Parking space determination method, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a parking space determination method, electronic equipment and a storage medium, and the electronic equipment obtains the identity information of a target vehicle when the target vehicle enters a parking lot; determining whether the target vehicle is a first vehicle according to the identity information; wherein the first vehicle represents a vehicle having a parking record in the parking lot; if it is determined that the target vehicle is the first vehicle, candidate parking spaces corresponding to the target vehicle are determined based on a parking preference analysis model; wherein the parking preference analysis model comprises a first decision tree model corresponding to each vehicle and constructed based on parking record data of each vehicle with parking records in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot; and the target parking space of the target vehicle is determined based on the candidate parking spaces, so that the parking space determination efficiency can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a parking space determination method, an electronic device, and a storage medium. Background Art

[0002] Current parking space determination methods mostly use optimization algorithms, such as ant colony algorithm, particle swarm algorithm, simulated annealing algorithm, etc. These methods determine the parking space closest to the target vehicle through multiple searches and iterations; however, these algorithms usually require repeated iterations, and have high time complexity and space complexity. Therefore, when using these algorithms to determine parking spaces, there is a general defect of low efficiency. Summary of the invention

[0003] The embodiments of the present application provide a parking space determination method, an electronic device, and a storage medium, which can effectively improve the efficiency of parking space determination.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] In a first aspect, an embodiment of the present application provides a parking space determination method, the method comprising:

[0006] When the target vehicle enters the parking lot, obtaining the identity information of the target vehicle;

[0007] Determine whether the target vehicle is a first vehicle according to the identity information; wherein the first vehicle represents a vehicle that has a parking record in the parking lot;

[0008] If it is determined that the target vehicle is the first vehicle, a candidate parking space corresponding to the target vehicle is determined based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on parking record data of each vehicle having parking records in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot;

[0009] A target parking space for the target vehicle is determined based on the candidate parking spaces.

[0010] In a second aspect, an embodiment of the present application provides an electronic device, the electronic device comprising an acquisition unit and a determination unit,

[0011] The acquisition unit is used to acquire the identity information of the target vehicle when the target vehicle enters the parking lot;

[0012] The determination unit is used to determine whether the target vehicle is a first vehicle according to the identity information; wherein the first vehicle represents a vehicle that has a parking record in the parking lot; if the target vehicle is determined to be the first vehicle, a candidate parking space corresponding to the target vehicle is determined based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on parking record data of each vehicle that has a parking record in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot; a target parking space for the target vehicle is determined based on the candidate parking spaces.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory storing instructions executable by the processor; when the instructions are executed by the processor, the above-mentioned parking space determination method is implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned parking space determination method is implemented.

[0015] An embodiment of the present application provides a parking space determination method, an electronic device, and a storage medium. When a target vehicle enters a parking lot, the electronic device obtains identity information of a target vehicle; determines whether the target vehicle is a first vehicle based on the identity information; wherein the first vehicle represents a vehicle that has a parking record in the parking lot; if the target vehicle is determined to be the first vehicle, determines a candidate parking space corresponding to the target vehicle based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on parking record data of each vehicle that has a parking record in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot; and determines a target parking space for the target vehicle based on the candidate parking spaces. It can be seen that when allocating a parking space to a target vehicle currently entering the parking lot, the present application first determines whether the target vehicle has a parking record in the parking lot. If so, the candidate parking space for the target vehicle is determined based on the parking preference analysis model; and since the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on the parking record data of each vehicle with a parking record in the parking lot, and a second decision tree model constructed based on the parking record data set of the parking lot, the parking preference analysis model takes into account both the personalized needs of different vehicles when parking and the generalized properties of the parking data of all vehicles. Therefore, based on the parking preference analysis model, the candidate parking space corresponding to the target vehicle can be analyzed more accurately and effectively, and then the target parking space can be selected from the candidate parking spaces, which can greatly reduce the complexity of the parking space determination method and thus improve the efficiency of parking space determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Schematic diagram of the implementation process of the parking space determination method proposed in the embodiment of the present application Figure 1 ;

[0017] Figure 2 Schematic diagram of the implementation process of the parking space determination method proposed in the embodiment of the present application Figure 2 ;

[0018] Figure 3 Schematic diagram of the composition structure of the electronic device proposed in the embodiment of the present application Figure 1 ;

[0019] Figure 4 Schematic diagram of the composition structure of the electronic device proposed in the embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. It is understood that the specific embodiments described herein are only used to explain the related applications, rather than to limit the applications. It should also be noted that, for ease of description, only the parts related to the related applications are shown in the drawings.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0022] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0023] The current parking space determination methods mostly use optimization algorithms, such as ant colony algorithm, particle swarm algorithm, simulated annealing algorithm, etc., which aim to solve the problem of how the target vehicle reaches the nearest parking space through multiple searches and iterations. In addition, fuzzy algorithms and game theory algorithms are also used to solve the problem of determining the parking space of the target user. The existing technical solutions mainly have the disadvantages of high algorithm solution complexity, high algorithm resource requirements, weak interaction with the environment, and low resource utilization. The parking tendency of the target user is the result of the interaction between the environment and the user's intention, but the existing technical solutions mostly consider information related to the target vehicle, and do not consider the influence of factors other than the target vehicle on the user's choice of parking space. It does not combine the environment with user information, and has low resource utilization. On the other hand, when looking for the best parking space, the existing technical solutions mostly use optimization algorithms to solve, and the optimization algorithms often have the problems of many solution parameters and low solution efficiency. For example, some technical solutions use greedy control methods and simulated annealing algorithms to output one-to-one and many-to-many parking results respectively; however, the greedy control method is essentially a first-come-first-served greedy control strategy. First-come-first-served requires that parking services need to be processed in sequence, which can easily lead to the problem of long average waiting time; for the simulated annealing algorithm, the search time and results of the optimal parking solution are affected by the temperature cooling rate. The lower the cooling rate means the more optimization iterations and the longer the search time; although reducing the number of optimization iterations can reduce the search time, it will also result in the situation of skipping the optimal solution; not only that, the optimization algorithms all have common shortcomings such as slow convergence speed, no definite termination criteria, and more control parameters, which can easily lead to problems such as low efficiency in solving the optimal solution for parking solutions based on such methods and high algorithm space complexity.

[0024] In order to solve the above problems, in an embodiment of the present application, the electronic device obtains the identity information of the target vehicle when the target vehicle enters the parking lot; determines whether the target vehicle is the first vehicle based on the identity information; wherein the first vehicle represents a vehicle that has a parking record in the parking lot; if the target vehicle is determined to be the first vehicle, the candidate parking space corresponding to the target vehicle is determined based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on the parking record data of each vehicle that has a parking record in the parking lot, and a second decision tree model constructed based on the parking record data set of the parking lot; determines the target parking space of the target vehicle based on the candidate parking spaces; and can effectively improve the efficiency of determining parking spaces.

[0025] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0026] Figure 1 Schematic diagram of the implementation process of the parking space determination method proposed in the embodiment of the present application Figure 1 ,like Figure 1 As shown, in an embodiment of the present application, the method for an electronic device to determine a parking space may include the following steps:

[0027] Step 101: When a target vehicle enters a parking lot, obtain the identity information of the target vehicle.

[0028] In an embodiment of the present application, the electronic device may first obtain the identity information of the target vehicle when the target vehicle enters the parking lot.

[0029] In an embodiment of the present application, a camera may be deployed in the parking lot, and the electronic device may obtain the identity information of the target vehicle based on the camera shooting; wherein the identity information of the target vehicle may be the license plate information of the target vehicle, such as the license plate number.

[0030] It can be understood that, in the embodiment of the present application, the target vehicle is the vehicle that currently enters the parking lot and whose corresponding parking space needs to be determined.

[0031] It should be noted that, in the embodiments of the present application, the electronic device may be any device with communication and storage functions, for example, the electronic device may be a personal computer (PC), a laptop computer or other electronic device.

[0032] Step 102: Determine whether the target vehicle is a first vehicle based on the identity information; wherein the first vehicle represents a vehicle that has a parking record in the parking lot.

[0033] In an embodiment of the present application, when a target vehicle enters a parking lot, the electronic device can determine whether the target vehicle is a first vehicle based on the identity information after obtaining the identity information of the target vehicle; wherein the first vehicle represents a vehicle that has a parking record in the parking lot.

[0034] Step 103: If the target vehicle is determined to be the first vehicle, a candidate parking space corresponding to the target vehicle is determined based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on parking record data of each vehicle having a parking record in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot.

[0035] In an embodiment of the present application, after the electronic device determines whether the target vehicle is the first vehicle based on the identity information, if it is determined that the target vehicle is the first vehicle, it determines the candidate parking space corresponding to the target vehicle based on the parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on the parking record data of each vehicle with a parking record in the parking lot, and a second decision tree model constructed based on the parking record data set of the parking lot.

[0036] It should be noted that, in the embodiments of the present application, the first decision tree model may be an ID3 decision tree model, and the second decision tree model may be a CART decision tree model.

[0037] In some embodiments of the present application, before the electronic device determines the candidate parking space corresponding to the target vehicle based on the parking preference analysis model, it can first construct a first decision tree model; when constructing the first decision tree model, the electronic device can obtain historical parking data of the parking lot; wherein the historical parking data includes relevant parking data corresponding to vehicles with parking records in the parking lot; pre-processing the historical parking data to obtain processed historical parking data; and determining the parking record data of each vehicle based on the processed historical parking data.

[0038] It should be noted that data preprocessing can be data cleaning of historical parking data; historical parking data can be obtained by processing parking lot camera data and edge cloud server reporting data through fusion perception algorithm, and when the parking lot environment is dim or the license plate is obscured, there may be problems with incomplete data collection, so it is necessary to clean the historical parking data, such as eliminating data with missing license plate features in the historical parking data, so as to obtain the cleaned historical parking data.

[0039] It should be noted that, in an embodiment of the present application, the parking record data includes at least one of first distance information, first attribute label, second distance information, second attribute label, path congestion information, obstacle information, parking space length information, parking space width information, first average distance information, second average distance information, charging pile parking space information and path preference information.

[0040] In some embodiments of the present application, when the electronic device constructs the first decision tree model based on the parking record data, it can perform one-hot encoding on the parking record data of each vehicle to obtain the encoded parking data corresponding to each vehicle; thereby constructing the first decision tree model based on the encoded parking data.

[0041] In some embodiments of the present application, when determining the first distance information and the first attribute label, the electronic device can determine the distance between the target parking space of each vehicle and each elevator hall in the parking lot in the processed historical parking data to obtain the first distance information; determine the first attribute label corresponding to the target parking space of each vehicle based on the first distance information and the first threshold; wherein the first attribute label includes a near elevator hall label and a not near elevator hall label; the first distance information can be a Euclidean distance.

[0042] It should be noted that when the minimum value in the first distance information corresponding to a vehicle is less than the first threshold, the first attribute label is a near elevator hall label; when the minimum value in the first distance information corresponding to a vehicle is greater than or equal to the first threshold, the first attribute label is a not near elevator hall label; the specific value of the first threshold is not limited in this application.

[0043] For example, in the processed historical parking data, the latitude and longitude position of a parking space (target parking space) of a certain vehicle is recorded as P obj (x p ,y p ), the position of each elevator hall in the parking lot is recorded as P e1 (x1, y1), ..., P en (x n ,y n ), where n is the number of elevator halls, n ≥ 1; then P can be calculated obj (x p ,y p ) respectively with P e1 (x1, y1), ..., P en (x n ,y n ) to obtain the first distance information; calculate the minimum value of the distance between the target parking space and each elevator hall, that is, the minimum value in the first distance information of the vehicle is P min =min{euclidean(P obj , P e1 )、…、euclidean(P obj , P en )}, and the first threshold is EP dis , when P min Less than EP dis When P is , the target parking space is considered to be near the elevator hall, and the first attribute label is the near elevator hall label. min Greater than or equal to EP dis When , the first attribute label is the non-near elevator hall label.

[0044] In some embodiments of the present application, when determining the second distance information and the second attribute tag, the electronic device may determine the distance between the target parking space of each vehicle and the exit of the parking lot in the processed historical parking data to obtain the second distance information; determine the second attribute tag corresponding to the target parking space of each vehicle based on the second distance information and the second threshold; wherein the second attribute tag includes a near exit tag and a non-near exit tag; the second distance information may be a Euclidean distance.

[0045] It should be noted that when the minimum value in the second distance information corresponding to a vehicle is less than the second threshold, the second attribute label is a near-exit label; when the minimum value in the second distance information corresponding to a vehicle is greater than or equal to the second threshold, the second attribute label is a non-near-exit label; the specific value of the second threshold is not limited in this application.

[0046] For example, the latitude and longitude of the exit lift position of the parking lot is recorded as R1(x p1 ,y p1 ),…,R m (x pm ,y pm ), where m is the number of exits of the parking lot, m≥1; calculating the Euclidean distance between the target parking space of a vehicle in the processed historical parking data and the exits of each parking lot, and obtaining the second distance information corresponding to the vehicle; calculating the minimum value R in the second distance information m in = min{euclidean(P obj , R1), ..., euclidean (P obj , R m )}, the second threshold is RP dis ; When R min Less than RP dis When , the vehicle is considered to be parked near the exit of the parking lot, and the second attribute label is the near exit label; and when R min Greater than or equal to RP dis When , the second attribute label is a non-near-exit label.

[0047] It can be seen from this that the present application can calculate the Euclidean distance relationship between the parking space of each vehicle in the historical parking data and the parking lot exit and elevator hall based on the latitude and longitude coordinates of the parking space in the high-precision map and the latitude and longitude coordinates of the parking lot exit and elevator hall, thereby adding any one or more attribute labels of near the elevator hall, not near the elevator hall, near the exit and not near the exit to the parking space of each vehicle in the historical parking data.

[0048] In some embodiments of the present application, path congestion information represents the path congestion information to reach the target parking space of each vehicle; obstacle information represents the number of vehicles parked on the left and right sides of the target parking space of each vehicle; parking space length information represents the length information of the target parking space; parking space width information represents the width information of the target parking space; charging pile parking space information is used to determine whether the target parking space is a charging pile parking space; path preference information represents the path shape information of each vehicle entering its respective target parking space; wherein, the path preference information includes straight line driving information and broken line driving information.

[0049] It should be noted that due to the different driving skills of different users, the obstacles around their parking spaces are also one of the factors that determine whether the user enters the parking space; therefore, this application collects information on the number of vehicles parked on the left and right sides of the target parking space of each user's vehicle in historical parking data, and can divide the obstacle information into: the number of obstacles is 0, the number of obstacles is 1, and the number of obstacles is 2, for example, respectively recorded as obstacle 0, obstacle 1, and obstacle 2; wherein the obstacle information can be obtained by capturing and identifying by cameras in the parking lot.

[0050] It should be noted that the size of the parking space is also a factor in determining the target vehicle's entry. Generally speaking, the larger the parking space area, the easier it is for the user to park in the parking space, and the higher the user's tendency to park in this parking space. This application uses parking space length information and parking space width information to characterize the relevant data of the parking space size.

[0051] It should be noted that the present application can also determine whether each parking space is a charging pile parking space, thereby determining whether the target parking space of each vehicle in the processed historical parking data is a charging pile parking space.

[0052] In some embodiments of the present application, the type of vehicle can be determined by obtaining the color of the vehicle's license plate. For example, a green license plate is determined to be a rechargeable vehicle, and any other license plate color is determined to be a non-rechargeable vehicle. Furthermore, when the target vehicle is determined to be a non-rechargeable vehicle based on the color of its license plate, when determining the target parking space for the target vehicle, considering that the number of parking spaces with charging piles in most parking lots is less than that without charging piles, non-rechargeable vehicles are not recommended to park in charging pile spaces.

[0053] In some embodiments of the present application, when the electronic device determines that the target vehicle is a non-chargeable vehicle, when determining the target parking space for the target vehicle based on the candidate parking spaces, the electronic device may eliminate the charging pile spaces among the candidate parking spaces to obtain a first candidate parking space; and then determine the target parking space based on the first candidate parking space.

[0054] Furthermore, in an embodiment of the present application, since the charging pile parking space in the parking lot has been determined, the target parking space of the chargeable vehicle can be associated with the charging pile parking space information in the high-precision map. For example, when the charging pile parking space identity identification number (Identity document, ID) is consistent with the parking space ID of the chargeable vehicle, the chargeable vehicle is deemed to have parked in the charging pile parking space.

[0055] It should be noted that in the embodiments of the present application, a k-means clustering model can also be established based on the historical parking path information of all vehicles in the processed historical parking data, and the driving route preference corresponding to each vehicle, that is, the path preference information, can be determined through cluster analysis. The present application classifies straight driving routes (straight driving information) into one type of preference and zigzag driving routes (zigzag driving information) into another type of preference.

[0056] In some embodiments of the present application, when determining the first average distance information and the second average distance information, the electronic device may calculate the average value of the distances between the candidate parking spaces corresponding to each vehicle in the processed historical parking data and each elevator hall in the parking lot to obtain the first average distance information; and calculate the average value of the distances between the candidate parking spaces for each vehicle in the processed historical parking data and the exit of the parking lot to obtain the second average distance information.

[0057] It should be noted that in the embodiments of the present application, in the historical parking data, each vehicle has multiple candidate parking spaces in addition to the final target parking space, and the candidate parking spaces have a certain correlation with the preferences of the user driving the vehicle. Therefore, the distance between the historical candidate parking spaces other than the target parking space where the user parks and the elevator hall, and the distance between the candidate parking spaces and the parking lot exit are also taken into consideration.

[0058] For example, in the processed historical parking data, for a certain vehicle, the distances between k (k ≥ 1) candidate parking spaces and the elevator hall generated by the parking space determination method proposed in this embodiment are recorded as {P tmp1 , P tmp2 , ..., P tmpk}, then the average value of the distance between the candidate parking spaces and the elevator hall, that is, the first average distance information, can be expressed as:

[0059] For example, in the processed historical parking data, for a certain vehicle, the distances between q (q≥1) candidate parking spaces generated by the parking space determination method proposed in this embodiment and the parking lot exit are recorded as {R tmp1 , P tmp2 , ..., P tmpq}, then the average value of the distance between the candidate parking space and the parking lot exit, that is, the second average distance information, can be expressed as

[0060] For example, the parking record data may be as shown in Table 1 below:

[0061] Table 1

[0062]

[0063] Exemplarily, the data obtained after the first distance information, the second distance information, the path congestion information, the obstacle information, the parking space length information, the parking space width information, the first average distance information, the second average distance information and the path preference information in the parking record data of the vehicle i are processed by unique hot encoding is recorded as D i ={x1, ..., x a , ..., x d}, where x1,…,x d Represents data features, such as x1,…,x d It may correspond to the first distance information, the second distance information, the path congestion information, the obstacle information, the parking space length information, the parking space width information, the first average distance information, the second average distance information and the path preference information respectively.

[0064] It should be noted that, in the embodiment of the present application, since the parking record data also includes attribute label information such as the first attribute label, the second attribute label, and the charging pile parking space information, in order to construct the subsequent model, the above text or text attribute label information can also be converted into structured data by using one-hot encoding processing; thus, after all the text or text data in the parking record data are subjected to one-hot encoding processing, the encoded parking data can be obtained; for example, the encoded parking data is recorded as L={(D1, y1),…,(D i ,y i )}; where y i The data obtained after the attribute label information corresponding to vehicle i is one-hot encoded.

[0065] In an embodiment of the present application, the parking preference analysis model can understand the important factors that affect the user's choice of parking space based on historical data characteristics, and then help the user to provide parking guidance that meets the user's expectations when entering the parking lot again; therefore, the parking preference analysis model is mainly aimed at users with a history of parking; the preference analysis model can be constructed based on the idea of ​​random forest, combining the uncertainty sampling decision tree method of random forest with the decision tree method constructed by a single user sample (parking record data of each vehicle), taking into account both generalization attributes and personalized needs, to obtain better analysis results.

[0066] In some embodiments of the present application, when constructing the first decision tree model, the license plate number can be used as the unique identifier of the vehicle, and a corresponding ID3 decision tree can be established for the vehicle; the process of building the first decision tree model is explained by taking vehicle i as an example: starting from the root node, the encoded parking data D is calculated for the node j The information gain of the data features in, where D j The features in can have corresponding attribute label information; for example, D i The first distance information encoded in y i Corresponding to the first attribute label in D i The second distance information encoded in i Corresponding to the second attribute label in; the calculation formula of information gain can be expressed as: x a That is D i A data feature in the data feature x a There are U possible values, expressed as If you use x a Right D i If the partition is performed, U branch nodes will be generated, among which the μth branch node contains D i All the features in the data x a The upper value is The sample is Ent(D i ) means D i The information entropy of Among them, p k Indicates D i Middle y k The proportion of class samples, s represents D i The number of label types included; according to D i Information entropy Ent(D i ), and considering that different branch nodes contain different numbers of samples, weights are assigned to branch nodes. The larger the information gain, the greater the data feature x. a The stronger the impact on the vehicle's parking position selection, the data feature with the largest information gain is selected as the node feature, and the attribute label corresponding to the data feature with the largest information gain can be used as the most inclined preference label; sub-nodes are established by different values ​​of the data feature, and then the above method is recursively called on the sub-nodes to construct a decision tree, until the information gain of all data features is very small or no data features can be selected, and the first decision tree model corresponding to vehicle i is obtained; the first decision tree model can predict the parking preference of vehicle i and obtain the preference label of vehicle i.

[0067] In some embodiments of the present application, due to the limitation of sample quantity, it is difficult to make the model have good generalization performance and classification accuracy by only establishing a separate decision tree for independent users, i.e., each vehicle; therefore, after establishing the first decision tree model corresponding to each vehicle, the present application can also randomly extract samples and features to form a training set for the parking record data set of all vehicles or users in the parking lot to construct a CART decision tree (second decision tree model); different from the ID3 decision tree of the first decision tree model, the CART decision tree uses the Gini coefficient to divide attributes.

[0068] Furthermore, in an embodiment of the present application, the electronic device can also collect the results generated by the first decision tree model and the second decision tree model obtained based on the parking record data of the parking lot, for example, t results, and use the relative majority voting method to confirm the final classification result, that is, predicting the preference label with the highest votes. If multiple preference labels receive the highest votes at the same time, one is randomly selected as the final preference label result; the model has good noise resistance, and its generalization performance and classification ability are far superior to a single decision tree.

[0069] Exemplarily, the output result of the parking preference analysis model is H, Among them, h i represents a decision tree classifier whose class label set is {h1,...,h t}.

[0070] In some embodiments of the present application, when determining candidate parking spaces using a parking preference analysis model, a preference label result corresponding to the target vehicle can be first obtained based on the parking preference analysis model, and then matching processing is performed based on the preference label result and the vacant parking spaces in the parking lot to obtain the candidate parking spaces.

[0071] For example, after the target vehicle enters the parking lot, the electronic device determines the target vehicle's preference tag result h based on the target vehicle's license plate information and the parking preference analysis model. p , and then traverse the current free parking spaces in the parking lot, obtain the attribute labels corresponding to the free parking spaces, and p and the attribute labels corresponding to the vacant parking spaces; when the preference label result h p When there is a match in the attribute tag corresponding to the vacant parking space, the vacant parking space corresponding to the matching attribute tag is taken as a candidate parking space; for example, the candidate parking space set is represented as G = {θ1, ..., θ g}, where g is the number of candidate parking spaces.

[0072] Step 104: Determine a target parking space for the target vehicle based on the candidate parking spaces.

[0073] In an embodiment of the present application, if the electronic device determines that the target vehicle is the first vehicle, after determining the candidate parking space corresponding to the target vehicle based on the parking preference analysis model, the target parking space of the target vehicle can be determined based on the candidate parking space.

[0074] In some embodiments of the present application, when the electronic device determines the target parking space of the target vehicle based on the candidate parking spaces, it can determine the distance between the candidate parking spaces and the real-time location information of the target vehicle, and then determine the target parking space according to the shortest distance between the candidate parking spaces and the real-time location information of the target vehicle.

[0075] It should be noted that, in the embodiment of the present application, the distance between the candidate parking space and the real-time position information of the target vehicle may be the Euclidean distance.

[0076] Exemplarily, based on the longitude and latitude of each candidate parking space in the candidate parking space set G, the Euclidean distance between each candidate parking space and the real-time position information of the target vehicle is calculated respectively, and the parking space corresponding to the shortest Euclidean distance is taken as the target parking space, which is recorded as F°.

[0077] In some embodiments of the present application, the electronic device may also take into account the parking difficulty information of each candidate parking space when determining the target parking space; wherein the parking difficulty information of the candidate parking space may be information about the number of cars parked on the left and right sides of the candidate parking space, and the parking difficulty information may be 0, 1, or 2.

[0078] Exemplarily, after obtaining the parking space corresponding to the shortest Euclidean distance, the electronic device can determine the parking difficulty information of the parking space corresponding to the shortest Euclidean distance; if it is determined that the parking difficulty information is less than or equal to 1 (the parking difficulty measurement threshold), the parking space corresponding to the shortest Euclidean distance can be determined as the target parking space; if it is determined that the parking difficulty information is greater than 1, the alternative parking space can continue to be determined based on the Euclidean distances between each candidate parking space and the real-time position information of the target vehicle, except for the shortest Euclidean distance, until the parking difficulty information of the alternative parking space is less than or equal to 1, the alternative parking space is determined as the target parking space; wherein, the parking difficulty measurement threshold can be set according to the actual usage scenario, and this application does not make any specific limitation.

[0079] In some embodiments of the present application, the electronic device can also generate a global path from the real-time position information of the target vehicle to the target parking space based on the A-star search algorithm (A-starAlgorithm), and send the global path information to the target vehicle to guide the target vehicle into the target parking space.

[0080] For example, the electronic device generates a map from the real-time position of the target vehicle to the target parking space F based on the A star search algorithm. ° The global path of the target vehicle is used to guide the target vehicle into the target parking space.

[0081] In some embodiments of the present application, the electronic device can determine the optimal path from the real-time position of the target vehicle to the target parking space based on the A-star search algorithm and the real-time path congestion, and send the optimal path to the target vehicle to guide the target vehicle into the target parking space; wherein, the optimal path represents the path from the real-time position of the target vehicle to the target parking space with the shortest distance and the lowest path congestion; thereby reducing or even avoiding the situation where the target vehicle encounters congested sections on the path to enter the target parking space, effectively improving the traffic efficiency of the target vehicle.

[0082] In some embodiments of the present application, the electronic device can also synchronously calculate the Euclidean distance between the current real-time position of the target vehicle and the global path corresponding to the target parking space during the driving process of the target vehicle, for example, calculating the Euclidean distance between the current real-time longitude and latitude information (real-time position) of the target vehicle and the global path corresponding to the target parking space; when the distance data of a preset number of frames, such as the Euclidean distance of continuous α frame data, are all greater than the deviation threshold, it can be determined that the target vehicle has shifted, and the nearest candidate parking space is reassigned to the target vehicle as the target parking space, and corresponding guidance path information is generated to guide the target vehicle into the new target parking space.

[0083] It should be noted that in the embodiments of the present application, the values ​​of the preset number of frames and the deviation threshold are not limited in this application.

[0084] In an embodiment of the present application, when the target vehicle is the first vehicle, the electronic device determines the candidate parking spaces of the target vehicle based on the parking preference analysis model, and then determines the target parking spaces based on the candidate parking spaces. This process can be understood as obtaining the candidate parking spaces using static factor information, and then obtaining the target parking spaces based on the dynamic factor information and the static factor information. The static factor information may be relevant information of the target vehicle in the parking record data, such as the target vehicle's license plate information, path preference information, parking space length and width information, parking preferences (such as near elevator halls, charging pile parking spaces, near exits), and obstacle information. The dynamic factor information may include vacant parking space information, real-time path congestion conditions, global path deviation detection information, parking difficulty information of candidate parking spaces, and the real-time position of the target vehicle. This enables the deduction of the target parking space that is most suitable for the target vehicle to park.

[0085] In the embodiments of the present application, Figure 2As shown, after the electronic device determines whether the target vehicle is the first vehicle according to the identity information, that is, after step 102, it may further include the following steps:

[0086] Step 105: If it is determined that the target vehicle is not the first vehicle, a target parking space is determined among the vacant parking spaces in the parking lot based on the real-time position information of the target vehicle.

[0087] In an embodiment of the present application, after the electronic device determines whether the target vehicle is the first vehicle based on the identity information, if it is determined that the target vehicle is not the first vehicle, it determines the target parking space among the vacant parking spaces in the parking lot based on the real-time location information of the target vehicle.

[0088] It should be noted that, in an embodiment of the present application, the electronic device can update the free parking spaces in the parking lot in real time. When the target vehicle enters the parking lot, if the target vehicle is not the first vehicle, the electronic device can calculate the distance between the real-time position of the target vehicle and the free parking spaces in the parking lot, and determine the free parking space corresponding to the shortest distance between the real-time position and the free parking spaces in the parking lot as the target parking space; wherein, the Euclidean distance can be used to calculate the distance between the real-time position of the target vehicle and the free parking spaces in the parking lot.

[0089] Exemplarily, for a target vehicle that is not the first vehicle, the electronic device determines the shortest distance between the real-time position of the target vehicle and each vacant parking space in the parking lot, and determines the parking space corresponding to the shortest distance as the target parking space. It can take the current real-time position of the target vehicle as the starting point and traverse the vacant parking space F that is closest to it, and F can be used as the target parking space; then the electronic device can generate a global path from the current real-time position of the target vehicle to F based on the A-star search algorithm, and send the global path information to the target vehicle to guide the target vehicle into the target parking space.

[0090] In some embodiments of the present application, the electronic device can also synchronously calculate the Euclidean distance between the current real-time position of the target vehicle and the global path corresponding to the target parking space during the driving process of the target vehicle, for example, calculating the Euclidean distance between the current real-time longitude and latitude information (real-time position) of the target vehicle and the global path corresponding to the target parking space; when the distance data of a preset number of frames, such as the Euclidean distance of continuous α frame data, are all greater than the deviation threshold, it can be determined that the target vehicle has shifted, and the nearest vacant parking space is re-assigned to the target vehicle as the target parking space, and corresponding guidance path information is generated to guide the target vehicle into the new target parking space.

[0091] To summarize, the present application realizes a multi-factor data feature mining and processing by processing the parking record data of the parking lot based on clustering methods, feature engineering, and encoding methods, and can extract and mine useful information layer by layer. The parking preference analysis model constructed in this way can be more accurate, and can then perform accurate parking preference analysis on target vehicles with parking records to obtain preference label results, thereby effectively improving the efficiency of parking space determination; at the same time, the present application can combine the high-precision map parking space attribute analysis with the user preference analysis to determine the target parking space, and can allocate parking spaces that suit the users' parking habits to the users. This matching method is simple and feasible, and is not restricted by the external environment of the parking lot.

[0092] Based on the above embodiment, in another embodiment of the present application, Figure 3 Schematic diagram of the composition structure of the electronic device proposed in the embodiment of the present application Figure 1 ,like Figure 3 As shown, the electronic device 10 proposed in the embodiment of the present application may include: an acquisition unit 101, a determination unit 102 and a construction unit 103.

[0093] The acquisition unit 101 is used to acquire the identity information of the target vehicle when the target vehicle enters the parking lot;

[0094] The determination unit 102 is used to determine whether the target vehicle is a first vehicle according to the identity information; wherein the first vehicle represents a vehicle having a parking record in the parking lot; if the target vehicle is determined to be the first vehicle, a candidate parking space corresponding to the target vehicle is determined based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on parking record data of each vehicle having a parking record in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot; a target parking space for the target vehicle is determined based on the candidate parking spaces.

[0095] In some embodiments, the acquisition unit 101 is further used to acquire historical parking data of the parking lot before determining the candidate parking space corresponding to the target vehicle based on the parking preference analysis model when the determination unit 102 determines that the target vehicle is the first vehicle; wherein the historical parking data includes relevant parking data corresponding to vehicles that have parking records in the parking lot; performing data preprocessing on the historical parking data to obtain processed historical parking data; and determining the parking record data of each vehicle based on the processed historical parking data.

[0096] In some embodiments, the determination unit 102 is further used to determine the parking record data of each vehicle based on the processed historical parking data; wherein the parking record data includes at least one of first distance information, first attribute label, second distance information, second attribute label, path congestion information, obstacle information, parking space length information, parking space width information, first average distance information, second average distance information, charging pile parking space information and path preference information.

[0097] The construction unit 103 is configured to construct the first decision tree model based on the parking record data.

[0098] In some embodiments, the construction unit 103 is further configured to perform one-hot encoding on the parking record data of each vehicle to obtain the encoded parking data corresponding to each vehicle; and to construct the first decision tree model based on the encoded parking data.

[0099] In some embodiments, the acquisition unit 101 is also used to determine the distance between the target parking space of each vehicle and each elevator hall in the parking lot in the processed historical parking data to obtain first distance information; and determine the first attribute label corresponding to the target parking space of each vehicle according to the first distance information and the first threshold; wherein the first attribute label includes a near elevator hall label and a not near elevator hall label.

[0100] In some embodiments, the acquisition unit 101 is also used to determine the distance between the target parking space of each vehicle and the exit of the parking lot in the processed historical parking data to obtain the second distance information; and determine the second attribute label corresponding to the target parking space of each vehicle according to the second distance information and the second threshold; wherein the second attribute label includes a near exit label and a non-near exit label.

[0101] In some embodiments, path congestion information represents the path congestion information to reach the target parking space of each vehicle; obstacle information represents the number of vehicles parked on the left and right sides of the target parking space of each vehicle; parking space length information represents the length information of the target parking space; parking space width information represents the width information of the target parking space; charging pile parking space information is used to determine whether the target parking space is a charging pile parking space; path preference information represents the path shape information of each vehicle entering its respective target parking space; wherein, the path preference information includes straight line driving information and broken line driving information.

[0102] In some embodiments, the acquisition unit 101 is also used to calculate the average value of the distance between the candidate parking space corresponding to each vehicle and each elevator hall in the parking lot in the processed historical parking data to obtain first average distance information; and to calculate the average value of the distance between the candidate parking space for each vehicle and the exit of the parking lot in the processed historical parking data to obtain second average distance information.

[0103] In some embodiments, the determination unit 102 is further used to determine whether the target vehicle is the first vehicle according to the identity information, and if it is determined that the target vehicle is not the first vehicle, determine the target parking space among the vacant parking spaces in the parking lot based on the real-time location information of the target vehicle.

[0104] In some embodiments, the determination unit 102 is further configured to eliminate charging pile parking spaces from the candidate parking spaces if the target vehicle is a non-chargeable vehicle to obtain a first candidate parking space; and determine the target parking space based on the first candidate parking space.

[0105] In the embodiments of the present application, further, Figure 4 Schematic diagram of the composition structure of the electronic device proposed in the embodiment of the present application Figure 2 ,like Figure 4 As shown, the electronic device 10 proposed in the embodiment of the present application may also include a processor 104 and a memory 105 storing executable instructions of the processor 104; further, the electronic device 10 may also include a communication interface 106, and a bus 107 for connecting the processor 104, the memory 105 and the communication interface 106.

[0106] In the embodiment of the present application, the processor 104 can be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, and a microprocessor. It can be understood that for different devices, the electronic device used to implement the above-mentioned processor function can also be other, and the embodiment of the present application is not specifically limited. The electronic device 10 can also include a memory 105, which can be connected to the processor 104, wherein the memory 105 is used to store executable program code, the program code includes computer operation instructions, and the memory 105 may include a high-speed RAM memory, and may also include a non-volatile memory, for example, at least two disk memories.

[0107] In the embodiment of the present application, the bus 107 is used to connect the communication interface 106, the processor 104 and the memory 105, and the mutual communication between these devices.

[0108] In the embodiment of the present application, the memory 105 is used to store instructions and data.

[0109] Furthermore, in an embodiment of the present application, the processor 104 is used to obtain identity information of the target vehicle when the target vehicle enters the parking lot; determine whether the target vehicle is a first vehicle based on the identity information; wherein the first vehicle represents a vehicle that has a parking record in the parking lot; if the target vehicle is determined to be the first vehicle, determine a candidate parking space corresponding to the target vehicle based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on parking record data of each vehicle that has a parking record in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot; determine the target parking space of the target vehicle based on the candidate parking spaces.

[0110] In practical applications, the memory 105 may be a volatile memory, such as a random access memory (RAM); or a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); or a combination of the above types of memories, and provide instructions and data to the processor 104.

[0111] In addition, each functional module in this embodiment can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or software functional modules.

[0112] If the integrated unit is implemented in the form of a software function module and is not sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the method of this embodiment. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0113] An embodiment of the present application provides an electronic device, which, when the target vehicle enters a parking lot, obtains identity information of a target vehicle; determines whether the target vehicle is a first vehicle based on the identity information; wherein the first vehicle represents a vehicle that has a parking record in the parking lot; if the target vehicle is determined to be the first vehicle, determines a candidate parking space corresponding to the target vehicle based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on parking record data of each vehicle that has a parking record in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot; and determines a target parking space for the target vehicle based on the candidate parking spaces. It can be seen that when allocating a parking space to a target vehicle currently entering the parking lot, the present application first determines whether the target vehicle has a parking record in the parking lot. If so, the candidate parking space for the target vehicle is determined based on the parking preference analysis model; and since the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on the parking record data of each vehicle with a parking record in the parking lot, and a second decision tree model constructed based on the parking record data set of the parking lot, the parking preference analysis model takes into account both the personalized needs of different vehicles when parking and the generalized properties of the parking data of all vehicles. Therefore, based on the parking preference analysis model, the candidate parking space corresponding to the target vehicle can be analyzed more accurately and effectively, and then the target parking space can be selected from the candidate parking spaces, which can greatly reduce the complexity of the parking space determination method and thus improve the efficiency of parking space determination.

[0114] Specifically, the program instructions corresponding to a parking space determination method in this embodiment may be stored in a storage medium such as a CD, a hard disk, or a USB flash drive. When the program instructions corresponding to a parking space determination method in the storage medium are read or executed by an electronic device, the following steps are included:

[0115] When the target vehicle enters the parking lot, obtaining the identity information of the target vehicle;

[0116] Determining whether the target vehicle is a first vehicle according to the identity information; wherein the first vehicle represents a vehicle that has a parking record in the parking lot;

[0117] If the target vehicle is determined to be the first vehicle, a candidate parking space corresponding to the target vehicle is determined based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on parking record data of each vehicle having parking records in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot;

[0118] A target parking space for the target vehicle is determined based on the candidate parking spaces.

[0119] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of hardware embodiments, software embodiments, or embodiments in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0120] The present application is described with reference to implementation flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0121] 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 specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which is implemented in the implementation flow diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing the steps in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0123] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A parking space determination method, characterized in that: The method comprises: When the target vehicle enters the parking lot, obtaining the identity information of the target vehicle; Determine whether the target vehicle is a first vehicle according to the identity information; wherein the first vehicle represents a vehicle that has a parking record in the parking lot; If it is determined that the target vehicle is the first vehicle, a candidate parking space corresponding to the target vehicle is determined based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on parking record data of each vehicle having parking records in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot; A target parking space for the target vehicle is determined based on the candidate parking spaces.

2. The method according to claim 1, characterized in that: If it is determined that the target vehicle is the first vehicle, before determining the candidate parking space corresponding to the target vehicle based on the parking preference analysis model, the method further includes: Acquire historical parking data of the parking lot; wherein the historical parking data includes relevant parking data corresponding to vehicles having parking records in the parking lot; Performing data preprocessing on the historical parking data to obtain processed historical parking data; Determining the parking record data of each vehicle according to the processed historical parking data; wherein the parking record data includes at least one of first distance information, first attribute label, second distance information, second attribute label, path congestion information, obstacle information, parking space length information, parking space width information, first average distance information, second average distance information, charging pile parking space information, and path preference information; The first decision tree model is constructed based on the parking record data.

3. The method according to claim 2, characterized in that The step of constructing the first decision tree model based on the parking record data includes: Performing one-hot encoding processing on the parking record data of each vehicle to obtain the encoded parking data corresponding to each vehicle; The first decision tree model is constructed based on the encoded parking data.

4. The method according to claim 2, characterized in that: The determining the parking record data of each vehicle according to the processed historical parking data includes: Determine the distance between the target parking space of each vehicle and each elevator hall in the parking lot in the processed historical parking data to obtain the first distance information; The first attribute label corresponding to each target parking space of each vehicle is determined according to the first distance information and the first threshold; wherein the first attribute label includes a near elevator hall label and a not near elevator hall label.

5. The method according to claim 2, characterized in that: The determining the parking record data of each vehicle according to the processed historical parking data includes: Determine the distance between the target parking space of each vehicle and the exit of the parking lot in the processed historical parking data to obtain the second distance information; The second attribute label corresponding to each target parking space of each vehicle is determined according to the second distance information and the second threshold; wherein the second attribute label includes a near exit label and a non-near exit label.

6. The method according to claim 2, characterized in that The path congestion information represents the path congestion information to reach the target parking space of each vehicle; The obstacle information represents the number of vehicles parked on the left and right sides of the target parking space of each vehicle; The parking space length information represents the length information of the target parking space; The parking space width information represents the width information of the target parking space; The charging pile parking space information is used to determine whether the target parking space is a charging pile parking space; The path preference information represents the path shape information of each vehicle driving into its respective target parking space; wherein the path preference information includes straight line driving information and broken line driving information.

7. The method according to claim 2, characterized in that The determining the parking record data of each vehicle according to the processed historical parking data includes: Calculating the average value of the distances between the candidate parking spaces corresponding to the respective vehicles and the respective elevator halls in the parking lot in the processed historical parking data to obtain the first average distance information; The second average distance information is obtained by calculating the average value of the distances between the candidate parking spaces of the respective vehicles and the exit of the parking lot in the processed historical parking data.

8. The method according to claim 1, characterized in that After determining whether the target vehicle is the first vehicle according to the identity information, the method further includes: If it is determined that the target vehicle is not the first vehicle, the target parking space is determined in an empty parking space in the parking lot based on the real-time position information of the target vehicle.

9. The method according to claim 1, characterized in that: If the target vehicle is a non-chargeable vehicle, determining the target parking space of the target vehicle based on the candidate parking spaces includes: Eliminate the charging pile parking spaces from the candidate parking spaces to obtain a first candidate parking space; The target parking space is determined based on the first candidate parking space.

10. An electronic device, characterized in that: The electronic device comprises an acquisition unit and a determination unit, The acquisition unit is used to acquire the identity information of the target vehicle when the target vehicle enters the parking lot; The determination unit is used to determine whether the target vehicle is a first vehicle according to the identity information; wherein the first vehicle represents a vehicle that has a parking record in the parking lot; if the target vehicle is determined to be the first vehicle, a candidate parking space corresponding to the target vehicle is determined based on a parking preference analysis model; wherein the parking preference analysis model includes a first decision tree model corresponding to each vehicle constructed based on parking record data of each vehicle that has a parking record in the parking lot, and a second decision tree model constructed based on a parking record data set of the parking lot; a target parking space for the target vehicle is determined based on the candidate parking spaces.

11. An electronic device, characterized in that: The electronic device includes a processor and a memory storing instructions executable by the processor; when the instructions are executed by the processor, the method according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images