the first feature data and the second feature data corresponding to each historical battery swapping information to generate sample data.

[0108] Figure 8 This is another schematic diagram of the battery swapping station queue number determination device according to an embodiment of the present invention. Figure 8As shown, the battery swapping station queue number determination device in this embodiment includes a sending unit 81 and a display unit 82. The sending unit 81 sends battery swapping orders, which include the scheduled battery swapping time, the scheduled battery swapping station identifier, and the battery swapping vehicle model. The display unit 82 receives and displays the queue number for the target time period to which the battery swapping order belongs. The queue number is determined by processing the battery swapping reservation information corresponding to the battery swapping order within the target time period and the queue number for the current time period using a pre-trained prediction model. The prediction model is trained based on historical battery swapping information corresponding to historical battery swapping orders at the battery swapping station in different time periods.

[0109] Figure 9 This is a schematic diagram of an electronic device according to an embodiment of the present invention. (For example...) Figure 9 As shown, Figure 9 The illustrated electronic device is a general-purpose data processing device, comprising a general-purpose computer hardware architecture, including at least a processor 91 and a memory 92. The processor 91 and memory 92 are connected via a bus 93. The memory 92 is adapted to store instructions or programs executable by the processor 91. The processor 91 can be a standalone microprocessor or a collection of one or more microprocessors. Thus, the processor 91 executes the instructions stored in the memory 92, thereby performing the method flow of the embodiments of the present invention as described above to process data and control other devices. The bus 93 connects the aforementioned components together, and also connects these components to a display controller 94, a display device, and an input / output (I / O) device 95. The input / output (I / O) device 95 can be a mouse, keyboard, modem, network interface, touch input device, motion-sensing input device, printer, and other devices known in the art. Typically, the input / output device 95 is connected to the system via an input / output (I / O) controller 96.

[0110] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus (devices), or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0111] This application is described with reference to flowchart illustrations of methods, apparatus (devices), and computer program products according to embodiments of this application. It should be understood that each step in the flowchart can be implemented by computer program instructions.

[0112] These computer program instructions may be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction means, the implementation process of which is described in the instruction means. Figure 1 The function specified in one or more processes.

[0113] These computer program instructions may also be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing device, produce instructions for implementing processes. Figure 1 A device for a function specified in one or more processes.

[0114] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program for use by a computer to execute some or all of the above-described method embodiments.

[0115] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program specifying the relevant hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0116] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining the queue size at a battery swapping station, characterized in that, The method includes: Get the number of people in the queue for the current time period; Obtain battery swap reservation information, which includes multiple battery swap orders, and each battery swap order includes the reserved battery swap time, the reserved battery swap station identifier, and the battery swap vehicle model; The queue number for the current time period and the battery swapping reservation information are input into a pre-trained prediction model for processing to determine the queue number for future time periods. The prediction model is trained and determined based on historical battery swapping information corresponding to historical battery swapping orders at the battery swapping station in different time periods.

2. The method according to claim 1, characterized in that, The historical battery swapping information includes the number of battery swapping orders, the number of scheduled battery swapping orders, the number of unscheduled battery swapping orders, the battery swapping duration, the battery swapping vehicle models, and the number of people in the queue.

3. The method according to claim 1, characterized in that, The prediction model was determined based on the following method: Obtain historical battery swapping information for different time periods; The historical battery swapping information is preprocessed and feature-engineered to determine sample data, which includes a training set, a validation set, and a test set. The training set is used to iteratively train the preset prediction model; The output of the prediction model after iterative training is validated using the validation set. The performance of the validated prediction model is evaluated using the test set.

4. The method according to claim 3, characterized in that, The process of preprocessing and feature engineering the historical battery swapping information to determine the sample data includes: The historical battery swapping information is preprocessed to determine the first feature data. The preprocessing includes data cleaning, format conversion and / or standardization. The first feature data is subjected to feature engineering processing to determine the second feature data, which includes time period label, average battery swapping time and reservation order ratio. The first feature data and the second feature data corresponding to each of the historical battery swapping information are integrated to generate sample data.

5. A method for determining the queue size at a battery swapping station, characterized in that, The method includes: Send a battery swapping order, which includes the scheduled battery swapping time, the identifier of the scheduled battery swapping station, and the vehicle model to be swapped. The system receives and displays the queue number for the target time period to which the battery swapping order belongs. The queue number is determined by processing the battery swapping reservation information corresponding to the battery swapping order within the target time period and the queue number for the current time period using a pre-trained prediction model. The prediction model is trained and determined based on the historical battery swapping information corresponding to historical battery swapping orders at the battery swapping station in different time periods.

6. A battery swapping station reservation system, characterized in that, The system includes: At least one user terminal is configured to send a battery swapping order, the battery swapping order including a scheduled battery swapping time, a scheduled battery swapping station identifier, and a battery swapping vehicle model; and to receive and display the queue number for the target time period to which the battery swapping order belongs; The server is configured to: obtain the queue count for the current time period; obtain battery swapping reservation information, which includes multiple battery swapping orders; input the queue count for the current time period and the battery swapping reservation information into a pre-trained prediction model for processing to determine the queue count for future time periods; and send the queue count for each battery swapping order corresponding to a target time period to the corresponding terminal; wherein the prediction model is trained and determined based on historical battery swapping information corresponding to historical battery swapping orders at the battery swapping station in different time periods, and the future time periods include the target time periods.

7. A device for determining the number of people queuing at a battery swapping station, characterized in that, The device includes: The acquisition unit is used to acquire the number of queues in the current time period; acquire battery swapping reservation information, which includes multiple battery swapping orders, and each battery swapping order includes the reserved battery swapping time, the reserved battery swapping station identifier, and the battery swapping vehicle model; The processing unit is used to input the queue number of the current time period and the battery swap reservation information into a pre-trained prediction model for processing, and to determine the queue number of the future time period. The prediction model is trained and determined based on the historical battery swap information corresponding to the historical battery swap orders of the battery swap station in different time periods.

8. A device for determining the queue length at a battery swapping station, characterized in that, The device includes: A sending unit is used to send a battery swapping order, which includes the scheduled battery swapping time, the identifier of the scheduled battery swapping station, and the vehicle model to be swapped. The display unit is used to receive and display the queue number of the target time period to which the battery swapping order belongs. The queue number is determined by processing the battery swapping reservation information corresponding to the battery swapping order in the target time period and the queue number in the current time period through a pre-trained prediction model. The prediction model is trained and determined based on the historical battery swapping information corresponding to the historical battery swapping orders in different time periods of the battery swapping station.

9. A computer program product, characterized in that, The computer program product includes a computer program / instruction that, when executed by a processor, implements the method of any one of claims 1-5.

10. An electronic device comprising a memory and a processor, characterized in that, The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any one of claims 1-5.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1-5.

Images