Method, apparatus, medium, and device for predicting vacancy rate of parking space

Abstract

Provided are a method, an apparatus, a medium, and a device for predicting the vacancy rate of a parking space. The vacancy rate of the parking space of each parking lot within the area to be predicted at a plurality of times before the time to be predicted is input into the feature extraction network of the parking space vacancy rate prediction model to obtain a first feature for characterizing the time-dependent relationship of the vacancy rate of the parking space of each parking lot. Also, the spatial relationship graph between each parking lot within the area to be predicted and the first feature are input into the graph fusion network to obtain a fused feature. Then, the fused feature is input into the result prediction network to obtain the vacancy rate of the parking space of each parking lot within the area to be predicted at the time to be predicted. Based on the relationship between the vacancy rate of the parking space and time, the relationship between the vacancy rate of the parking space and space, and the potential correlation between the vacancy rate of the parking space and time and space, by simultaneously obtaining the prediction results of the vacancy rates of the parking spaces of a plurality of parking lots within the area to be predicted, the prediction efficiency of the vacancy rate of the parking space and the accuracy of the prediction result can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to a method, apparatus, medium, and device for predicting the vacancy rate of parking spaces.

Background Art

[0002] With the development of science and technology, artificial intelligence has also been rapidly developing. Among them, in the field of traffic big data, machine learning models are also widely used.

[0003] Generally, a machine learning model can be used to predict the vacancy rate of parking spaces in a certain area, so that a driver can select a parking space based on the prediction information and park. However, in the process of obtaining the model, it is necessary to consider not only the relationship between the vacancy rate of parking spaces and time in the parking lots within the area, but also the spatial correlation between each parking lot. Therefore, it is a difficulty to determine how to simultaneously determine the future vacancy rates of parking spaces in multiple parking lots.

[0004] Based on such problems, the present disclosure provides a method for predicting the vacancy rate of parking spaces.

Summary of the Invention

Problems to be Solved by the Invention

[0005] The present disclosure provides a method, apparatus, medium, and device for predicting the vacancy rate of parking spaces.

Means for Solving the Problems

[0006] The technical solutions used in the present disclosure are as follows.

[0007] The present disclosure provides a method for predicting the vacancy rate of a parking space. The method is applied to a computing device, and a pre-trained vacancy rate prediction model for the parking space is arranged in the computing device. The vacancy rate prediction model for the parking space includes a feature extraction network, a graph fusion network, and a result prediction network. The method includes: determining an area to be predicted and a time to be predicted; acquiring, as the historical vacancy rate of each parking lot, the vacancy rate of the parking space at a plurality of times before the time to be predicted in each parking lot within the area to be predicted; inputting the historical vacancy rate of each parking lot into the feature extraction network to obtain a first feature, where the first feature is used to characterize the time-dependent relationship of the historical vacancy rate of each parking lot; constructing a spatial relationship graph among the parking lots within the area to be predicted; inputting the spatial relationship graph and the first feature into the graph fusion network to obtain a fusion feature; inputting the fusion feature into the result prediction network to obtain the vacancy rate of the parking space of each parking lot within the area to be predicted at the time to be predicted.

[0008] Optionally, before inputting the spatial relationship graph and the first feature into the graph fusion network, the method further includes: inputting the historical vacancy rate of each parking lot into the feature extraction network to obtain a second feature, where the second feature is used to characterize the similarity of the historical vacancy rate of each parking lot; The step of inputting the spatial relationship graph and the first feature into the graph fusion network includes: further inputting the spatial relationship graph, the first feature, and the second feature into the graph fusion network.

[0009] Optionally, the step of constructing a spatial relationship graph between each parking lot within the area to be predicted specifically includes: constructing the spatial relationship graph with each parking lot within the area to be predicted as nodes and the distance between each pair of parking lots within the area to be predicted as the weight of the edges.

[0010] Optionally, the graph fusion network includes an attention network and a graph convolutional network. The step of inputting the spatial relationship graph, the first feature, and the second feature into the graph fusion network includes: inputting the spatial relationship graph, the first feature, and the second feature into the attention network to obtain an output result with attention weights; and inputting the output result and the historical vacancy rate of each parking lot into the graph convolutional network.

[0011] Optionally, the parking space vacancy rate prediction model further includes an environmental feature extraction network. Before inputting the fused feature into the result prediction network, the method further includes: obtaining environmental information of each parking lot within the area to be predicted before the time to be predicted, where the environmental information includes at least weather information and holiday information; inputting the environmental information into the environmental feature extraction network to obtain environmental features. The step of inputting the fused feature into the result prediction network includes: further inputting the first feature, the fused feature, the environmental feature, and the historical vacancy rate of each parking lot into the result prediction network.

[0012] Optionally, the parking space vacancy rate prediction model obtains the vacancy rates of the parking spaces of each parking lot within the specified area at at least two historical times; Using the vacancy rate of the parking spaces in each parking lot at the latest historical time among the at least two historical times as a label, and using the vacancy rates of the parking spaces in each parking lot at other historical times as samples; Inputting the samples into the feature extraction network to obtain sample features, where the sample features are used to characterize the relationship between the historical vacancy rates and time of each parking lot; Constructing a spatial relationship graph between each parking lot within the specified area as a sample spatial relationship graph; Inputting the sample spatial relationship graph and the sample features into the graph fusion network to obtain sample fusion features; Inputting the sample fusion features into the result prediction network to obtain the prediction results of the vacancy rates of the parking spaces at the latest historical time in the specified area; Training the vacancy rate prediction model of the parking space with the goal of minimizing the difference between the prediction results of the vacancy rates of the parking spaces and the label.

[0013] The present disclosure provides a prediction device for the vacancy rate of a parking space. A pre-trained vacancy rate prediction model of the parking space is arranged in the prediction device for the vacancy rate of the parking space. The vacancy rate prediction model of the parking space includes a feature extraction network, a graph fusion network, and a result prediction network. The device includes: A determination module for determining the area to be predicted and the time to be predicted; An acquisition module for acquiring the vacancy rates of the parking spaces in each parking lot within the area to be predicted at a plurality of times before the time to be predicted as the historical vacancy rates of each parking lot; A first input module for inputting the historical vacancy rates of each parking lot into the feature extraction network to obtain first features, where the first features are used to characterize the time-dependent relationship of the historical vacancy rates of each parking lot. A construction module for constructing a spatial relationship graph between each parking lot within the area to be predicted, A second input module for inputting the spatial relationship graph and the first feature into the graph fusion network to obtain a fused feature, An output module for inputting the fused feature into the result prediction network to obtain the vacancy rate of the parking spaces in each parking lot within the area to be predicted at the time to be predicted.

[0014] Optionally, the first input module specifically Inputs the historical vacancy rate of each parking lot into the feature extraction network and is used to obtain a second feature, and the second feature is used to characterize the similarity of the historical vacancy rates of each parking lot. Specifically, the second input module Is used to input the spatial relationship graph, the first feature, and the second feature into the graph fusion network.

[0015] Optionally, the construction module specifically Uses each parking lot within the area to be predicted as a node and the distance between each parking lot within the area to be predicted as the weight of the edge to construct the spatial relationship graph.

[0016] Optionally, the graph fusion network includes an attention network and a graph convolutional network. Specifically, the second input module Inputs the spatial relationship graph, the first feature, and the second feature into the attention network to obtain an attention-weighted output result. Is used to input the output result and the historical vacancy rate of each parking lot into the graph convolutional network.

[0017] Optionally, the parking space vacancy rate prediction model further includes an environmental feature extraction network. The device further includes an environmental information input module, Specifically, the environmental information input module, acquires environmental information of each parking lot in the area to be predicted before the time to be predicted, the environmental information includes at least weather information and holiday information, inputs the environmental information into the environmental feature extraction network, and is used to obtain environmental features. Specifically, the output module, is used to input the first feature, the fusion feature, the environmental feature, and the historical vacancy rate of each parking lot into the result prediction network.

[0018] Optionally, the device further includes a training module, Specifically, the training module, acquires the vacancy rate of parking spaces at at least two historical times of each parking lot in the designated area, uses the vacancy rate of parking spaces of each parking lot at the latest historical time among the at least two historical times as a label, and uses the vacancy rate of parking spaces of each parking lot at other historical times as a sample, inputs the sample into the feature extraction network to obtain a sample feature, and the sample feature is used to characterize the relationship between the historical vacancy rate of each parking lot and time, constructs a spatial relationship graph between each parking lot in the designated area as a sample spatial relationship graph, inputs the sample spatial relationship graph and the sample feature into the graph fusion network to obtain a sample fusion feature, inputs the sample fusion feature into the result prediction network to obtain a prediction result of the vacancy rate of each parking space at the latest historical time in the designated area, is used to train the parking space vacancy rate prediction model with the goal of minimizing the difference between the prediction result of the vacancy rate of each parking space and the label.

[0019] The present disclosure provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method for predicting the vacancy rate of a parking space is implemented.

[0020] The present disclosure provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for predicting the vacancy rate of a parking space is implemented.

Advantages of the Invention

[0021] At least one of the above technical solutions used in the present disclosure can achieve the following beneficial effects.

[0022] In the method for predicting the vacancy rate of a parking space provided by the present disclosure, the vacancy rate of the parking spaces in each parking lot within the area to be predicted before the time to be predicted is input into the feature extraction network of the vacancy rate prediction model of the parking space, and the first feature for characterizing the relationship between the vacancy rate of the parking spaces in each parking lot and time can be obtained. Further, the spatial relationship graph between each parking lot within the area to be predicted and the first feature are input into the graph fusion network, and the fusion feature for characterizing the relationship between the vacancy rate of the parking spaces in each parking lot and time and space can be obtained. Then, the fusion feature is input into the result prediction network of the vacancy rate prediction model of the parking space to obtain the vacancy rate of the parking spaces in each parking lot within the area to be predicted at the time to be predicted. Based on the relationship between the vacancy rate of the parking space and time, the relationship between the vacancy rate of the parking space and space, and the potential mutual relationship between the vacancy rate of the parking space and time and space, by simultaneously obtaining the prediction results of the vacancy rates of the parking spaces in a plurality of parking lots within the area to be predicted, the prediction efficiency of the vacancy rate of the parking space and the accuracy of the prediction result can be improved.

Brief Description of the Drawings

[0023] The accompanying drawings described herein are used to deepen the understanding of the present disclosure, constitute a part of the present disclosure, and the exemplary embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an undue limitation of the present disclosure.

[0024]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Embodiments for Carrying Out the Invention

[0025] To make the purpose, technical solution and advantages of the present disclosure clearer, hereinafter, in combination with specific embodiments of the present disclosure and the corresponding accompanying drawings, the technical solution of the present disclosure will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, not all of them. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative labor shall fall within the protection scope of the present disclosure.

[0026] Hereinafter, in combination with the accompanying drawings, the technical solutions provided in each embodiment of the present disclosure will be described in detail.

[0027] FIG. 1 is a schematic diagram showing the flow of a method for predicting the vacancy rate of a parking space provided in the present disclosure, and includes the following steps.

[0028] In S100, determine the area to be predicted and the time to be predicted.

[0029] In S102, obtain, as the historical vacancy rate of each parking lot, the vacancy rate of the parking spaces at a plurality of times before the time to be predicted within the area to be predicted for each parking lot.

[0030] The execution entity of the prediction method of the present disclosure may be any computing device (for example, a server, a terminal) having computing capabilities. A pre-trained parking space vacancy rate prediction model is arranged in the computing device. As shown in FIG. 2, the parking space vacancy rate prediction model includes a feature extraction network, a graph fusion network, and a result prediction network.

[0031] The computing device may determine the area to be predicted and the time to be predicted. The area to be predicted and the time to be predicted may be obtained from the input of the user, that is, the time to be predicted that the user wants to know and the vacancy rate of the parking spaces in the area to be predicted. Alternatively, the area to be predicted may be the area where the user is located at the current time, and the time to be predicted may be the current time. That is, when the user is driving a vehicle, it can be predicted in real time according to the driving route of the user. In addition, the area to be predicted and the time to be predicted may be set in advance, and the area to be predicted and the time to be predicted are determined based on a preset time length threshold and a geographical area.

[0032] Furthermore, in order to determine the relationship between the vacancy rate of parking spaces in each parking lot within the area to be predicted and time by means of the parking space vacancy rate prediction model, the computing device may obtain, as the historical vacancy rate of each parking lot, the vacancy rate of the parking space in each parking lot within the area to be predicted at a time before the time to be predicted, based on the area to be predicted and the time to be predicted. For example, if the area to be predicted is Area B in City A and the time to be predicted is 18:30 on April 19th, the computing device can obtain the vacancy rate of the parking space in each parking lot in Area B of City A before 18:30 on April 19th. Assuming that there are three parking lots, X, Y, and Z, in Area B of City A, the computing device can obtain that at 18:29 on April 19th, the vacancy rate of the parking space in Parking Lot X is 20%, the vacancy rate of the parking space in Parking Lot Y is 30%, and the vacancy rate of the parking space in Parking Lot Z is 40%; at 18:24 on April 19th, the vacancy rate of the parking space in Parking Lot X is 19%, the vacancy rate of the parking space in Parking Lot Y is 20%, and the vacancy rate of the parking space in Parking Lot Z is 20%.

[0033] Here, when obtaining the vacancy rate of the parking space in each parking lot within the area to be predicted at a time before the time to be predicted, the vacancy rate of the parking space in each parking lot within the area to be predicted at a time before the time to be predicted may be obtained based on a preset time period. That is, determine a preset time period for sampling, determine the sampling time by setting it back from the time to be predicted based on the preset time period, and obtain the vacancy rate of the parking space in each parking lot at each sampling time. For example, if the preset time period is 5 minutes and the time to be predicted is 18:50, the vacancy rate of the parking space in each parking lot at times such as 18:45 and 18:40 may be obtained.

[0034] Note that regarding which occupancy rates of the parking spaces in each parking lot within the area to be predicted at several times before the time to be predicted are to be obtained, it is not particularly limited specifically, and it may be obtained as necessary. For example, assuming that the input required for the occupancy rate prediction model of the parking space is the historical occupancy rate of each parking lot at 5 times before the time to be predicted, the historical occupancy rate of each parking lot at 5 times before the time to be predicted may be obtained. Further, the occupancy rate of the parking space is determined based on all the parking spaces and the available (empty) parking spaces in each parking lot.

[0035] Also, the occupancy rate of the parking space in each parking lot is calculated based on all the parking spaces and the available (i.e., empty) parking spaces in each parking lot.

[0036] In S104, the historical occupancy rate of each parking lot is input into the feature extraction network, and a first feature is obtained. The first feature is used to characterize the relationship between the historical occupancy rate of each parking lot and time.

[0037] The computing device may input the historical occupancy rate of each parking lot into the feature extraction network of the occupancy rate prediction model of the parking space, and obtain a first feature for characterizing the time-dependent relationship of the historical occupancy rate of each parking lot.

[0038] In S106, a spatial relationship graph between each parking lot within the area to be predicted is constructed.

[0039] In one or more embodiments of the present disclosure, after determining the area to be predicted and the time to be predicted in step S100 above, in order to determine the relationship between the occupancy rate and the space of the parking spaces in each parking lot within the area to be predicted, a spatial relationship graph between each parking lot within the area to be predicted may be constructed.

[0040] Here, when constructing the spatial relationship graph, each parking lot within the area to be predicted can be used as a node, and the distance between each pair of parking lots within the area to be predicted can be used as the weight of the edge to construct the spatial relationship graph. To explain along the above-mentioned example, in District B of City A, there are three parking lots, namely X, Y, and Z. Assuming the distance from Parking Lot X to Parking Lot Y is 3 km, the distance from Parking Lot X to Parking Lot Z is 5 km, and the distance from Parking Lot Z to Parking Lot Y is 4 km, a spatial relationship graph as shown in Figure 3 can be constructed.

[0041] Note that when constructing the spatial relationship graph, the distance between each pair of parking lots is not the straight-line distance, but the actual road distance. Based on the electronic map of the area to be predicted, the shortest road connecting two parking lots can be determined, and a road topology map between each pair of parking lots can be obtained. Based on the road topology map, the distance between two parking lots can be determined, and this distance can be used as the weight of the corresponding edge between the two parking lots in the spatial relationship graph. Of course, the driving time between parking lots, etc., can also be used as the weight of the edge in the spatial relationship graph. By way of example rather than limitation, the weight may be a comprehensive consideration of the actual distance, driving time, or other influencing factors. For example, the actual distance or driving time between two parking lots may be calculated using a map tool or comprehensively calculated considering factors such as traffic congestion.

[0042] Also, when constructing the spatial relationship graph, first, an adjacency matrix can be used to represent the relationship between nodes (i.e., parking lots). The elements of the adjacency matrix represent the weight between two nodes. The elements of the adjacency matrix

Number

[0043] In S108, the spatial relationship graph and the first feature are input into the graph fusion network to obtain a fused feature.

[0044] After obtaining a first feature for characterizing the relationship between the vacancy rate of parking spaces in each parking lot within the area to be predicted and time, and a spatial relationship graph of each parking lot within the area to be predicted, the computing device may input the spatial relationship graph and the first feature into a graph fusion network to obtain a fused feature for characterizing the relationship between the vacancy rate of parking spaces in each parking lot and time and space.

[0045] Here, the graph fusion network may include an attention network and a graph convolutional network (GCN). The attention network enables the vacancy rate prediction model of the parking space to selectively focus on important parts. The graph convolutional network can combine the features of the spatial relationship graph and the first feature and output a fused feature.

[0046] The spatial relationship graph and the first feature may be input into the attention network to obtain an attention-weighted output result. Further, the output result and the historical vacancy rate of each parking lot may be input into the graph convolutional network to obtain a fused feature.

[0047] Note that when the spatial relationship graph and the first feature are input into the attention network, since the spatial relationship graph represents the adjacency relationship using a matrix form and the attention network handles the operations between matrices, the first feature is converted into a matrix form similar to the adjacency matrix represented by the spatial relationship graph. For example, the first feature and the transpose of the first feature are matrix-multiplied, and then the calculation result of the matrix multiplication, the second feature matrix calculated later, and the spatial relationship graph are input into the attention network.

[0048] In S110, input the fusion feature into the result prediction network to obtain the vacancy rate of the parking spaces in each parking lot within the area to be predicted at the time to be predicted.

[0049] The computing device may input the fusion feature and the historical vacancy rate of each parking lot into the result prediction network to obtain the vacancy rate of the parking spaces in each parking lot within the area to be predicted at the time to be predicted.

[0050] Explaining according to the above-described example, if the area to be predicted is Area B of City A and the time to be predicted is 18:30 on April 19th, the computing device can obtain the vacancy rate of the parking spaces in each parking lot in Area B of City A before 18:30 on April 19th. Assuming that there are three parking lots, X, Y, and Z, in Area B of City A, the computing device can obtain that at 18:29 on April 19th, the vacancy rate of the parking spaces in Parking Lot X is 20%, the vacancy rate of the parking spaces in Parking Lot Y is 30%, and the vacancy rate of the parking spaces in Parking Lot Z is 40%; at 18:24 on April 19th, the vacancy rate of the parking spaces in Parking Lot X is 19%, the vacancy rate of the parking spaces in Parking Lot Y is 20%, and the vacancy rate of the parking spaces in Parking Lot Z is 20%. Assume that the vacancy rates of the parking spaces in each parking lot (that is, at 18:29 on April 19th, the vacancy rate of the parking spaces in Parking Lot X is 20%, the vacancy rate of the parking spaces in Parking Lot Y is 30%, and the vacancy rate of the parking spaces in Parking Lot Z is 40%; at 18:24 on April 19th, the vacancy rate of the parking spaces in Parking Lot X is 19%, the vacancy rate of the parking spaces in Parking Lot Y is 20%, and the vacancy rate of the parking spaces in Parking Lot Z is 20%) and the fusion feature are input into the result prediction network, and a prediction result that at 18:30 on April 19th, the vacancy rate of the parking spaces in Parking Lot X is 50%, the vacancy rate of the parking spaces in Parking Lot Y is 70%, and the vacancy rate of the parking spaces in Parking Lot Z is 40% is obtained.

[0051] In the above-described method for predicting the vacancy rate of a parking space provided in the present disclosure shown in FIG. 1, the vacancy rate of the parking space of each parking lot in the area to be predicted at a plurality of times before the time to be predicted is input into the feature extraction network of the vacancy rate prediction model of the parking space, and a first feature for characterizing the time-dependent relationship of the vacancy rate of the parking space of each parking lot can be obtained. Further, the spatial relationship graph between each parking lot in the area to be predicted and the first feature are input into the graph fusion network, and a fusion feature for characterizing the relationship between the vacancy rate of the parking space of each parking lot and time and space is obtained. Then, the fusion feature is input into the result prediction network of the vacancy rate prediction model of the parking space to obtain the vacancy rate of the parking space of each parking lot in the area to be predicted at the time to be predicted. The vacancy rate of the parking space of a parking lot is not only related to time, but also related to the spatial position of each parking lot. That is, when there are differences in time and spatial position, the vacancy rate of the parking space of each parking lot is different. Therefore, based on the relationship between the vacancy rate of the parking space and time, the relationship between the vacancy rate of the parking space and space, and the potential correlation between the vacancy rate of the parking space and time and space, by simultaneously obtaining the prediction results of the vacancy rates of the parking spaces of a plurality of parking lots in the area to be predicted, the prediction efficiency of the vacancy rate of the parking space and the accuracy of the prediction result can be improved.

[0052] In one or more embodiments of the present disclosure, when the vacancy rates of the parking spaces of each parking lot at a certain time are the same, the difference in the vacancy rates of the parking spaces of the parking lot at the next time is generally not very large. In order to improve the accuracy of the prediction result, the similarity of the vacancy rates of the parking spaces of each parking lot at the same time before the time to be predicted may be calculated to give a hint to the model. Thereby, the model can determine the similarity of the vacancy rates of the parking spaces of each parking lot at the time to be predicted based on the similarity of the vacancy rates of the parking spaces of each parking lot at the same time before the time to be predicted.

[0053] The feature extraction network may include a first feature extraction network and a second feature extraction network. The first feature extraction network is used to extract a first feature for characterizing the relationship between the historical vacancy rate and time of each parking lot. The second feature extraction network is used to extract a second feature for characterizing the similarity of the historical vacancy rates of each parking lot. The historical vacancy rate of each parking lot can be input into the first feature extraction network to obtain the first feature, and the historical vacancy rate of each parking lot can be input into the second feature extraction network to obtain the second feature.

[0054] In one or more embodiments of the present disclosure, the first feature extraction network may be a Gated Recurrent Unit (GRU), and the second feature extraction network may be Dynamic Time Warping (DTW).

[0055] GRU may include two gates: an Update Gated z t and a Reset Gated r t Usually, the reset gate is used to determine how much old information to forget, while the update gate is used to determine which information to forget and which new information needs to be added. The input x t (that is, the vacancy rate of the parking spaces in each parking lot at time t), the reset gate r t and the hidden state h (t-1) at the previous time t - 1 are combined to calculate a candidate hidden state

Number

Number

Number

Number

Number

[0056] In one or more embodiments of the present disclosure, one node represents one parking lot including a plurality of parking spaces. Each parking lot has occupancy data at different times. For example, to predict the occupancy rate at time t = 3, it is necessary to calculate the DTW distance using the occupancy rates between different parking lots at times t = 1 and 2. Therefore, in the second feature extraction network, the similarity of the historical vacancy rates between two nodes can be calculated using the following formula (5).

Number

[0057] In step S108 above, the first feature, the second feature, and the spatial relationship graph may be input into the graph fusion network to obtain a fusion feature. Specifically, the first feature, the second feature, and the spatial relationship graph may be input into the attention network of the graph fusion network to obtain an output result, and further, the output result may be input into the graph convolutional network to obtain a fusion feature.

[0058] Here, when using the attention network, the attention network is used to selectively focus on specific parts of the input sequence when generating an output. The basic principle of the attention network is to weight each input element according to the importance of the output at a specific step. Therefore, the model can selectively focus on the most important parts of the input and ignore the less important parts. The calculation of attention is represented by the following Equation (6). [Number] Here, Q is the calculation result of matrix multiplying the first feature, K is the second feature, and V may be a spatial relationship graph. d k represents the dimensionality of Q and K. Since the first feature is calculated as the number of nodes * the number of hidden layers based on the hidden state of the GRU, it is necessary to further process it using matrix multiplication to convert it into the form of the number of nodes * the number of nodes. Dividing the product of Q and K by the square root of the dimensions of Q and K helps to stabilize the gradient in the training process. By using the attention network, the parking space vacancy rate prediction model can simultaneously focus on different aspects of the first feature, the second feature, and the spatial relationship graph, extract temporal and spatial information, and finally obtain the attention-weighted output result, which can improve the accuracy and comprehensiveness of the parking space vacancy rate prediction model.

[0059] Next, when using the GCN network, the method of spectral graph convolution is used to first calculate the normalized graph Laplacian matrix based on the fused features, which can be expressed by the following formula (7). [Number] Here, D = diag(d i ) is the degree matrix, and d i = Σ j A ij is the degree of the i-th node, and the node represents a node in the road topology map, that is, a parking lot. A ij is the general term for the first feature, the second feature, and the spatial relationship graph. [Number] represents the fused features. The convolution operation can be defined by the following formula (8). [Number] Here,

Number

[0060] To further simplify the calculation and avoid overfitting, generally, the convolution is calculated using the first-order approximation of the graph Laplacian, and the convolution layer operation finally used can be represented by the following formula (9).

Number

[0061] The attention network and the GCN network can effectively obtain the spatio-temporal dependence relationship and improve the prediction accuracy. On the other hand, the attention network enables the parking space vacancy rate prediction model to selectively focus on important parts of the input sequence, thereby enhancing the generalization ability of the parking space vacancy rate prediction model.

[0062] Furthermore, in different environments, the vacancy rates of parking spaces in each parking lot are different, that is, the vacancy rates of parking spaces in each parking lot are affected by the environment. Therefore, in one or more embodiments of the present disclosure, the parking space vacancy rate prediction model further includes an environmental feature extraction network.

[0063] Before inputting the fused features into the result prediction network, the computing device acquires the environmental information of each parking lot in the area to be predicted before the time to be predicted, and inputs the environmental information into the environmental feature extraction network to obtain environmental features. Finally, the first feature, the fused feature, the environmental feature, and the historical vacancy rate of each parking lot are input into the result prediction network to obtain the vacancy rate of the parking space in each parking lot in the area to be predicted at the time to be predicted.

[0064] Here, the environmental information includes at least weather information and holiday information.

[0065] In addition, in one or more embodiments of the present disclosure, the environmental feature extraction network may be a GRU, and the result prediction network may be a Multilayer Perceptron (MLP).

[0066] Furthermore, in one or more embodiments of the present disclosure, a method for training an occupancy rate prediction model for parking spaces is provided.

[0067] Specifically, the computing device obtains the occupancy rate of parking spaces in each parking lot within the specified area at at least two historical times, uses the occupancy rate of the parking spaces in each parking lot at the latest historical time among the at least two historical times as a label, uses the occupancy rate of the parking spaces in each parking lot at other historical times as a sample, inputs the sample into the feature extraction network to obtain sample features, constructs a spatial relationship graph between each parking lot within the specified area as a sample spatial relationship graph, then inputs the sample spatial relationship graph and the sample features into the graph fusion network to obtain sample fusion features, inputs the sample fusion features into the result prediction network to obtain the prediction results of the occupancy rate of the parking spaces in each parking lot at the latest historical time of the specified area, and finally, trains the occupancy rate prediction model for parking spaces with the goal of minimizing the difference between the prediction result and the label of the occupancy rate of each parking space. That is, adjust the parameters of the feature extraction network, the graph fusion network, and the result prediction network.

[0068] Here, the sample features are used to characterize the relationship between the historical occupancy rate and time of each parking lot.

[0069] Note that when training the occupancy rate prediction model for parking spaces, one input sample may be the occupancy rate of the parking spaces in each parking lot at a plurality of historical times.

[0070] In one or more embodiments of the present disclosure, when the feature extraction network includes a first feature extraction network and a second feature extraction network, the graph fusion network includes an attention network and a graph convolutional network, and the parking space vacancy rate prediction model further includes an environmental feature extraction network, first, input a sample into the first feature extraction network to obtain a first sample feature, input the sample into the second feature extraction network to obtain a second sample feature, construct a sample spatial relationship graph between each parking lot within the specified area, and then input the first sample feature, the dot product result of the first sample feature, the second sample feature, and the sample spatial relationship graph into the attention network to obtain an attention-weighted sample output result, and the sample output result may be input into the graph convolutional network to obtain a sample fusion feature.

[0071] Also, environmental information of each parking lot within the specified area may be obtained as sample environmental information, and the sample environmental information may be input into the environmental feature extraction network to obtain sample environmental features.

[0072] Finally, input the sample fusion feature, the sample environmental feature, the first sample feature, and the sample into the result prediction network to obtain the prediction result of the vacancy rate of each parking space in each parking lot at the latest historical time in the specified area. The parking space vacancy rate prediction model is trained with the goal of minimizing the difference between the prediction result of the vacancy rate of each parking space and the label.

[0073] That is, with the goal of minimizing the difference between the prediction result of the vacancy rate of each parking space and the label, the parameters of the first feature extraction network, the second feature extraction network, the attention network, the graph convolutional network, the environmental feature extraction network, and the result prediction network are adjusted.

[0074] In one or more embodiments of the present disclosure, the vacancy rate of the parking spaces in each parking lot within the area to be predicted obtained by prediction may be distributed to the cloud. The user may obtain the prediction result through the communication between the cloud and the computing device without performing calculations and storage on the computing device. This can improve the calculation efficiency and save the storage capacity.

[0075] Furthermore, the vacancy rate of the parking spaces in each parking lot within the area to be predicted at a plurality of future times can be predicted. Thus, the user can plan the movement route in advance according to their own movement requirements and actual situations, avoid wasting time and resources, and improve the traffic efficiency and quality of the area to be predicted.

[0076] Based on the above-described method for predicting the vacancy rate of parking spaces, an embodiment of the present disclosure further provides a device for predicting the vacancy rate of corresponding parking spaces as shown in FIG. 4.

[0077] FIG. 4 is a schematic diagram showing a device for predicting the vacancy rate of parking spaces provided in the present disclosure. In the device for predicting the vacancy rate of parking spaces, a pre-trained model for predicting the vacancy rate of parking spaces is arranged. The model for predicting the vacancy rate of parking spaces includes a feature extraction network, a graph fusion network, and a result prediction network. The device includes: a determination module 402 for determining the area to be predicted and the time to be predicted; an acquisition module 406 for acquiring the vacancy rate of the parking spaces at a plurality of times before the time to be predicted in each parking lot within the area to be predicted as the historical vacancy rate of each parking lot; a first input module 408 for inputting the historical vacancy rate of each parking lot into the feature extraction network to obtain a first feature, where the first feature is used to characterize the time-dependent relationship of the historical vacancy rate of each parking lot; a construction module 404 for constructing a spatial relationship graph between each parking lot within the area to be predicted; A second input module 410 for inputting the spatial relationship graph and the first feature into the graph fusion network to obtain a fused feature; An output module 414 for inputting the fused feature into the result prediction network to obtain the vacancy rate of the parking spaces in each parking lot within the area to be predicted at the time to be predicted.

[0078] Optionally, the first input module 408 specifically: Inputs the historical vacancy rate of each parking lot into the feature extraction network and is used to obtain a second feature, and the second feature is used to characterize the similarity of the historical vacancy rates of each parking lot. Specifically, the second input module 410: Is used to input the spatial relationship graph, the first feature, and the second feature into the graph fusion network.

[0079] Optionally, the construction module 404 specifically: Uses each parking lot within the area to be predicted as a node and the distance between each parking lot within the area to be predicted as the edge weight to construct the spatial relationship graph.

[0080] Optionally, the graph fusion network includes an attention network and a graph convolutional network. Specifically, the second input module 410: Inputs the spatial relationship graph, the first feature, and the second feature into the attention network to obtain an attention-weighted output result. Is used to input the output result and the historical vacancy rate of each parking lot into the graph convolutional network.

[0081] Optionally, the parking space vacancy rate prediction model further includes an environmental feature extraction network. The apparatus further includes an environmental information input module 412. Specifically, the environmental information input module 412 acquires environmental information of each parking lot within the area to be predicted before the time to be predicted, the environmental information includes at least weather information and holiday information, inputs the environmental information into the environmental feature extraction network, and is used to obtain environmental features. Specifically, the output module 414 is used to input the first feature, the fusion feature, the environmental feature, and the historical vacancy rate of each parking lot into the result prediction network.

[0082] Optionally, the device further includes a training module 400. Specifically, the training module 400 acquires the vacancy rate of parking spaces in each parking lot within the specified area at at least two historical times. Uses the vacancy rate of parking spaces in each parking lot at the latest historical time among the at least two historical times as a label, and the vacancy rate of parking spaces in each parking lot at other historical times as a sample. Inputs the sample into the feature extraction network to obtain sample features, and the sample features are used to characterize the relationship between the historical vacancy rate of each parking lot and time. Constructs a spatial relationship graph between each parking lot within the specified area as a sample spatial relationship graph. Inputs the sample spatial relationship graph and the sample features into the graph fusion network to obtain sample fusion features. Inputs the sample fusion features into the result prediction network to obtain a prediction result of the vacancy rate of each parking space at the latest historical time in the specified area. Is used to train the vacancy rate prediction model of the parking space with the goal of minimizing the difference between the prediction result of the vacancy rate of each parking space and the label.

[0083] The present disclosure further provides a computer-readable storage medium, which stores a computer program, and the computer program is used to execute the method for predicting the vacancy rate of the parking space described above.

[0084] Based on the method for predicting the vacancy rate of the parking space described above, the present disclosure further provides an electronic device shown in FIG. 5. As shown in FIG. 5, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, an internal memory, and a non-volatile memory. Of course, it may also include other hardware required for other operations. The processor reads the corresponding computer program from the non-volatile memory into the internal memory and executes it to implement the method for predicting the vacancy rate of the parking space described above.

[0085] Of course, in addition to the software implementation, the present disclosure does not exclude other implementation manners such as logical devices and combinations of hardware and software. That is to say, the execution subject of the following processing process is not limited to each logical unit, and it may be hardware or a logical device.

[0086] In the 1990s, improvements in certain technologies could be clearly distinguished between hardware improvements (such as improvements in circuit structures of diodes, transistors, switches, etc.) and software improvements (such as improvements in method flows). However, with the development of technology, many current improvements in method flows can now be regarded as direct improvements to hardware circuit structures. Designers mostly obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be categorically stated that improvements in method flows cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit, and its logical function is determined by programming by the user of the device. Instead of chip manufacturers designing and manufacturing dedicated integrated circuit chips, designers program to "integrate" a digital system onto a single PLD.And currently, instead of making integrated circuit chips by hand, this programming is mostly realized using software called a "logic compiler", which is similar to the software compilers used when writing programs. To compile the previous original code, it is necessary to write in a specific programming language, which is called a Hardware Description Language (HDL). There is not just one type of HDL. There are many types, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. Currently, the most commonly used ones are VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog. It will be obvious to those skilled in the art that a hardware circuit that realizes a logical method flow can be easily obtained just by logically programming the method flow in some of the above hardware description languages and programming it into an integrated circuit.

[0087] The controller may be implemented in any suitable manner. For example, the controller may include a microprocessor or a processor, and a computer-readable storage medium storing computer-readable program code executable by the (micro)processor (such as software or firmware). It may also adopt the form of logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, microcontrollers such as ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller may further be implemented as part of the control logic of the memory. In addition to implementing the controller with pure computer-readable program code, it will be apparent to those skilled in the art that by logically programming method steps, the same functions can also be fully executed by the controller in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller may be regarded as a hardware component, and the devices included therein for realizing various functions may also be regarded as the structure within the hardware component. Or, further, the devices for realizing various functions may be regarded as software modules for realizing the method or the structure within the hardware component.

[0088] The system, apparatus, module, or unit described in the above embodiments may specifically be implemented by a computer chip, an entity, or a product having some function. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a mobile phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet, a wearable device, or any combination of several of these devices.

[0089] For the convenience of description, when the above apparatus is described, it is divided into various units according to functions and described separately. Of course, when implementing the present disclosure, the functions of each unit can also be realized by the same or multiple software and / or hardware.

[0090] As will be understood by those skilled in the art, the embodiments of the present disclosure may be provided as a method, a system, or a computer program product. Therefore, the present disclosure may use forms including embodiments consisting only of hardware, embodiments consisting only of software, or embodiments combining software and hardware. Further, the present disclosure may also be in the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to magnetic disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0091] This disclosure is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device implement the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0092] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction apparatus for implementing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0093] These computer program instructions may also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more flows of the flowchart and / or one or more blocks of the block diagram.

[0094] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0095] The memory may include forms such as volatile memory, random access memory (RAM) and / or non-volatile memory of computer-readable storage media, for example, read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable storage media.

[0096] A computer-readable storage medium includes volatile and non-volatile media, removable and non-removable media, and can implement information storage by any method or technology. The information may be computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory, or other memory technologies, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage, or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible from a computing device. According to the definitions herein, computer-readable storage media does not include transitory media, such as modulated data signals and carriers.

[0097] Also, the term "comprising", "containing", or any other variation thereof is intended to include non-exclusive inclusion, such that a process, method, article, or device that includes a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such a process, method, article, or device. Without further limitation, an element limited by the phrase "comprising one..." does not preclude the presence of additional identical elements in the process, method, article, or device that includes the element.

[0098] As will be appreciated by those skilled in the art, the embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an embodiment consisting of only hardware, an embodiment consisting of only software, or an embodiment combining software and hardware. Furthermore, the present disclosure may be in the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, magnetic disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0099] The present disclosure may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The present disclosure may also be implemented in a distributed computing environment where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media including memory devices.

[0100] Each embodiment in the present disclosure is described in a progressive manner, and the same or similar parts between each embodiment may be referred to each other, and the differences from other embodiments are emphasized in each embodiment. In particular, for the system embodiment, since it is basically similar to the method embodiment, it will be briefly described, and the relevant parts may refer to the description of a part of the method embodiment.

[0101] The above are only embodiments of the present disclosure and are not used to limit the present disclosure. For those skilled in the art, various modifications and changes can be made to the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and principle of the present disclosure should be included in the scope of the claims of the present disclosure.

Claims

1. A method for predicting the vacancy rate of a parking space applied to a computing device, wherein the computing device is provided with a pre-trained vacancy rate prediction model for the parking space, and the vacancy rate prediction model for the parking space includes a feature extraction network, a graph fusion network, and a result prediction network, determining an area to be predicted and a time to be predicted; obtaining the vacancy rate of the parking space at a plurality of times before the time to be predicted for each parking lot in the area to be predicted as the historical vacancy rate of each parking lot; inputting the historical vacancy rate of each parking lot into the feature extraction network to obtain a first feature, wherein the first feature is used to characterize the time-dependent relationship of the historical vacancy rate of each parking lot; constructing a spatial relationship graph among the parking lots in the area to be predicted; inputting the spatial relationship graph and the first feature into the graph fusion network to obtain a fused feature; inputting the fused feature into the result prediction network to obtain the vacancy rate of the parking space of each parking lot in the area to be predicted at the time to be predicted, characterized by a method for predicting the vacancy rate of a parking space.

2. Before inputting the spatial relationship graph and the first feature into the graph fusion network, inputting the historical vacancy rate of each parking lot into the feature extraction network to obtain a second feature, wherein the second feature is used to characterize the similarity of the historical vacancy rate of each parking lot, further including the step of the step of inputting the spatial relationship graph and the first feature into the graph fusion network further includes the step of inputting the spatial relationship graph, the first feature and the second feature into the graph fusion network, characterized by the method according to claim 1.

3. The step of constructing a spatial relationship graph among the parking lots in the area to be predicted includes constructing the spatial relationship graph with each parking lot in the area to be predicted as a node and the distance between each parking lot in the area to be predicted as the weight of the edge, characterized by the method according to claim 1 or 2.

4. The graph fusion network includes an attention network and a graph convolutional network. The step of inputting the spatial relationship graph, the first feature, and the second feature into the graph fusion network is as follows: Inputting the spatial relationship graph, the first feature, and the second feature into the attention network to obtain an attention-weighted output result; Inputting the output result and the historical vacancy rate of each parking lot into the graph convolutional network. The method according to claim 2 or 3, characterized in that.

5. The parking space vacancy rate prediction model further includes an environmental feature extraction network. Before inputting the fused feature into the result prediction network, Obtaining environmental information of each parking lot in the area to be predicted before the time to be predicted, where the environmental information includes at least weather information and holiday information; Inputting the environmental information into the environmental feature extraction network to obtain environmental features. The step of inputting the fused feature into the result prediction network is as follows: Further including the step of inputting the first feature, the fused feature, the environmental feature, and the historical vacancy rate of each parking lot into the result prediction network. The method according to any one of claims 1 to 4, characterized in that.

6. The parking space vacancy rate prediction model is as follows: Obtaining the vacancy rate of the parking space of each parking lot in the specified area at at least two historical times; Using the vacancy rate of the parking space of each parking lot at the latest historical time among the at least two historical times as a label, and using the vacancy rate of the parking space of each parking lot at other historical times as a sample; Inputting the sample into the feature extraction network to obtain a sample feature, where the sample feature is used to characterize the relationship between the historical vacancy rate of each parking lot and time; Constructing a spatial relationship graph between each parking lot in the specified area as a sample spatial relationship graph; Inputting the sample spatial relationship graph and the sample feature into the graph fusion network to obtain a sample fusion feature; Inputting the sample fusion feature into the result prediction network to obtain a prediction result of the vacancy rate of each parking space in the specified area at the latest historical time. A method of training a vacancy rate prediction model for a parking space, including a step of training the vacancy rate prediction model for the parking space with an optimization goal of minimizing a difference between a prediction result of a vacancy rate of each parking space and the label. The method according to any one of claims 1 to 5, characterized in that.

7. A prediction device for a vacancy rate of a parking space, in which a pre-trained vacancy rate prediction model for the parking space is arranged, and the vacancy rate prediction model for the parking space includes a feature extraction network, a graph fusion network, and a result prediction network. A determination module for determining an area to be predicted and a time to be predicted. An acquisition module for acquiring, as a historical vacancy rate of each parking lot, a vacancy rate of a parking space at a plurality of times before the time to be predicted in each parking lot within the area to be predicted. A first input module for inputting the historical vacancy rate of each parking lot into the feature extraction network to obtain a first feature, where the first feature is used to characterize a time-dependent relationship of the historical vacancy rate of each parking lot. A construction module for constructing a spatial relationship graph between each parking lot within the area to be predicted. A second input module for inputting the spatial relationship graph and the first feature into the graph fusion network to obtain a fusion feature. An output module for inputting the fusion feature into the result prediction network to obtain a vacancy rate of a parking space in each parking lot within the area to be predicted at the time to be predicted. A prediction device for a vacancy rate of a parking space, characterized in that.

8. The first input module is used to input the historical vacancy rate of each parking lot into the feature extraction network to obtain a second feature, where the second feature is used to characterize the similarity of the historical vacancy rate of each parking lot. The second input module is used to input the spatial relationship graph, the first feature, and the second feature into the graph fusion network. The device according to claim 7, characterized in that.

9. The construction module is used to construct the spatial relationship graph with each parking lot within the area to be predicted as a node and the distance between each parking lot within the area to be predicted as the weight of an edge. The device according to claim 7 or 8, characterized in that.

10. The graph fusion network includes an attention network and a graph convolutional network, The second input module, inputs the spatial relationship graph, the first feature, and the second feature into the attention network to obtain an output result with attention weights, and is used to input the output result and the historical vacancy rate of each parking lot into the graph convolutional network, The apparatus according to claim 8 or 9, characterized in that.

11. The parking space vacancy rate prediction model further includes an environmental feature extraction network, and further includes an environmental information input module, The environmental information input module, obtains the environmental information of each parking lot in the area to be predicted before the time to be predicted, the environmental information includes at least weather information and holiday information, and inputs the environmental information into the environmental feature extraction network to obtain environmental features, which are used for this purpose, The output module, is used to input the first feature, the fusion feature, the environmental feature, and the historical vacancy rate of each parking lot into the result prediction network, The apparatus according to any one of claims 7 to 10, characterized in that.

12. The apparatus further includes a training module, The training module, obtains the vacancy rate of the parking space at at least two historical times of each parking lot in the specified area, uses the vacancy rate of the parking space of each parking lot at the latest historical time among the at least two historical times as the label, and uses the vacancy rate of the parking space of each parking lot at other historical times as the sample, inputs the sample into the feature extraction network to obtain sample features, and the sample features are used to characterize the relationship between the historical vacancy rate of each parking lot and time, constructs the spatial relationship graph between each parking lot in the specified area as the sample spatial relationship graph, inputs the sample spatial relationship graph and the sample features into the graph fusion network to obtain sample fusion features, inputs the sample fusion features into the result prediction network to obtain the prediction result of the vacancy rate of each parking space at the latest historical time in the specified area, and is used to train the parking space vacancy rate prediction model with the goal of minimizing the difference between the prediction result of the vacancy rate of each parking space and the label. The apparatus according to any one of claims 7 to 11, characterized in that...

13. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented. A computer-readable storage medium, characterized in that...

14. An electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented. An electronic device, characterized in that...

Images